| Model Name | Description | Status | Published | Action |
|---|---|---|---|---|
| Genfocus image-to-image |
GenFocus Model to Refocus Images
image-to-image |
OK | 1d | → |
| Genfocus image-to-image |
GenFocus Model to Refocus Images
image-to-image |
OK | 1d | → |
| Personaplex audio-to-audio |
PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.
audio |
OK | 2d | → |
| Workflow Utilities video-to-video |
FFMPEG Utility for Trim Video
video-to-video |
OK | 4d | → |
| Meshy 6 image-to-3d |
Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.
image-to-3d |
OK | 6d | → |
| Meshy 6 text-to-3d |
Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.
text-to-3d |
OK | 6d | → |
| Qwen Image Trainer V2 training |
Qwen Image LoRA training
lora personalization |
OK | 8d | → |
| Vidu image-to-video |
Vidu's Q3 Turbo Model
image-to-video |
OK | 9d | → |
| Vidu text-to-video |
Vidu's Q3 Turbo Model.
text-to-video |
OK | 9d | → |
| V2.6 video-to-video |
Wan 2.6 reference-to-video flash model.
reference-to-video |
OK | 9d | → |
| Bytedance video-to-video |
Transfer motion from a video to characters in an image using Dreamactor v2. Great performance for non-human and multiple characters
motion-control dreamactor |
OK | 9d | → |
| Flux 2 [klein] Realtime image-to-image |
Realtime generation with FLUX.2 [klein] from Black Forest Labs.
realtime image-to-image |
OK | 9d | → |
| Workflow Utilities audio-to-audio | FFMPEG Utility for Impulse Response | OK | 10d | → |
| Workflow Utilities image-to-image | FFMPEG Untility for Extracting nth Frame | OK | 10d | → |
| Workflow Utilities video-to-video | FFMPEG Utility for Blending Videos | OK | 10d | → |
| Workflow Utilities audio-to-audio | FFMPEG Utility for Audio Compression | OK | 10d | → |
| Kling Video v3 Text to Video [Pro] text-to-video |
Kling 3.0 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.
text-to-video |
OK | 11d | → |
| Kling O3 Image to Video [Pro] image-to-video |
Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.
image-to-video |
OK | 11d | → |
| Kling O3 Reference to Video [Pro] image-to-video |
Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.
reference-to-video |
OK | 11d | → |
| Kling O3 Text to Video [Pro] text-to-video |
Generate realistic videos using Kling O3 from Kling Team!
text-to-video |
OK | 11d | → |
| Kling O3 Text to Video [Standard] text-to-video |
Generate realistic videos using Kling O3 from Kling Team!
text-to-video |
OK | 11d | → |
| Kling O3 Reference to Video [Standard] image-to-video |
Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments.
reference-to-video |
OK | 11d | → |
| Kling Video v3 Text to Video [Standard] text-to-video |
Kling 3.0 Standard: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.
text-to-video |
OK | 11d | → |
| Kling O3 Image to Video [Pro] image-to-video |
Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance.
image-to-video |
OK | 11d | → |
| Kling O3 Edit Video [Standard] video-to-video |
Edit videos using Kling O3 from Kling Team!
video-to-video |
OK | 11d | → |
| Kling O3 Edit Video [Pro] video-to-video |
Edit videos using Kling O3 from Kling Team!
video-to-video |
OK | 11d | → |
| Kling O3 Reference Video to Video [Standard] video-to-video |
Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.
video-to-video |
OK | 11d | → |
| Kling Video v3 Image to Video [Standard] image-to-video |
Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.
image-to-video |
OK | 11d | → |
| Kling Video v3 Image to Video [Pro] image-to-video |
Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.
image-to-video |
OK | 11d | → |
| Kling O3 Reference Video to Video [Pro] video-to-video |
Kling O3 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity.
video-to-video |
OK | 11d | → |
| MiniMax Speech 2.8 [HD] text-to-speech | Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech. | OK | 11d | → |
| MiniMax Speech 2.8 [Turbo] text-to-speech | Generate speech from text prompts and different voices using the MiniMax Speech-2.8 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech. | OK | 11d | → |
| Kling Image text-to-image |
Kling V3: Latest Kling Image model
text-to-image |
OK | 12d | → |
| Kling Image image-to-image |
Kling Image V3: Latest kling image model
image-to-image |
OK | 12d | → |
| Kling Image image-to-image |
Kling Omni 3: Top-tier image-to-image with flawless consistency.
image-to-image |
OK | 12d | → |
| Kling Image text-to-image |
Kling Omni 3: Top-tier text-to-image with flawless consistency.
text-to-image |
OK | 12d | → |
| Vidu image-to-video |
Vidu's latest Q3 pro models.
image-to-video |
OK | 15d | → |
| Vidu text-to-video |
Vidu's latest Q3 pro models
text-to-video |
OK | 15d | → |
| Hunyuan 3d text-to-3d |
Create detailed, fully-textured 3D models with text
3d |
OK | 17d | → |
| Grok Imagine Image image-to-image |
Edit images precisely with xAI's Grok Imagine model
grok xai image-editing |
OK | 17d | → |
| Grok Imagine Image text-to-image |
Generate highly aesthetic images with xAI's Grok Imagine Image generation model.
xai grok text-to-image |
OK | 17d | → |
| Grok Imagine Video video-to-video |
Edit videos using xAI's Grok Imagine
video-edit v2v grok xai |
OK | 17d | → |
| Grok Imagine Video image-to-video |
Generate videos from images with audio using xAI's Grok Imagine Video model.
grok xai image-to-video i2v |
OK | 17d | → |
| Grok Imagine Video text-to-video |
Generate videos with audio from text using Grok Imagine Video.
xai grok t2v text-to-video |
OK | 17d | → |
| Hunyuan Image image-to-image |
Image editing endpoint for Hunyuan Image 3.0 Instruct.
tencent hunyuan-image instruct edit |
OK | 18d | → |
| Hunyuan Image 3.0 Instruct text-to-image |
Instruct version of Hunyuan-Image 3.0, with internal reasoning capabilities.
hunyuan-image v3 instruct |
OK | 18d | → |
| Hunyuan 3D Smart Topology 3d-to-3d |
Optimize 3D mesh topology with Hunyuan 3D Smart Topology.
3d hunyuan topology |
OK | 18d | → |
| Hunyuan 3D Rapid Image to 3D image-to-3d |
Rapidly generate 3D models from images using Hunyuan 3D.
3d hunyuan image-to-3d |
OK | 18d | → |
| Hunyuan 3D Pro Text to 3D text-to-3d |
Generate 3D models from text prompts with Hunyuan 3D Pro
3d hunyuan text-to-3d |
OK | 18d | → |
| Hunyuan 3D Pro Image to 3D image-to-3d |
Generate 3D models from images with Hunyuan 3D Pro
3d hunyuan image-to-3d |
OK | 18d | → |
| Z-Image Trainer training |
Fast LoRA trainer for Z-Image, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
lora personalization trainer |
OK | 18d | → |
| Hunyuan 3D Part Splitter 3d-to-3d |
Split 3D models into parts with Hunyuan 3D
3d hunyuan mesh |
OK | 18d | → |
| Qwen Image Max text-to-image |
Text-to-Image endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.
qwen-image max |
OK | 19d | → |
| Qwen Image Max image-to-image |
Image editing endpoint for Qwen-Image-Max. Qwen Image Max improves upon the Qwen Image Plus series by enhancing the realism and naturalness of images.
qwen-image max |
OK | 19d | → |
| Workflow Utilities unknown | ffmpeg utility to interleave videos | OK | 19d | → |
| Z Image Base (LoRA) text-to-image |
LoRA endpoint for Z-Image, the foundation model of the Z- Image family.
z-image base lora |
OK | 19d | → |
| Z Image Base text-to-image |
Z-Image is the foundation model of the Z- Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence.
z-image base |
OK | 19d | → |
| LTX-2 19B Distilled audio-to-video | Generate video with audio from audio, text and images using LTX-2 Distilled and custom LoRA | OK | 19d | → |
| LTX-2 19B audio-to-video | Generate video with audio from audio, text and images using LTX-2 and custom LoRA | OK | 19d | → |
| LTX-2 19B Distilled audio-to-video | Generate video with audio from audio, text and images using LTX-2 Distilled | OK | 19d | → |
| LTX-2 19B audio-to-video | Generate video with audio from audio, text and images using LTX-2 | OK | 19d | → |
| Replace Background image-to-image |
Creates enriched product shots by placing them in various environments using textual descriptions.
bria replace-background |
OK | 19d | → |
| Pixverse image-to-video |
Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.
image-to-video |
OK | 20d | → |
| Pixverse image-to-video |
Use the latest pixverse v5.6 model to turn your texts and images into amazing videos.
image-to-video |
OK | 20d | → |
| Pixverse text-to-video |
Use the latest pixverse v5.6 model to turn your texts into amazing videos.
text-to-video |
OK | 20d | → |
| Qwen 3 TTS - Voice Design [1.7B] text-to-speech |
Create custom voices using Qwen3-TTS Voice Design model and later use Clone Voice model to create your own voices!
text-to-speech voice-design |
OK | 20d | → |
| Qwen 3 TTS - Text to Speech [1.7B] text-to-speech |
Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model
text-to-speech |
OK | 20d | → |
| Qwen 3 TTS - Text to Speech [0.6B] text-to-speech |
Bring speech to your texts using Qwen3-TTS Custom-Voice model with pre-trained voices or use your custom voice with Qwen3-TTS Clone Voice model
text-to-speech |
OK | 20d | → |
| Qwen 3 TTS - Clone Voice [1.7B] unknown |
Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!
clone-voice voice-clone |
OK | 20d | → |
| Qwen 3 TTS - Clone Voice [0.6B] unknown |
Clone your voices using Qwen3-TTS Clone-Voice model with zero shot cloning capabilities and use it on text-to-speech models to create speeches of yours!
clone-voice voice-clone |
OK | 20d | → |
| Z Image Turbo Trainer V2 training |
Fast LoRA trainer for Z-Image-Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
lora personalization trainer |
OK | 22d | → |
| Ai Face Swap video-to-video |
AI-FaceSwap-Video is a service that can replace a person's face throughout a video clip while keeping their movements natural.
faceswap utility transformation |
OK | 23d | → |
| Ai Face Swap image-to-image |
AI-FaceSwap-Image is a service that can take one person's face and realistically blend it onto another's in a photo.
faceswap utility transformation |
OK | 23d | → |
| Fibo Edit [Structured Instruction] text-to-json |
Structured Instructions Generation endpoint for Fibo Edit, Bria's newest editing model.
structured-prompt-generation fibo-edit json |
OK | 26d | → |
| Fibo Edit [Replace Object by Text] image-to-image |
Natural, expressive object swapping within images using plain language
object-replacement bria fibo-edit json |
OK | 26d | → |
| Fibo Edit [Sketch to Image] image-to-image |
Converts line drawings and sketches into photorealistic, fully colored images
sketch-to-image bria fibo-edit json |
OK | 26d | → |
| Fibo Edit [Restore] image-to-image |
Automatically renews and cleans noisy or degraded images.
image-restoration fibo-edit bria json |
OK | 26d | → |
| Fibo Edit [Reseason] image-to-image |
Transforms the seasonal or weather atmosphere of an image.
bria fibo-edit reseason |
OK | 26d | → |
| Fibo Edit [Relight] image-to-image |
Precise, controllable lighting changes using simple, structured text inputs.
bria fibo-edit relighting json |
OK | 26d | → |
| Fibo Edit [Restyle] image-to-image |
Transforms images into distinct artistic styles using curated, production-grade style mappings
bria fibo-edit restyle json |
OK | 26d | → |
| Fibo Edit [Rewrite Text] image-to-image |
Precise, reliable modification of existing text inside images.
bria fibo-edit text-rewriting image-editing |
OK | 26d | → |
| Fibo Edit [Erase by Text] image-to-image |
Fast, reliable removal of unwanted elements from images. Designed for predictability, scale, and production use.
bria fibo-edit prompt-eraser |
OK | 26d | → |
| Fibo Edit image-to-image |
A high-quality editing model that achieves maximum controllability and transparency by combining JSON + Mask + Image.
bria fibo-edit image-editing json |
OK | 26d | → |
| Fibo Edit [Add Object by Text] image-to-image |
Precise, context-aware insertion of new objects into an existing image using simple, structured spatial commands.
bria fibo-edit object-addition json |
OK | 26d | → |
| Fibo Edit [Blend] image-to-image |
Complex, multi-step visual composition through natural language.
bria fibo-edit blend json |
OK | 26d | → |
| Fibo Edit [Colorize] image-to-image |
Transforms the color treatment of images using predefined, style-based commands
bria fibo-edit color |
OK | 26d | → |
| Vidu image-to-video | Use the latest Vidu Q2 Pro models which much more better quality and control on your videos. | OK | 27d | → |
| Flux 2 [klein] 9B Base Lora image-to-image | Image-to-image editing with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications. | OK | 27d | → |
| Flux 2 [klein] 9B Base Lora text-to-image | Text-to-image generation with LoRA support for FLUX.2 [klein] 9B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations. | OK | 27d | → |
| Flux 2 [klein] 4B Base Lora image-to-image | Image-to-image editing with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Specialized style transfer and domain-specific modifications. | OK | 27d | → |
| Flux 2 [klein] 4B Base Lora text-to-image | Text-to-image generation with LoRA support for FLUX.2 [klein] 4B Base from Black Forest Labs. Custom style adaptation and fine-tuned model variations. | OK | 27d | → |
| Nemotron audio-to-text | Use the fast speed and pin point accuracy of nemotron to transcribe your texts. | OK | 27d | → |
| Nemotron audio-to-text | Use the fast speed and pin point accuracy of nemotron to transcribe your texts. | OK | 27d | → |
| Fibo Lite text-to-json |
Structured Prompt Generation endpoint for Fibo-Lite, Bria's SOTA Open source model
bria fibo structured-prompt |
OK | 27d | → |
| Fibo Lite text-to-json |
Structured Prompt Generation endpoint for Fibo-Lite, Bria's SOTA Open source model
bria structured-prompting |
OK | 27d | → |
| V2.6 image-to-video | Wan 2.6 image-to-video flash model. | OK | 28d | → |
| Flux 2 Klein 9B Base Trainer training | Fine-tune FLUX.2 [klein] 4B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks. | OK | 29d | → |
| Flux 2 Klein 9B Base Trainer training | Fine-tune FLUX.2 [klein] 9B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks. | OK | 29d | → |
| Flux 2 Klein 4B Base Trainer training | Fine-tune FLUX.2 [klein] 4B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains. | OK | 29d | → |
| Flux 2 Klein image-to-image | Image-to-image editing with LoRA support for FLUX.2 [klein] 9B from Black Forest Labs. Specialized style transfer and domain-specific modifications. | Deprecated | 29d | → |
| Flux 2 Klein text-to-image | Text-to-image generation with LoRA support for FLUX.2 [klein] from Black Forest Labs. Custom style adaptation and fine-tuned model variations. | Deprecated | 29d | → |
| Flux 2 Klein 4B Base Trainer training | Fine-tune FLUX.2 [klein] 4B from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks. | OK | 29d | → |
| Flux 2 [klein] 4B Base image-to-image | Image-to-image editing with Flux 2 [klein] 4B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | OK | 1/15 | → |
| FLUX.2 [klein] 9B Base text-to-image | Text-to-image generation with FLUX.2 [klein] 9B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. | OK | 1/15 | → |
| Flux 2 [klein] 9B Base image-to-image | Image-to-image editing with Flux 2 [klein] 9B Base from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | OK | 1/15 | → |
| Flux 2 [klein] 4B Base text-to-image | Text-to-image generation with Flux 2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. | OK | 1/15 | → |
| Flux 2 [klein] 4B image-to-image | Image-to-image editing with Flux 2 [klein] 4B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | OK | 1/15 | → |
| Flux 2 [klein] 9B image-to-image | Image-to-image editing with Flux 2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | OK | 1/15 | → |
| FLUX.2 [klein] 9B text-to-image | Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. | OK | 1/15 | → |
| Flux 2 [klein] 4B text-to-image | Text-to-image generation with Flux 2 [klein] 4B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. | OK | 1/15 | → |
| ImagineArt 1.5 Pro Preview text-to-image |
ImagineArt 1.5 Pro is an advanced text-to-image model that creates ultra-high-fidelity 4K visuals with lifelike realism, refined aesthetics, and powerful creative output suited for professional use.
visuals imagineart realism text |
OK | 1/15 | → |
| Qwen Image 2512 Trainer V2 training |
Fast LoRA trainer for Qwen-Image-2512
lora personalization |
OK | 1/15 | → |
| Flux 2 [klein] 4B image-to-image | Image-to-image editing with Flux 2 [klein] 4B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | Deprecated | 1/15 | → |
| ElevenLabs Voice Changer audio-to-audio |
Change the voices in your audios with voices in ElevenLabs!
voice-change audio-to-audio |
OK | 1/14 | → |
| ElevenLabs Dubbing audio-to-video |
Generate dubbed videos or audios using ElevenLabs Dubbing feature!
dubbing audio-to-audio |
OK | 1/14 | → |
| ElevenLabs Speech to Text - Scribe V2 speech-to-text |
Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!
speech-to-text |
OK | 1/14 | → |
| Glm Image image-to-image |
Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.
image-to-image |
OK | 1/14 | → |
| Glm Image text-to-image |
Create high-quality images with accurate text rendering and rich knowledge details—supports editing, style transfer, and maintaining consistent characters across multiple images.
text-to-image |
OK | 1/14 | → |
| OpenRouter [Video][Enterprise] video-to-text | Run any VLM (Video Language Model) with fal, powered by OpenRouter. | OK | 1/13 | → |
| OpenRouter [Video] video-to-text | Run any VLM (Video Language Model) with fal, powered by OpenRouter. | OK | 1/13 | → |
| Nova SR audio-to-audio |
Enhance muffled 16 kHz speech audio into crystal-clear 48 kHz
speech-enhancements audio-super-resolution audio-sr |
OK | 1/13 | → |
| Flux 2 Trainer V2 training | Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks. | OK | 1/10 | → |
| Flux 2 Trainer V2 training | Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains. | OK | 1/10 | → |
| Longcat Multi Avatar audio-to-video |
LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.
audio-to-video image-to-video |
OK | 1/8 | → |
| Silero VAD audio-to-text |
Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model
vad silero voice-activity-detection |
OK | 1/8 | → |
| DeepFilterNet 3 audio-to-audio |
Enhance speech audio by removing background noise and upsampling to 48KHz
speech-enhancement |
OK | 1/7 | → |
| LTX-2 Video to Video Trainer training |
Train LTX-2 for video transformation or video-conditioned generation.
ltx2-video fine-tuning video-to-video |
OK | 1/7 | → |
| Qwen Image Edit 2511 Multiple Angles image-to-image |
Generates same scene from different angles (azimuth/elevation) with Qwen image Edit 2511 and the Lora Multiple Angles
stylized transform lora multi-angles multiples angles |
OK | 1/7 | → |
| LTX-2 19B Distilled video-to-video | Generate video with audio from videos using LTX-2 Distilled and custom LoRA | OK | 1/7 | → |
| LTX-2 19B Distilled video-to-video | Generate video with audio from videos using LTX-2 Distilled | OK | 1/7 | → |
| LTX-2 19B video-to-video | Generate video with audio from videos using LTX-2 and custom LoRA | OK | 1/7 | → |
| LTX-2 19B video-to-video | Generate video with audio from videos using LTX-2 | OK | 1/7 | → |
| Ultrashape 3d-to-3d |
UltraShape-1.0 is a 3D diffusion framework that generates high-fidelity 3D geometry through coarse-to-fine geometric refinement.
3d-to-3d |
OK | 1/6 | → |
| LTX-2 19B Distilled video-to-video | Extend videos with audio using LTX-2 Distilled and custom LoRA | OK | 1/5 | → |
| LTX-2 19B Distilled video-to-video | Extend videos with audio using LTX-2 Distilled | OK | 1/5 | → |
| LTX-2 19B Distilled image-to-video | Generate video with audio from images using LTX-2 Distilled and custom LoRA | OK | 1/5 | → |
| LTX-2 19B Distilled image-to-video | Generate video with audio from images using LTX-2 Distilled | OK | 1/5 | → |
| LTX-2 19B Distilled text-to-video | Generate video with audio from text using LTX-2 Distilled and custom LoRA | OK | 1/5 | → |
| LTX-2 19B Distilled text-to-video | Generate video with audio from text using LTX-2 Distilled | OK | 1/5 | → |
| LTX-2 19B video-to-video | Extend video with audio using LTX-2 and custom LoRA | OK | 1/5 | → |
| LTX-2 19B text-to-video | Generate video with audio from text using LTX-2 and custom LoRA | OK | 1/5 | → |
| LTX-2 19B image-to-video | Generate video with audio from images using LTX-2 and custom LoRA | OK | 1/5 | → |
| LTX-2 19B video-to-video | Extend video with audio using LTX-2 | OK | 1/5 | → |
| LTX-2 19B text-to-video | Generate video with audio from text using LTX-2 | OK | 1/5 | → |
| LTX-2 19B image-to-video | Generate video with audio from images using LTX-2 | OK | 1/5 | → |
| LTX-2 Video Trainer training |
Train LTX-2 for custom styles and effects.
ltx2-video fine-tuning |
OK | 1/3 | → |
| Qwen Image 2512 text-to-image |
LoRA inference endpoint for Qwen Image 2512, an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.
qwen 2512 lora |
OK | 1/2 | → |
| Qwen Image 2512 Trainer training |
Qwen Image 2512 LoRA training
lora personalization |
OK | 1/1 | → |
| Qwen Image Edit 2511 image-to-image |
Endpoint for Qwen's Image Editing 2511 model with LoRa support.
stylized transform lora |
OK | 2025/12/30 | → |
| Qwen Image 2512 text-to-image |
Qwen Image 2512 is an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation.
qwen 2512 |
OK | 2025/12/30 | → |
| Longcat Multi Avatar audio-to-video |
LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.
audio-to-video image-to-video |
OK | 2025/12/30 | → |
| Longcat Single Avatar audio-to-video |
LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.
audio-to-video image-to-video |
OK | 2025/12/30 | → |
| Longcat Single Avatar audio-to-video |
LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.
audio-to-video |
OK | 2025/12/30 | → |
| Sam Audio audio-to-audio |
Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.
audio-to-audio sam-audio |
OK | 2025/12/30 | → |
| Sam Audio audio-to-audio |
Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.
audio-to-audio sam-audio |
OK | 2025/12/30 | → |
| Sam Audio video-to-audio |
Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.
video-to-audio sam-audio |
OK | 2025/12/30 | → |
| Ai Home image-to-image |
AI Home Style reimagines your home interior and exterior design with bold, prompt-driven concepts
stylized transform |
OK | 2025/12/30 | → |
| Ai Home image-to-image |
AI Home Edit transforms your home interior and exterior photos with realistic, prompt-based edits
stylized transform |
OK | 2025/12/30 | → |
| Hunyuan Motion [0.46B] text-to-3d |
Generate 3D human motions via text-to-generation interface of Hunyuan Motion!
text-to-3d motion |
OK | 2025/12/30 | → |
| Hunyuan Motion [1B] text-to-3d |
Generate 3D human motions via text-to-generation interface of Hunyuan Motion!
text-to-3d motion |
OK | 2025/12/30 | → |
| Arbiter vision |
Semantic image alignment measurements
clip-score |
OK | 2025/12/26 | → |
| Arbiter vision |
Image reference comparison measurements
dists sdi mse ssim lpips |
OK | 2025/12/26 | → |
| Arbiter vision |
Reference-free image measurements
arniqa nima iqa musiq |
OK | 2025/12/26 | → |
| Wan Move [480p] image-to-video |
Use Wan-Move to generate videos with controlled the motion using trajectories
image-to-video motion-control motion |
OK | 2025/12/24 | → |
| Qwen Image Layered image-to-image |
Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. Use loras to get your custom outputs.
qwen lora |
OK | 2025/12/24 | → |
| FFmpeg API [Merge Audios] audio-to-audio |
Merge audios into a single audio using FFmpeg API!
ffmpeg |
OK | 2025/12/23 | → |
| Wan v2.6 Text to Image text-to-image |
Wan 2.6 text-to-image model.
text-to-image |
OK | 2025/12/23 | → |
| Wan v2.6 Image to Image image-to-image |
Wan 2.6 image-to-image model.
image-to-image |
OK | 2025/12/23 | → |
| Video video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.
bria video erase keypoints |
OK | 2025/12/23 | → |
| Video video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency
bria video erase |
OK | 2025/12/23 | → |
| Video video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.
bria video erase |
OK | 2025/12/23 | → |
| Qwen Image Edit 2511 Trainer training | LoRA trainer for Qwen Image Edit 2511 | OK | 2025/12/23 | → |
| Kandinsky5 Pro image-to-video | Kandinsky 5.0 Pro is a diffusion model for fast, high-quality image-to-video generation. | OK | 2025/12/23 | → |
| Kandinsky5 Pro text-to-video | Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation. | OK | 2025/12/23 | → |
| Bytedance text-to-video |
Generate videos with audio with Seedance 1.5
bytedance seedance audio |
OK | 2025/12/23 | → |
| Bytedance image-to-video |
Generate videos with audio with Seedance 1.5 (supports start & end frame)
bytedance seedance audio |
OK | 2025/12/23 | → |
| Qwen Image Layered Trainer training |
Train LoRAs for the Qwen-Image-Layered model, customize how images are split into layers.
qwen layer trainer |
OK | 2025/12/23 | → |
| Live Avatar image-to-video |
Real-time avatar generation with Live Avatar. Have natural face-to-face conversations with AI avatars that respond instantly—streaming infinite-length video with immediate visual feedback.
realtime image-to-video audio-to-video |
OK | 2025/12/22 | → |
| OpenRouter [Audio] unknown | Run any ALM (Audio Language Model) with fal, powered by OpenRouter. | OK | 2025/12/22 | → |
| Elevenlabs Music text-to-audio |
Generate high quality, realistic music with fine controls using Elevenlabs Music!
music text-to-music |
OK | 2025/12/22 | → |
| Lightx video-to-video |
Use tlightx capabilities to relight and recamera your videos.
video-to-video |
OK | 2025/12/22 | → |
| Lightx video-to-video |
Use the capabilities of lightx to relight and recamera your videos.
video-to-video recamera relight |
OK | 2025/12/22 | → |
| Kling Video v2.6 Motion Control [Standard] video-to-video | Transfer movements from a reference video to any character image. Cost-effective mode for motion transfer, perfect for portraits and simple animations. | OK | 2025/12/21 | → |
| Kling Video v2.6 Motion Control [Pro] video-to-video | Transfer movements from a reference video to any character image. Pro mode delivers higher quality output, ideal for complex dance moves and gestures. | OK | 2025/12/21 | → |
| Qwen Image Edit 2511 image-to-image |
Endpoint for Qwen's Image Editing 2511 model.
stylized transform |
OK | 2025/12/19 | → |
| Qwen Image Layered image-to-image |
Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers.
qwen layer |
OK | 2025/12/19 | → |
| Lucy Restyle video-to-video |
Restyle videos up to 30 min long - maintaining maximum detail quality.
video-edit |
OK | 2025/12/18 | → |
| Z-Image Turbo image-to-image |
Generate images from text, an image, a mask and custom LoRA using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
inpainting |
OK | 2025/12/18 | → |
| Z-Image Turbo image-to-image |
Generate images from text, an image and a mask using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
inpainting |
OK | 2025/12/18 | → |
| Trellis 2 image-to-3d |
Generate 3D models from your images using Trellis 2. A native 3D generative model enabling versatile and high-quality 3D asset creation.
image-to-3D |
OK | 2025/12/17 | → |
| Scail video-to-video | SCAIL is a character animation model that uses 3D consistent pose representations to animate reference images with coherent motion, supporting complex movements. | OK | 2025/12/17 | → |
| Crystal Upscaler [Video] video-to-video |
Do high precision video upscaling that respects the original video perfectly using Crystal Upscaler's new video upscaling method!
upscale video-to-video |
OK | 2025/12/17 | → |
| Vibevoice text-to-speech |
Generate long speech snippets fast using Microsoft's powerful TTS.
vibevoice fast |
OK | 2025/12/17 | → |
| Bria Video Eraser video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.
bria erase |
OK | 2025/12/17 | → |
| Bria Video Eraser video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency.
bria erase |
OK | 2025/12/17 | → |
| Bria Video Eraser video-to-video |
A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency
bria erase |
OK | 2025/12/17 | → |
| Hunyuan Video V1.5 image-to-video |
Hunyuan Video 1.5 is Tencent's latest and best video model
image-to-video |
OK | 2025/12/17 | → |
| Hunyuan3d V3 text-to-3d | Turn simple sketches into detailed, fully-textured 3D models. Instantly convert your concept designs into formats ready for Unity, Unreal, and Blender. | OK | 2025/12/16 | → |
| Hunyuan3d V3 image-to-3d | Create your imagined 3D models with just text. Production-ready, export-ready professional assets with realistic lighting and materials in minutes. | OK | 2025/12/16 | → |
| Hunyuan3d V3 image-to-3d | Transform your photos into ultra-high-resolution 3D models in seconds. Film-quality geometry with PBR textures, ready for games, e-commerce, and 3D printing. | OK | 2025/12/16 | → |
| Flux 2 image-to-image | Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—in a flash. | OK | 2025/12/16 | → |
| Flux 2 text-to-image | Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities— in a flash. | OK | 2025/12/16 | → |
| GPT-Image 1.5 image-to-image |
GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.
openai gpt-image |
OK | 2025/12/16 | → |
| GPT-Image 1.5 text-to-image |
GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail.
openai gpt-image |
OK | 2025/12/16 | → |
| Kling Video Create Voice audio-to-audio | Create Voices to be used with Kling Models Voice Control | OK | 2025/12/16 | → |
| Fibo Lite text-to-image |
Fibo Lite, the new addition to the Fibo model family, allows generating high-quality images with the same controllability of the JSON structured prompt with significantly improved latency.
bria fibo lite |
OK | 2025/12/16 | → |
| Flux 2 image-to-image | Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—all at turbo speed. | OK | 2025/12/16 | → |
| Flux 2 text-to-image | Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities—all at turbo speed. | OK | 2025/12/16 | → |
| Flux 2 Max text-to-image |
FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.
flux2 max |
OK | 2025/12/16 | → |
| Flux 2 Max image-to-image |
FLUX.2 [max] delivers state-of-the-art image generation and advanced image editing with exceptional realism, precision, and consistency.
flux2 image-editing high-quality |
OK | 2025/12/16 | → |
| Ai Baby And Aging Generator image-to-image |
AI Baby Generator is a service that instantly creates realistic predictions of a future child from parent photos.
stylized transform |
OK | 2025/12/16 | → |
| Ai Baby And Aging Generator image-to-image |
AI Aging Generator performs controllable age progression or regression from a single face photo, generating lifelike portraits across eight age groups from baby to senior.
utility editing |
OK | 2025/12/16 | → |
| Ai Detector vision |
AI Detector (Image) is an advanced service that analyzes a single picture and returns a verdict on whether it was likely created by AI.
utility |
OK | 2025/12/16 | → |
| Ai Detector text-to-text |
AI Detector (Text) is an advanced AI service that analyzes a passage and returns a verdict on whether it was likely written by AI.
utility |
OK | 2025/12/16 | → |
| Wan v2.6 Text to Video text-to-video |
Wan 2.6 text-to-video model.
text-to-video |
OK | 2025/12/16 | → |
| Wan v2.6 Reference to Video video-to-video |
Wan 2.6 reference-to-video model.
reference-to-video |
OK | 2025/12/16 | → |
| Wan 2.6 video-to-video |
Wan 2.6 reference-to-video model.
reference-to-video |
Deprecated | 2025/12/16 | → |
| Wan 2.6 text-to-video |
Wan 2.6 text-to-video model.
text-to-video |
Deprecated | 2025/12/16 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Apply designs/graphics onto people's shirts
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Remove existing lighting and apply soft, even illumination
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Remove unwanted elements (objects, people, text) while maintaining image consistency
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Blend products into backgrounds with automatic perspective and lighting correction
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Create group photos
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Generate full portrait from a cropped face photo
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Add a realistic scene behind the object with white background
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Create cinematic transitions and scene progressions (camera movements, framing changes)
stylized transform |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora Gallery image-to-image |
Precise camera position and angle control (rotation, zoom, vertical movement)
stylized transform |
OK | 2025/12/15 | → |
| Veo 3.1 Fast video-to-video |
Extend Veo-Created Videos up to 30 seconds
extend-video |
OK | 2025/12/15 | → |
| Veo 3.1 video-to-video |
Extend Veo-Created Videos up to 30 seconds
extend-video |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Lora image-to-image |
LoRA endpoint for the Qwen Image Edit 2509 model.
image-to-image image-editing |
OK | 2025/12/15 | → |
| Qwen Image Edit 2509 Trainer training | LoRA trainer for Qwen Image Edit 2509 | OK | 2025/12/15 | → |
| Qwen Image Edit 2509 image-to-image |
Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.
image-editing image-to-image high-quality-text |
OK | 2025/12/15 | → |
| Wan v2.6 Image to Video image-to-video |
Wan 2.6 image-to-video model.
image-to-video |
OK | 2025/12/15 | → |
| Kling O1 Reference Image to Video [Standard] image-to-video | Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments. | OK | 2025/12/15 | → |
| Kling O1 First Frame Last Frame to Video [Standard] image-to-video | Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance. | OK | 2025/12/15 | → |
| Kling O1 Reference Video to Video [Standard] video-to-video | Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity. | OK | 2025/12/15 | → |
| Kling O1 Edit Video [Standard] video-to-video | Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure. | OK | 2025/12/15 | → |
| Chatterbox Turbo text-to-speech |
Turbo-charged voice generation. Control every breath, laugh, and sigh with inline tags - now at turbo speed.
text-to-speech |
Deprecated | 2025/12/15 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.
stylized transform |
OK | 2025/12/12 | → |
| Maya text-to-speech |
Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
text-to-speech tts |
OK | 2025/12/12 | → |
| Maya text-to-speech |
Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
text-to-speech tts |
OK | 2025/12/12 | → |
| Moondream3 Preview [Segment] image-to-image |
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
mask segmentation |
OK | 2025/12/12 | → |
| Fabric 1.0 text-to-video |
VEED Fabric 1.0 text-to-video API
lipsync avatar text-to-video |
OK | 2025/12/12 | → |
| Steady Dancer video-to-video | Create smooth, realistic videos from a single photo while keeping the original appearance intact—precise motion control without losing identity or visual quality. | OK | 2025/12/11 | → |
| One To All Animation video-to-video |
One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes
video to video motion |
OK | 2025/12/11 | → |
| One To All Animation video-to-video |
One-to-All Animation is a pose driven video model that animates characters from a single reference image, enabling flexible, alignment-free motion transfer across diverse styles and scenes
video to video motion |
OK | 2025/12/11 | → |
| Creatify Aurora image-to-video |
Generate high fidelity, studio quality videos of your avatar speaking or singing using the Aurora from Creatify team!
lipsync image-to-video |
OK | 2025/12/11 | → |
| Wan Vision Enhancer video-to-video |
Wan Vision Enhancer for magnify/enhance video with high fidelity and creativity.
stylized transform |
OK | 2025/12/10 | → |
| Sync React-1 video-to-video |
Use React-1 from SyncLabs to refine human emotions and do realistic lip-sync without losing details!
lipsync video-to-video |
OK | 2025/12/10 | → |
| Stepx Edit2 image-to-image | Image-to-image editing with Step1X-Edit v2 from StepFun. Reasoning-enhanced modifications through a thinking–editing–reflection loop with MLLM world knowledge for abstract instruction comprehension. | OK | 2025/12/9 | → |
| Z-Image Turbo image-to-image |
Generate images from text and edge, depth or pose images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
turbo z-image fast lora |
OK | 2025/12/7 | → |
| Z-Image Turbo image-to-image | Generate images from text and edge, depth or pose images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model. | OK | 2025/12/7 | → |
| Z-Image Turbo image-to-image |
Generate images from text and images using custom LoRA and Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
turbo z-image fast lora |
OK | 2025/12/7 | → |
| Z-Image Turbo image-to-image |
Generate images from text and images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.
turbo z-image fast |
OK | 2025/12/7 | → |
| Longcat Image image-to-image | LongCat image Edit is a 6B parameter image editing model excelling at multilingual text rendering, photorealism and deployment efficiency. | OK | 2025/12/5 | → |
| Longcat Image text-to-image | LongCat image is a 6B parameter model excelling at multilingual text rendering, photorealism and deployment efficiency. | OK | 2025/12/5 | → |
| Kling AI Avatar v2 Pro image-to-video | Kling AI Avatar v2 Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters | OK | 2025/12/4 | → |
| Kling AI Avatar v2 Standard image-to-video | Kling AI Avatar v2 Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters | OK | 2025/12/4 | → |
| Z Image Trainer training |
Train LoRAs on Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
turbo z-image fast trainer |
OK | 2025/12/3 | → |
| Bytedance text-to-image |
A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.
stylized transform |
OK | 2025/12/3 | → |
| Bytedance image-to-image |
A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.
stylized transform |
OK | 2025/12/3 | → |
| Sam 3 3d-to-3d |
SAM 3D enables full scene reconstructions, placing objects and humans in a shared context together.
align 3D |
OK | 2025/12/2 | → |
| Sam 3 image-to-3d |
SAM 3D allows for accurate 3D reconstruction of human body shape and position from a single image.
3d human pose |
OK | 2025/12/2 | → |
| Sam 3 image-to-3d |
SAM 3D enables precise 3D reconstruction of objects from real images, while accurately reconstructing their geometry and texture.
3d object |
OK | 2025/12/2 | → |
| Vidu image-to-image |
Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.
images-to-imag reference-to-image |
OK | 2025/12/2 | → |
| Vidu text-to-image | Use vidu Text-to-Image to turn your prompts into reality. | OK | 2025/12/2 | → |
| Kling Video v2.6 Text to Video text-to-video | Kling 2.6 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation. | OK | 2025/12/2 | → |
| Kling Video v2.6 Image to Video image-to-video | Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation. | OK | 2025/12/2 | → |
| Pixverse image-to-video | Pixverse Effects | OK | 2025/12/2 | → |
| Pixverse image-to-video | Pixverse Transition | OK | 2025/12/2 | → |
| Z-Image Turbo text-to-image |
Text-to-Image endpoint with LoRA support for Z-Image Turbo, a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
z-image lora fast |
OK | 2025/12/1 | → |
| Pixverse image-to-video |
Generate high quality video clips from text and image prompts using PixVerse v5.5
image-to-video |
OK | 2025/12/1 | → |
| Pixverse text-to-video |
Generate high quality video clips from text and image prompts using PixVerse v5.5
text-to-video |
OK | 2025/12/1 | → |
| Video Background Removal video-to-video | Remove background from any video with people and objects. No green screen needed. | OK | 2025/12/1 | → |
| Kling O1 First Frame Last Frame to Video [Pro] image-to-video | Generate a video by taking a start frame and an end frame, animating the transition between them while following text-driven style and scene guidance. | OK | 2025/12/1 | → |
| Kling O1 Reference Image to Video [Pro] image-to-video | Transform images, elements, and text into consistent, high-quality video scenes, ensuring stable character identity, object details, and environments. | OK | 2025/12/1 | → |
| Kling O1 Edit Video [Pro] video-to-video | Edit an existing video using natural-language instructions, transforming subjects, settings, and style while retaining the original motion structure. | OK | 2025/12/1 | → |
| Kling O1 Reference Video to Video [Pro] video-to-video | Kling O1 Omni generates new shots guided by an input reference video, preserving cinematic language such as motion, and camera style to produce seamless scene continuity. | OK | 2025/12/1 | → |
| Kling O1 Image image-to-image |
Perform precise image edits using strong reference control, transforming subjects, styles, and local details while preserving visual consistency.
edit realism typography |
OK | 2025/12/1 | → |
| Ovis Image text-to-image |
Ovis-Image is a 7B text-to-image model specifically optimized for quick, high quality text rendering.
ovis-image artistic |
OK | 2025/11/29 | → |
| Video Background Removal video-to-video | Remove background from any video with people and objects. No green screen needed. | OK | 2025/11/28 | → |
| Video Background Removal video-to-video | Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges. | OK | 2025/11/28 | → |
| LTX Video 2.0 Fast text-to-video | Create high-fidelity video with audio from text with LTX-2 Fast | OK | 2025/11/26 | → |
| LTX Video 2.0 Pro text-to-video | Create high-fidelity video with audio from text with LTX-2 Pro. | OK | 2025/11/26 | → |
| LTX Video 2.0 Fast image-to-video | Create high-fidelity video with audio from images with LTX-2 Fast | OK | 2025/11/26 | → |
| LTX Video 2.0 Pro image-to-video | Create high-fidelity video with audio from images with LTX-2 Pro | OK | 2025/11/26 | → |
| LTX Video 2.0 Retake video-to-video | Change sections of a video using LTX-2 | OK | 2025/11/26 | → |
| Z-Image Turbo text-to-image |
Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
turbo z-image fast |
OK | 2025/11/26 | → |
| LTX Video 2.0 Retake video-to-video | Change sections of a video using LTX-2 | Deprecated | 2025/11/26 | → |
| Lucy Edit [Fast] video-to-video |
Lucy Edit Fast is a rapid, localized video editing model that lets you modify specific elements like objects, or backgrounds in just 10 seconds.
edit video-edit |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
Applies sepia vintage effect to images
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery image-to-image |
Virtual clothing try-on (2 images: person + garment)
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
Generates satellite/aerial view style images
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
Makes images more photorealistic and natural
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery image-to-image |
Generates same object from different angles (azimuth/elevation)
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
HDR surrealistic effect with intense colors
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery image-to-image |
Extends a face into a full body portrait
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
Transforms images into comic book style
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery text-to-image |
Ballpoint pen sketch drawing style
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery image-to-image |
Virtually furnishes an empty apartment
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 Lora Gallery image-to-image |
Add a background to images with white/clean background
stylized transform |
OK | 2025/11/25 | → |
| Crystal Upscaler image-to-image |
An advanced image enhancement tool designed specifically for facial details and portrait photography, utilizing Clarity AI's upscaling technology.
image-to-image |
OK | 2025/11/25 | → |
| Flux 2 Trainer training | Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks. | OK | 2025/11/25 | → |
| Flux 2 Trainer training | Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific styles and domains. | OK | 2025/11/25 | → |
| Flux 2 Flex image-to-image | Image editing with FLUX.2 [flex] from Black Forest Labs. Supports multi-reference editing with customizable inference steps and enhanced text rendering. | OK | 2025/11/25 | → |
| Flux 2 Flex text-to-image |
Text-to-image generation with FLUX.2 [flex] from Black Forest Labs. Features adjustable inference steps and guidance scale for fine-tuned control. Enhanced typography and text rendering capabilities.
stylized transform |
OK | 2025/11/25 | → |
| Flux 2 image-to-image | Image-to-image editing with LoRA support for FLUX.2 [dev] from Black Forest Labs. Specialized style transfer and domain-specific modifications. | OK | 2025/11/23 | → |
| Flux 2 text-to-image | Text-to-image generation with LoRA support for FLUX.2 [dev] from Black Forest Labs. Custom style adaptation and fine-tuned model variations. | OK | 2025/11/23 | → |
| Flux 2 image-to-image | Image-to-image editing with FLUX.2 [dev] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control. | OK | 2025/11/23 | → |
| Flux 2 text-to-image | Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. | OK | 2025/11/23 | → |
| Flux 2 Pro text-to-image | Image editing with FLUX.2 [pro] from Black Forest Labs. Ideal for high-quality image manipulation, style transfer, and sequential editing workflows | OK | 2025/11/23 | → |
| Flux 2 Pro image-to-image | Text-to-image generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images. | OK | 2025/11/23 | → |
| Chrono Edit Lora image-to-image |
LoRA endpoint for the Chrono Edit model.
image-to-image image-editing |
OK | 2025/11/21 | → |
| Chrono Edit Lora Gallery image-to-image |
You can make edits simply by drawing a quick sketch on the input image.
paint edit sketch |
OK | 2025/11/21 | → |
| Chrono Edit Lora Gallery image-to-image |
Upscales and cleans up the image.
upscale details |
OK | 2025/11/21 | → |
| Hunyuan Video V1.5 text-to-video |
Hunyuan Video 1.5 is Tencent's latest and best video model
hunyuan-video text-to-video |
OK | 2025/11/21 | → |
| Sam 3 image-to-image |
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
segmentation rle real-time |
OK | 2025/11/20 | → |
| Sam 3 vision |
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
embeddings mask real-time |
OK | 2025/11/20 | → |
| Sam 3 video-to-video |
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
segmentation mask real-time rle |
OK | 2025/11/20 | → |
| Sam 3 video-to-video |
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
segmentation mask real-time |
OK | 2025/11/20 | → |
| Segment Anything Model 3 image-to-image |
SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks.
segmentation mask real-time |
OK | 2025/11/20 | → |
| Gemini 3 Pro Image Preview image-to-image |
Nano Banana Pro (a.k.a Nano Banana 2) is Google's new state-of-the-art image generation and editing model
realism typography |
OK | 2025/11/20 | → |
| Gemini 3 Pro Image Preview text-to-image |
Nano Banana Pro (a.k.a Nano Banana 2) is Google's new state-of-the-art image generation and editing model
realism typography |
OK | 2025/11/20 | → |
| Nano Banana Pro image-to-image |
Nano Banana Pro (a.k.a Nano Banana 2) is Google's new state-of-the-art image generation and editing model
realism typography |
OK | 2025/11/20 | → |
| Nano Banana Pro text-to-image |
Nano Banana Pro (a.k.a Nano Banana 2) is Google's new state-of-the-art image generation and editing model
realism typography |
OK | 2025/11/20 | → |
| Imagineart 1.5 Preview text-to-image |
ImagineArt 1.5 text-to-image model generates high-fidelity professional-grade visuals with lifelike realism, strong aesthetics, and text that actually reads correctly.
visuals imagineart realism text |
OK | 2025/11/20 | → |
| Lynx image-to-video |
Generate subject consistent videos using Lynx from ByteDance!
image-to-video subject |
OK | 2025/11/18 | → |
| Maya1 text-to-speech |
Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
text-to-speech tts |
OK | 2025/11/15 | → |
| OpenRouter Responses [OpenAI Compatible] llm | The OpenRouter Responses API with fal, powered by OpenRouter, provides unified access to a wide range of large language models - including GPT, Claude, Gemini, and many others through a single API interface. | OK | 2025/11/13 | → |
| Fibo Mashup image-to-image |
Combine three images to create an amazing mashup image with Bria's FIBO model.
bria fibo image-to-image |
Deprecated | 2025/11/13 | → |
| OpenRouter Embeddings [OpenAI Compatible] llm | The OpenRouter Embeddings API with fal, powered by OpenRouter, provides unified access to a wide range of large language models - including GPT, Claude, Gemini, and many others through a single API interface. | OK | 2025/11/12 | → |
| OpenRouter [Vision] vision | Run any VLM (Vision Language Model) with fal, powered by OpenRouter. | OK | 2025/11/12 | → |
| OpenRouter llm | Run any LLM (Large Language Model) with fal, powered by OpenRouter. | OK | 2025/11/12 | → |
| OpenRouter Chat Completions [OpenAI Compatible] llm | Run any LLM (Large Language Model) with fal, powered by OpenRouter. This endpoint is compatible with the OpenAI API. | OK | 2025/11/12 | → |
| Editto video-to-video |
Edit videos using instruction-based prompting using Editto model!
video-edit wan-vace |
OK | 2025/11/12 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Precise camera position and angle control (rotation, zoom, vertical movement)
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Apply designs/graphics onto people's shirts
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Remove existing lighting and apply soft, even illumination
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Remove unwanted elements (objects, people, text) while maintaining image consistency
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Create cinematic transitions and scene progressions (camera movements, framing changes)
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Blend products into backgrounds with automatic perspective and lighting correction
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Create group photos
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Generate full portrait from a cropped face photo
stylized transform |
OK | 2025/11/11 | → |
| Qwen Image Edit Plus Lora Gallery image-to-image |
Add a realistic scene behind the object with white background
stylized transform |
OK | 2025/11/11 | → |
| Flashvsr video-to-video |
Upscale your videos using FlashVSR with the fastest speeds!
upscale video-to-video |
OK | 2025/11/11 | → |
| Pixverse image-to-video | Generate high quality video clips by swapping person, objects and background using Pixverse Swap. | OK | 2025/11/10 | → |
| Pika image-to-video | Discover ultimate control with Pikaframes key frame interpolation, a stunning image-to-video feature that allows you to upload up to 5 keyframes, customize their transition length and prompt, and see their images come to life as seamless videos. | OK | 2025/11/7 | → |
| Infinity Star text-to-video |
InfinityStar’s unified 8B spacetime autoregressive engine to turn any text prompt into crisp 720p videos - 10× faster than diffusion models.
text-to-video |
OK | 2025/11/7 | → |
| Sana Video text-to-video |
Leverage Sana's ultra-fast processing speed to generate high-quality assets that transform your text prompts into production-ready videos
text-to-video |
OK | 2025/11/7 | → |
| Crystal Upscaler image-to-image |
An advanced image enhancement tool designed specifically for facial details and portrait photography, utilizing Clarity AI's upscaling technology.
image-to-image |
Deprecated | 2025/11/5 | → |
| Workflow Utilities video-to-video |
Add automatic subtitles to videos
auto-subtitle captioning |
OK | 2025/11/4 | → |
| Reve image-to-image |
Reve’s fast remix model lets you upload an reference images and then combine/transform them via a text prompt at lightning speed!
image-to-image |
OK | 2025/11/4 | → |
| Reve image-to-image |
Reve’s fast edit model lets you upload an existing image and then transform it via a text prompt at lightning speed!
image-to-image |
OK | 2025/11/4 | → |
| Image Outpaint image-to-image |
Directional outpainting. Choose edges to expand. left, right, top, or center (uniform all sides). Only expanded areas are generated; an optional zoom-out pulls the frame back by the chosen amount.
outpainting |
OK | 2025/11/3 | → |
| Fashion Size Estimator vision |
Fashion Size Estimator model analyzes human body images to predict clothing size recommendations and estimate key body measurements including height, bust, waist, and hip dimensions.
utility editing |
Deprecated | 2025/11/3 | → |
| Flux Vision Upscaler image-to-image | Flux Vision Upscaler for magnify/upscaling images with high fidelity and creativity. | OK | 2025/11/2 | → |
| Emu 3.5 Image image-to-image | Edit images with a text prompt using Emu 3.5 Image | OK | 2025/11/1 | → |
| Emu 3.5 Image text-to-image | Generate images from text using Emu 3.5 Image | OK | 2025/11/1 | → |
| Sima Video Upscaler Lite video-to-video |
Upscale your videos at real-time speeds with Sima Labs!
upscale video-to-video |
Deprecated | 2025/10/31 | → |
| Bytedance Upscaler video-to-video |
Upscale videos with Bytedance's video upscaler.
upscaler video bytedance |
OK | 2025/10/31 | → |
| Sima Upscaler image-to-image |
Upscale your images at blazingly fast speeds with Sima Labs!
upscale image-to-image |
Deprecated | 2025/10/31 | → |
| Chrono Edit image-to-image |
NVIDIA's Logically Consistent and Physics-Aware Image Editing Model
image-editing |
OK | 2025/10/30 | → |
| Minimax Music text-to-audio |
Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.
music audio |
OK | 2025/10/30 | → |
| Qwen Image Edit Plus Trainer training | LoRA trainer for Qwen Image Edit Plus | OK | 2025/10/30 | → |
| Qwen Image Edit Trainer training | LoRA trainer for Qwen Image Edit | OK | 2025/10/30 | → |
| LongCat Video text-to-video | Generate long videos in 720p/30fps from text using LongCat Video | OK | 2025/10/30 | → |
| LongCat Video image-to-video | Generate long videos in 720p/30fps from images using LongCat Video | OK | 2025/10/30 | → |
| LongCat Video image-to-video | Generate long videos from images using LongCat Video | OK | 2025/10/30 | → |
| LongCat Video text-to-video | Generate long videos from text using LongCat Video | OK | 2025/10/30 | → |
| LongCat Video Distilled image-to-video | Generate long videos in 720p/30fps from images using LongCat Video Distilled | OK | 2025/10/30 | → |
| LongCat Video Distilled text-to-video | Generate long videos in 720p/30fps from text using LongCat Video Distilled | OK | 2025/10/30 | → |
| Fibo text-to-json |
Structured Prompt Generation endpoint for Fibo, Bria's SOTA Open source model
bria fibo structured-prompting |
OK | 2025/10/29 | → |
| Omnipart image-to-3d | Image-to-3D endpoint for OmniPart, a part-aware 3D generator with semantic decoupling and structural cohesion. | OK | 2025/10/29 | → |
| MiniMax Speech 2.6 [Turbo] text-to-speech |
Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
text-to-speech |
OK | 2025/10/29 | → |
| MiniMax Speech 2.6 [HD] text-to-speech |
Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
text-to-speech |
OK | 2025/10/29 | → |
| Video As Prompt video-to-video |
A model for unified semantic control in video generation. It animates a static reference image using the motion and semantics from a reference video as a prompt.
video-as-prompt semantic control |
OK | 2025/10/29 | → |
| Bytedance image-to-3d |
Image to 3D endpoint for Bytedance's high-quality Seed3D 3d model generator.
seed3d.quality bytedance 3d |
OK | 2025/10/29 | → |
| Fibo text-to-image |
SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
bria fibo prompt-adherence |
OK | 2025/10/29 | → |
| LongCat Video Distilled image-to-video | Generate long videos from images using LongCat Video Distilled | OK | 2025/10/29 | → |
| LongCat Video Distilled text-to-video | Generate long videos from text using LongCat Video Distilled | OK | 2025/10/28 | → |
| Demucs audio-to-audio |
SOTA stemming model for voice, drums, bass, guitar and more.
audio |
OK | 2025/10/27 | → |
| Piflow text-to-image |
Use the faster speed of piflow to generate images with same quality to that of slower models.
text-to-image |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 [Pro] (Image to Video) image-to-video |
MiniMax Hailuo-2.3 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution
image-to-video |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 Fast [Standard] (Image to Video) image-to-video |
MiniMax Hailuo-2.3-Fast Image To Video API (Standard, 768p): Advanced fast image-to-video generation model with 768p resolution
image-to-video |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 [Standard] (Image to Video) image-to-video |
MiniMax Hailuo-2.3 Image To Video API (Standard, 768p): Advanced image-to-video generation model with 768p resolution
image-to-video |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 Fast [Pro] (Image to Video) image-to-video |
MiniMax Hailuo-2.3-Fast Image To Video API (Pro, 1080p): Advanced fast image-to-video generation model with 1080p resolution
image-to-video |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 [Standard] (Text to Video) text-to-video |
MiniMax Hailuo-2.3 Text To Video API (Standard, 768p): Advanced text-to-video generation model with 768p resolution
text-to-video |
OK | 2025/10/27 | → |
| MiniMax Hailuo 2.3 [Pro] (Text to Video) text-to-video |
MiniMax Hailuo-2.3 Text To Video API (Pro, 1080p): Advanced text-to-video generation model with 1080p resolution
text-to-video |
OK | 2025/10/27 | → |
| Birefnet video-to-video |
Video background removal version of bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)
utility editing |
OK | 2025/10/26 | → |
| Audio Understanding audio-to-audio |
A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.
utility audio |
OK | 2025/10/24 | → |
| Bytedance image-to-video |
Image to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost
bytedance seedance pro fast |
OK | 2025/10/24 | → |
| Bytedance text-to-video |
Text to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost
bytedance fast motion |
OK | 2025/10/24 | → |
| Vidu video-to-video | Use the latest Vidu Q2 models which much more better quality and control on your videos. | OK | 2025/10/24 | → |
| Vidu image-to-video |
Use the latest Vidu Q2 models which much more better quality and control on your videos.
image-to-video |
OK | 2025/10/24 | → |
| Vidu image-to-video |
Use the latest Vidu Q2 models which much more better quality and control on your videos.
image-to-video |
OK | 2025/10/24 | → |
| LTX Video 2.0 Pro text-to-video | Create high-fidelity video with audio from text with LTX-2 Pro. | Deprecated | 2025/10/23 | → |
| LTX Video 2.0 Fast text-to-video | Create high-fidelity video with audio from text with LTX-2 Fast | Deprecated | 2025/10/23 | → |
| LTX Video 2.0 Pro image-to-video | Create high-fidelity video with audio from images with LTX-2 Pro | Deprecated | 2025/10/23 | → |
| LTX Video 2.0 Fast image-to-video | Create high-fidelity video with audio from images with LTX-2 Fast | Deprecated | 2025/10/23 | → |
| Vidu text-to-video | Use the latest Vidu Q2 models which much more better quality and control on your videos. | OK | 2025/10/22 | → |
| Kling Video image-to-video |
Kling 2.5 Turbo Standard: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.
stylized transform |
OK | 2025/10/22 | → |
| GPT Image 1 Mini image-to-image |
GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.
image-to-image |
OK | 2025/10/21 | → |
| GPT Image 1 Mini text-to-image |
GPT Image 1 mini combines OpenAI's advanced language capabilities, powered by GPT-5, with GPT Image 1 Mini for efficient image generation.
text-to-image |
OK | 2025/10/21 | → |
| Qwen 3 Guard [8B] llm |
Use Qwen 3 Guard [8B] to detect and classify text as safe or harmful, delivering precise and reliable safety categorization.
filter safety utility |
OK | 2025/10/20 | → |
| Krea Wan 14b- Text to Video text-to-video |
Fast Text-to-Video endpoint for Krea's Wan 14b model.
text to video fast |
OK | 2025/10/20 | → |
| Sound Effect Generation text-to-audio |
Create professional-grade sound effects from animal and vehicle to nature, sci-fi, and otherworldly sounds. Perfect for films, games, and digital content.
sfx audio effects speech |
OK | 2025/10/18 | → |
| Music Generation text-to-audio |
Generate royalty-free instrumental music from electronic, hip hop, and indie rock to cinematic and classical genres. Perfect for games, films, social content, podcasts, and more.
speech audio music |
OK | 2025/10/18 | → |
| Meshy 5 Retexture 3d-to-3d |
Meshy-5 retexture applies new, high-quality textures to existing 3D models using either text prompts or reference images. It supports PBR material generation for realistic, production-ready results.
3d-to-3d |
OK | 2025/10/18 | → |
| Meshy 5 Remesh 3d-to-3d |
Meshy-5 remesh allows you to remesh and export existing 3D models into various formats
3d-to-3d |
OK | 2025/10/18 | → |
| Reve image-to-image |
Reve’s remix model lets you upload an reference images and then combine/transform them via a text prompt
image-to-image |
OK | 2025/10/17 | → |
| Reve text-to-image |
Reve’s text-to-image model generates detailed visual output that closely follow your instructions, with strong aesthetic quality and accurate text rendering.
text-to-image |
OK | 2025/10/17 | → |
| Reve image-to-image |
Reve’s edit model lets you upload an existing image and then transform it via a text prompt
image-to-image |
OK | 2025/10/17 | → |
| Wan Alpha text-to-video |
Generate videos with transparent backgrounds
transparent alpha |
OK | 2025/10/16 | → |
| Mirelo SFX V1.5 video-to-audio |
Generate synced sounds for any video, and return the new sound track (like MMAudio)
video-to-audio sfx |
OK | 2025/10/15 | → |
| Mirelo SFX V1.5 video-to-video |
Generate synced sounds for any video, and return it with its new sound track (like MMAudio)
video-to-video sfx |
OK | 2025/10/15 | → |
| Krea Wan 14B video-to-video | Superfast video model based on Wan 2.1 14b by Krea, excelling at real-time video-editing. | OK | 2025/10/14 | → |
| Image2Pixel image-to-image |
Turn images into pixel-perfect retro art
post-processing pixel-art |
OK | 2025/10/14 | → |
| Kandinsky5 text-to-video | Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation. | OK | 2025/10/13 | → |
| Kandinsky5 text-to-video | Kandinsky 5.0 is a diffusion model for fast, high-quality text-to-video generation. | OK | 2025/10/13 | → |
| DreamOmni2 image-to-image | DreamOmni2 is a unified multimodal model for text and image guided image editing. | OK | 2025/10/10 | → |
| Moondream3 Preview [Detect] vision |
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
Vision |
OK | 2025/10/9 | → |
| Moondream3 Preview [Point] vision |
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
Vision |
OK | 2025/10/9 | → |
| Moondream 3 Preview [Query] vision |
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
Vision |
OK | 2025/10/9 | → |
| Moondream3 Preview [Caption] vision |
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
Vision |
OK | 2025/10/9 | → |
| Kling Video video-to-audio | Generate audio from input videos using Kling | OK | 2025/10/9 | → |
| Sora 2 video-to-video |
Video-to-video remix endpoint for Sora 2, OpenAI’s advanced model that transforms existing videos based on new text or image prompts allowing rich edits, style changes, and creative reinterpretations while preserving motion and structure
video to video audio sora |
OK | 2025/10/8 | → |
| Veo 3.1 Fast image-to-video | Generate videos from a first/last frame using Google's Veo 3.1 Fast | OK | 2025/10/8 | → |
| Veo 3.1 image-to-video | Generate videos from a first and last framed using Google's Veo 3.1 | OK | 2025/10/8 | → |
| Veo 3.1 image-to-video | Generate Videos from images using Google's Veo 3.1 | OK | 2025/10/8 | → |
| Veo 3.1 Fast text-to-video | Faster and more cost effective version of Google's Veo 3.1! | OK | 2025/10/8 | → |
| Veo 3.1 Fast image-to-video | Generate videos from your image prompts using Veo 3.1 fast. | OK | 2025/10/8 | → |
| Veo 3.1 image-to-video | Veo 3.1 is the latest state-of-the art video generation model from Google DeepMind | OK | 2025/10/8 | → |
| Veo 3.1 text-to-video | Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on! | OK | 2025/10/8 | → |
| Hunyuan Part 3d-to-3d |
Use the capabilities of hunyuan part to generate point clouds from your 3D files.
3D-to-3D point-cloud |
OK | 2025/10/8 | → |
| Wan 2.1 VACE Long Reframe video-to-video | Reframe entire videos scene-by-scene using Wan VACE 2.1 | OK | 2025/10/7 | → |
| Index TTS 2.0 text-to-speech |
Generate natural, clear speeches using Index TTS 2.0 from IndexTeam
text-to-speech |
OK | 2025/10/7 | → |
| Meshy 6 Preview text-to-3d |
Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.
text-to-3d |
OK | 2025/10/6 | → |
| Meshy 5 Multi image-to-3d |
Meshy-5 multi image generates realistic and production ready 3D models from multiple images.
multi-image-to-3d |
OK | 2025/10/6 | → |
| Meshy 6 Preview image-to-3d |
Meshy-6-Preview is the latest model from Meshy. It generates realistic and production ready 3D models.
image-to-3d |
OK | 2025/10/6 | → |
| Sora 2 image-to-video |
Image-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.
image-to-video audio sora-2-pro |
OK | 2025/10/6 | → |
| Sora 2 text-to-video |
Text-to-video endpoint for Sora 2 Pro, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.
text-to-video audio sora-2-pro |
OK | 2025/10/6 | → |
| Sora 2 text-to-video |
Text-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.
text to video audio sora |
OK | 2025/10/6 | → |
| Sora 2 image-to-video |
Image-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.
image-to-video audio sora |
OK | 2025/10/6 | → |
| Qwen Image Edit Plus Lora image-to-image |
LoRA endpoint for the Qwen Image Edit Plus model.
image-to-image image-editing |
OK | 2025/10/3 | → |
| Lucidflux image-to-image |
LucidFlux for upscaling images with very high fidelity
image-to-image |
OK | 2025/10/3 | → |
| Ovi image-to-video |
Ovi can generate videos with audio from image and text inputs.
image-to-audio-video image-to-video |
OK | 2025/10/3 | → |
| Ovi Text to Video text-to-video | A unified paradigm for audio-video generation | OK | 2025/10/3 | → |
| Fabric 1.0 Fast image-to-video |
VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video
lipsync avatar |
OK | 2025/10/1 | → |
| Qwen Image Edit image-to-image |
Image to Image Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.
stylized transform |
OK | 2025/9/30 | → |
| Hunyuan Image text-to-image |
Leverage the state-of-the-art capabilities of Hunyuan Image 3.0 to generate visual content that effectively conveys the messaging of your written material.
text-to-image |
OK | 2025/9/28 | → |
| Hyper3d image-to-3d |
Rodin by Hyper3D generates realistic and production ready 3D models from text or images.
image-to-3d text-to-3d |
OK | 2025/9/26 | → |
| Lynx image-to-video |
Generate subject consistent videos using Lynx from ByteDance!
image-to-video subject |
Deprecated | 2025/9/26 | → |
| Wan 2.5 Image to Image image-to-image | Wan 2.5 image-to-image model. | OK | 2025/9/25 | → |
| Wan 2.5 Text to Image text-to-image | Wan 2.5 text-to-image model. | OK | 2025/9/25 | → |
| Wan 2.5 Text to Video text-to-video | Wan 2.5 text-to-video model. | OK | 2025/9/24 | → |
| Wan 2.5 Image to Video image-to-video | Wan 2.5 image-to-video model. | OK | 2025/9/24 | → |
| Bytedance OmniHuman v1.5 image-to-video |
Omnihuman v1.5 is a new and improved version of Omnihuman. It generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.
image-to-video lipsync |
OK | 2025/9/23 | → |
| Product Photoshoot image-to-image | Create product advertisements with an example image of the product | Deprecated | 2025/9/23 | → |
| Qwen Image Edit Plus image-to-image |
Endpoint for Qwen's Image Editing Plus model also known as Qwen-Image-Edit-2509. Has superior text editing capabilities and multi-image support.
image-editing image-to-image high-quality-text |
OK | 2025/9/22 | → |
| Kling Video image-to-video |
Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.
stylized transform |
OK | 2025/9/22 | → |
| Kling v2.5 Text to Video text-to-video |
Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.
animation stylized |
OK | 2025/9/22 | → |
| Infinitalk video-to-video |
Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.
video-to-video |
OK | 2025/9/22 | → |
| SeedVR2 video-to-video |
Upscale your videos using SeedVR2 with temporal consistency!
upscale video-to-video |
OK | 2025/9/22 | → |
| SeedVR2 image-to-image |
Use SeedVR2 to upscale your images
upscale image-to-image |
OK | 2025/9/22 | → |
| Wan VACE Video Edit video-to-video |
Edit videos using plain language and Wan VACE
video-edit wan-vace |
OK | 2025/9/22 | → |
| Wan-2.2 Animate Replace video-to-video |
Wan-Animate Replace is a model that can integrate animated characters into reference videos, replacing the original character while preserving the scene’s lighting and color tone for seamless environmental integration.
video to video motion |
OK | 2025/9/21 | → |
| Wan-2.2 Animate Move video-to-video |
Wan-Animate is a video model that generates high-fidelity character videos by replicating the expressions and movements of characters from reference videos.
video to video motion |
OK | 2025/9/21 | → |
| Fabric 1.0 image-to-video |
VEED Fabric 1.0 is an image-to-video API that turns any image into a talking video
lipsync avatar |
OK | 2025/9/19 | → |
| Product Holding image-to-image |
Place products naturally in a person’s hands for realistic marketing visuals.
product marketing |
OK | 2025/9/19 | → |
| Product Photography image-to-image |
Generate professional product photography with realistic lighting and backgrounds.
product marketing |
OK | 2025/9/19 | → |
| Lucy Edit [Pro] video-to-video |
Edit outfits, objects, faces, or restyle your video - all with maximum detail retention.
video-edit |
OK | 2025/9/18 | → |
| Lucy Edit [Dev] video-to-video |
Edit outfits, objects, faces, or restyle your video - all with maximum detail retention.
video-edit |
OK | 2025/9/18 | → |
| Virtual Try-on image-to-image |
Try on clothes virtually by combining person and clothing images.
fashion try-on virtual-try-on |
OK | 2025/9/18 | → |
| Texture Transform image-to-image |
Transform objects with different surface textures like marble, wood, or fabric.
texture-transform |
OK | 2025/9/18 | → |
| Relighting image-to-image |
Adjust and enhance images with different lighting styles.
relighting |
OK | 2025/9/18 | → |
| Style Transfer image-to-image |
Apply artistic styles like impressionism, cubism, or surrealism to your images.
style-transfer |
OK | 2025/9/18 | → |
| Photo Restoration image-to-image |
Restore old or damaged photos by fixing colors, scratches, and resolution.
photo-restoration image-enhance |
OK | 2025/9/18 | → |
| Portrait Enhance image-to-image |
Enhance and refine portrait photos with improved clarity and detail.
image-edit enhancement |
OK | 2025/9/18 | → |
| Photography Effects image-to-image |
Apply diverse photography styles and effects to transform your images.
style-transfer photography |
OK | 2025/9/18 | → |
| Perspective Change image-to-image |
Easily adjust the perspective of any image to different angles.
change-angle perspective |
OK | 2025/9/18 | → |
| Object Removal image-to-image |
Remove unwanted objects seamlessly from any image.
remove object-removal |
OK | 2025/9/18 | → |
| Headshot Generator image-to-image |
Generate professional headshot photos with customizable backgrounds.
headshot profile-photo |
OK | 2025/9/18 | → |
| Hair Change image-to-image |
Change hairstyles and hair colors in photos realistically.
hair-edit style-change |
OK | 2025/9/18 | → |
| Expression Change image-to-image |
Change facial expressions in photos with realistic results.
face-edit expression-change |
OK | 2025/9/18 | → |
| City Teleport image-to-image |
Place a person’s photo into iconic cities worldwide.
city-teleport backgroundswap |
OK | 2025/9/18 | → |
| Age Modify image-to-image |
Modify a face to look younger or older while keeping identity realistic.
age-transformation face-editing |
OK | 2025/9/18 | → |
| Makeup Changer image-to-image |
Apply realistic makeup styles with adjustable intensity.
makeup transform |
OK | 2025/9/18 | → |
| Qwen Image Edit image-to-image |
Inpainting Endpoint for the Qwen Edit Image editing model.
image-to-image inpainting qwen-image |
OK | 2025/9/17 | → |
| Wan 2.2 VACE Fun A14B video-to-video | VACE Fun for Wan 2.2 A14B from Alibaba-PAI | OK | 2025/9/17 | → |
| Wan 2.2 VACE Fun A14B video-to-video | VACE Fun for Wan 2.2 A14B from Alibaba-PAI | OK | 2025/9/17 | → |
| Wan 2.2 VACE Fun A14B video-to-video | VACE Fun for Wan 2.2 A14B from Alibaba-PAI | OK | 2025/9/17 | → |
| Wan 2.2 VACE Fun A14B video-to-video | VACE Fun for Wan 2.2 A14B from Alibaba-PAI | OK | 2025/9/17 | → |
| Wan 2.2 VACE Fun A14B video-to-video | VACE Fun for Wan 2.2 A14B from Alibaba-PAI | OK | 2025/9/17 | → |
| Isaac 0.1 [OpenAI Compatible Endpoint] vision |
OpenAI spec compatible endpoint of Isaac-01 which is a multimodal vision-language model from Perceptron for various vision language tasks.
multimodal vision |
OK | 2025/9/17 | → |
| Isaac 0.1 vision |
Isaac-01 is a multimodal vision-language model from Perceptron for various vision language tasks.
multimodal vision |
OK | 2025/9/17 | → |
| FLUX.1 SRPO [dev] image-to-image | FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/9/15 | → |
| FLUX.1 SRPO [dev] text-to-image | FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/9/15 | → |
| FLUX.1 SRPO [dev] image-to-image | FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/9/15 | → |
| FLUX.1 SRPO [dev] text-to-image | FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/9/15 | → |
| Pshuman image-to-3d |
Use the 6D pose estimation capabilities of PSHuman to generate 3D files from single image.
image-to-3D |
OK | 2025/9/13 | → |
| Kling TTS text-to-speech |
Generate speech from text prompts and different voices using the Kling TTS model, which leverages advanced AI techniques to create high-quality text-to-speech.
audio |
OK | 2025/9/13 | → |
| Kling AI Avatar image-to-video |
Kling AI Avatar Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters
stylized transform |
OK | 2025/9/13 | → |
| Kling AI Avatar Pro image-to-video |
Kling AI Avatar Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters
stylized transform |
OK | 2025/9/13 | → |
| MiniMax (Hailuo AI) Music v1.5 text-to-audio |
Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.
music |
OK | 2025/9/11 | → |
| Decart Lucy 14b image-to-video | Lucy-14B delivers lightning fast performance that redefines what's possible with image-to-video AI | OK | 2025/9/10 | → |
| Qwen Image Edit Lora image-to-image |
LoRA inference endpoint for the Qwen Image Editing model.
image-to-image image-editing lora |
OK | 2025/9/10 | → |
| Stable Audio 2.5 audio-to-audio |
Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI
audio |
OK | 2025/9/10 | → |
| Stable Audio 2.5 text-to-audio |
Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI
audio |
OK | 2025/9/10 | → |
| Stable Audio 25 audio-to-audio |
Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI
audio |
OK | 2025/9/10 | → |
| Hunyuan Image text-to-image |
Use the amazing capabilities of hunyuan image 2.1 to generate images that express the feelings of your text.
text-to-image |
OK | 2025/9/9 | → |
| Elevenlabs text-to-audio |
Generate realistic audio dialogues using Eleven-v3 from ElevenLabs.
audio |
OK | 2025/9/9 | → |
| Vidu image-to-image |
Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.
images-to-image |
OK | 2025/9/9 | → |
| Bytedance Seedream v4 Edit image-to-image |
A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.
stylized transform editing |
OK | 2025/9/9 | → |
| Bytedance Seedream v4 text-to-image |
A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.
stylized transform |
OK | 2025/9/9 | → |
| Hunyuan Video Foley video-to-video |
Use the capabilities of the hunyuan foley model to bring life to your videos by adding sound effect to them.
video-to-video add-sound |
OK | 2025/9/8 | → |
| Chatterbox text-to-speech |
Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.
text-to-speech multilingual |
OK | 2025/9/4 | → |
| Wan image-to-image |
Wan 2.2's 14B model edit high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail
image-to-image |
OK | 2025/9/3 | → |
| Elevenlabs text-to-audio |
Generate sound effects using ElevenLabs advanced sound effects model.
sound |
OK | 2025/9/2 | → |
| Sync Lipsync video-to-video |
Generate high-quality realistic lipsync animations from audio while preserving unique details like natural teeth and unique facial features using the state-of-the-art Sync Lipsync 2 Pro model.
animation lip sync high-quality |
OK | 2025/9/2 | → |
| Bytedance image-to-video |
Seedance lite reference-to-video allows the use of 1 to 4 images as reference to create a high-quality video.
reference-to-video image-to-video |
OK | 2025/9/1 | → |
| Avatars Text to Video text-to-video | High-quality avatar videos that feel real, generated from your text | OK | 2025/9/1 | → |
| Avatars Audio to Video audio-to-video | High-quality avatar videos that feel real, generated from your audio | OK | 2025/9/1 | → |
| Uso image-to-image |
Use USO to perform subject driven generations using reference image.
image-to-image |
OK | 2025/8/30 | → |
| Wan Ati image-to-video | WAN-ATI is a controllable video generation model that uses trajectory instructions to guide object, local, and camera motion, enabling precise and flexible image-to-video creation. | OK | 2025/8/29 | → |
| Decart image-to-video | Lucy-5B is a model that can create 5-second I2V videos in under 5 seconds, achieving >1x RTF end-to-end | OK | 2025/8/28 | → |
| Wan 2.2 Fun Control video-to-video |
Generate pose or depth controlled video using Alibaba-PAI's Wan 2.2 Fun
wan pose depth |
OK | 2025/8/28 | → |
| VibeVoice 7B text-to-speech |
Generate long, expressive multi-voice speech using Microsoft's powerful TTS
text-to-speech multi-speaker podcast |
OK | 2025/8/27 | → |
| VibeVoice 1.5B text-to-speech |
Generate long, expressive multi-voice speech using Microsoft's powerful TTS
text-to-speech multi-speaker podcast |
OK | 2025/8/27 | → |
| Wan-2.2 Speech-to-Video 14B audio-to-video |
Wan-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements, and professional camera work for film and television applications
audio-to-video talking-head |
OK | 2025/8/27 | → |
| Video video-to-video |
Upscale videos up to 8K output resolution. Trained on fully licensed and commercially safe data.
video-upscaling upscale |
OK | 2025/8/26 | → |
| Gemini 2.5 Flash Image image-to-image |
Gemini 2.5 Flash Image is Google's state-of-the-art image generation and editing model
image-editing |
OK | 2025/8/26 | → |
| Gemini 2.5 Flash Image text-to-image |
Nano Banana is Google's state-of-the-art image generation and editing model
text-to-image |
OK | 2025/8/26 | → |
| Qwen Image image-to-image |
Qwen-Image (Image-to-Image) transforms and edits input images with high fidelity, enabling precise style transfer, enhancement, and creative modification.
image-to-image |
OK | 2025/8/25 | → |
| Sonauto V2 audio-to-audio |
Extend an existing song
music text-to-music text-to-audio |
OK | 2025/8/23 | → |
| Sonauto V2 text-to-audio |
Replace sections of an existing audio with newly generated content
music text-to-music text-to-audio |
OK | 2025/8/23 | → |
| Sonauto V2 text-to-audio |
Create full songs in any style
music text-to-music text-to-audio |
OK | 2025/8/23 | → |
| Pixverse image-to-video |
Create seamless transition between images using PixVerse v5
stylized transform |
OK | 2025/8/23 | → |
| Pixverse image-to-video |
Generate high quality video clips with different effects using PixVerse v5
image-to-video |
OK | 2025/8/23 | → |
| Pixverse v5 Image to Video image-to-video |
Generate high quality video clips from text and image prompts using PixVerse v5
stylized transform |
OK | 2025/8/23 | → |
| Pixverse text-to-video | Generate high quality video clips from text and image prompts using PixVerse v5 | OK | 2025/8/23 | → |
| Infinitalk text-to-video | Infinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions. | OK | 2025/8/22 | → |
| Infinitalk video-to-video |
Infinitalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.
stylized transform |
OK | 2025/8/21 | → |
| Elevenlabs text-to-audio |
Generate text-to-speech audio using Eleven-v3 from ElevenLabs.
audio |
OK | 2025/8/20 | → |
| Reimagine image-to-image |
Reimagine uses a structure reference for generating new images while preserving the structure of an input image, guided by text prompts.
Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data
bria |
OK | 2025/8/20 | → |
| Nano Banana image-to-image |
Google's state-of-the-art image generation and editing model
image-editing |
OK | 2025/8/19 | → |
| Nano Banana text-to-image |
Google's state-of-the-art image generation and editing model
image-generation |
OK | 2025/8/19 | → |
| Nextstep 1 image-to-image | Endpoint for NextStep-1 Autoregressive Image Editing model. | OK | 2025/8/19 | → |
| Qwen Image Edit image-to-image |
Endpoint for Qwen's Image Editing model. Has superior text editing capabilities.
image-editing image-to-image high-quality-text |
OK | 2025/8/18 | → |
| Mirelo SFX video-to-audio |
Generate synced sounds for any video, and return the new sound track (like MMAudio)
sfx |
OK | 2025/8/15 | → |
| Mirelo SFX video-to-video |
Generate synced sounds for any video, and return it with its new sound track (like MMAudio)
video-to-video sfx |
OK | 2025/8/14 | → |
| Stable Avatar audio-to-video |
Stable Avatar generates audio-driven video avatars up to five minutes long
stable-avatar talking-head audio-to-video |
OK | 2025/8/14 | → |
| Marey Realism V1.5 video-to-video | Ideal for matching human movement. Your input video determines human poses, gestures, and body movements that will appear in the generated video. | OK | 2025/8/14 | → |
| Marey Realism V1.5 video-to-video | Pull motion from a reference video and apply it to new subjects or scenes. | OK | 2025/8/14 | → |
| Marey Realism V1.5 image-to-video | Generate a video starting from an image as the first frame with Marey, a generative video model trained exclusively on fully licensed data. | OK | 2025/8/14 | → |
| Qwen Image Trainer training |
Qwen Image LoRA training
lora personalization |
OK | 2025/8/14 | → |
| Marey Realism V1.5 text-to-video | Generate a video from a text prompt with Marey, a generative video model trained exclusively on fully licensed data. | OK | 2025/8/14 | → |
| EchoMimic V3 audio-to-video |
EchoMimic V3 generates a talking avatar model from a picture, audio and text prompt.
echomimic talking-head audio-to-video |
OK | 2025/8/13 | → |
| Any LLM llm |
Use any large language model from our selected catalogue (powered by OpenRouter)
chat claude gpt streaming |
Deprecated | 2025/8/13 | → |
| Luma Dream Machine image-to-video |
Generate video clips from your images using Luma Dream Machine v1.5
motion transformation |
Deprecated | 2025/8/13 | → |
| Any VLM vision |
Use any vision language model from our selected catalogue (powered by OpenRouter)
multimodal vision streaming |
Deprecated | 2025/8/13 | → |
| Luma Dream Machine text-to-video |
Generate video clips from your prompts using Luma Dream Machine v1.5
motion transformation |
Deprecated | 2025/8/13 | → |
| PlayAI Text-to-Speech Dialog text-to-audio |
Generate natural-sounding multi-speaker dialogues, and audio. Perfect for expressive outputs, storytelling, games, animations, and interactive media.
audio |
Deprecated | 2025/8/13 | → |
| PlayAI Text-to-Speech v3 text-to-speech | Blazing-fast text-to-speech. Generate audio with improved emotional tones and extensive multilingual support. Ideal for high-volume processing and efficient workflows. | Deprecated | 2025/8/13 | → |
| FLUX.1 [pro] Canny Fine-tuned image-to-image |
Utilize Flux.1 [pro] Controlnet with a fine-tuned LoRA to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.
controlnet detection editing composition |
Deprecated | 2025/8/13 | → |
| FLUX.1 [pro] Depth image-to-image |
Generate high-quality images from depth maps using Flux.1 [pro] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.
depth utility composition |
Deprecated | 2025/8/13 | → |
| Train Flux LoRAs For Pro Models training |
FLUX LoRA for Pro endpoints.
lora personalization |
Deprecated | 2025/8/13 | → |
| FLUX.1 [pro] Depth Fine-tuned image-to-image |
Generate high-quality images from depth maps using Flux.1 [pro] depth estimation model with a fine-tuned LoRA. The model produces accurate depth representations for scene understanding and 3D visualization.
depth utility composition |
Deprecated | 2025/8/13 | → |
| FLUX.1 [pro] Canny image-to-image |
Utilize Flux.1 [pro] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.
controlnet detection editing composition |
Deprecated | 2025/8/13 | → |
| ElevenLabs Sound Effects text-to-audio |
Generate sound effects using ElevenLabs advanced sound effects model.
sound |
Deprecated | 2025/8/13 | → |
| Easel AI Advanced Face Swap image-to-image |
Swap faces of one or two people at once, while preserving user and scene details!
face swap utility editing |
Deprecated | 2025/8/13 | → |
| Tavus LipSync v2 video-to-video | Generate lip sync using Tavus' state-of-the-art model for high-quality synchronization. | Deprecated | 2025/8/13 | → |
| gpt-image-1 image-to-image | OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key. | Deprecated | 2025/8/13 | → |
| gpt-image-1 text-to-image | OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key. | Deprecated | 2025/8/13 | → |
| Easel Avatar text-to-image |
Create scenes with one or two people using just selfies and text prompt (without LoRAs)
avatars loras image-generation |
Deprecated | 2025/8/13 | → |
| Easel Gifswap image-to-image |
Swap faces on GIFs
utility editing |
Deprecated | 2025/8/13 | → |
| PlayAI Inpaint audio-to-audio |
A novel way to perform audio editing, ensuring smooth transitions and consistent speaker characteristics for edits.
audio inpaint |
Deprecated | 2025/8/13 | → |
| Lipsync video-to-video | Realistic lipsync video - optimized for speed, quality, and consistency. | Deprecated | 2025/8/13 | → |
| any-llm Enterprise llm |
Run any large language model with fal, powered by OpenRouter.
This endpoint only supports models that do not train on private data.
Read more in OpenRouter's Privacy and Logging documentation.
chat claude gpt |
Deprecated | 2025/8/13 | → |
| Fashion Photoshoot image-to-image |
Instant fashion photoshoot with a selfie and an outfit
image-to-image |
Deprecated | 2025/8/13 | → |
| Fashion Try On image-to-image | Instant fashion try on with a full-body pic and an outfit | Deprecated | 2025/8/13 | → |
| Bytedance image-to-video |
Transform your images into stylized videos using this workflow.
image-to-video effects |
OK | 2025/8/12 | → |
| Ffmpeg Api video-to-video | Use ffmpeg capabilities to merge 2 or more videos. | OK | 2025/8/12 | → |
| Minimax text-to-speech |
Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/8/11 | → |
| Minimax text-to-speech |
Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.
text-to-speech |
OK | 2025/8/11 | → |
| Wan 2.2 14B Image Trainer training |
Wan 2.2 text to image LoRA trainer. Fine-tune Wan 2.2 for subjects and styles with unprecedented detail.
lora personalization |
OK | 2025/8/11 | → |
| Ideogram V3 Character Edit image-to-image |
Modify consistent characters while preserving their core identity. Edit poses, expressions, or clothing without losing recognizable character features
character-consistency |
OK | 2025/8/7 | → |
| Ideogram V3 Character image-to-image |
Generate consistent character appearances across multiple images. Maintain facial features, proportions, and distinctive traits for cohesive storytelling and branding
character-consistency |
OK | 2025/8/7 | → |
| Ideogram V3 Character Remix image-to-image |
Transform your consistent character into different art styles, settings, or scenarios while maintaining their distinctive appearance and identity
character-consistency |
OK | 2025/8/7 | → |
| Wan-2.2 Text-to-Video A14B with LoRAs text-to-video | Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. This endpoint supports LoRAs made for Wan 2.2. | OK | 2025/8/7 | → |
| Wan v2.2 A14B Image-to-Video A14B with LoRAs image-to-video |
Wan-2.2 image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and images. This endpoint supports LoRAs made for Wan 2.2
image-to-video motion lora |
OK | 2025/8/7 | → |
| Wan text-to-video | Wan 2.2's 5B distill model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding | OK | 2025/8/6 | → |
| Minimax image-to-video |
Create blazing fast and economical videos with MiniMax Hailuo-02 Image To Video API at 512p resolution
stylized transform |
OK | 2025/8/6 | → |
| Bytedance text-to-image |
Dreamina showcases superior picture effects, with significant improvements in picture aesthetics, precise and diverse styles, and rich details.
text-to-image |
OK | 2025/8/6 | → |
| Wan text-to-video |
Wan 2.2's 5B FastVideo model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding
text to video motion |
OK | 2025/8/5 | → |
| Wan v2.2 A14B Text-to-Image A14B with LoRAs text-to-image | Wan 2.2's 14B model with LoRA support generates high-fidelity images with enhanced prompt alignment, style adaptability. | OK | 2025/8/5 | → |
| Wan text-to-image | Wan 2.2's 5B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail | OK | 2025/8/5 | → |
| Wan text-to-image | Wan 2.2's 14B model generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail | OK | 2025/8/5 | → |
| Qwen Image text-to-image |
Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing.
text-to-image |
OK | 2025/8/4 | → |
| Wan video-to-video | Wan-2.2 video-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts and source videos. | OK | 2025/8/2 | → |
| Train Flux Krea LoRA training |
Train styles, people and other subjects at blazing speeds using the FLUX.1 Krea [dev] base model.
lora personalization |
OK | 2025/8/1 | → |
| Flux Krea Lora text-to-image |
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2025/8/1 | → |
| FLUX.1 Krea [dev] Inpainting with LoRAs image-to-image |
Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2025/8/1 | → |
| FLUX.1 Krea [dev] with LoRAs text-to-image |
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2025/8/1 | → |
| FLUX.1 Krea [dev] with LoRAs image-to-image |
FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.
lora style transfer |
OK | 2025/8/1 | → |
| Veo3 image-to-video | Veo 3 is the latest state-of-the art video generation model from Google DeepMind | OK | 2025/8/1 | → |
| Wan image-to-video | Wan-2.2 Turbo image-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. | OK | 2025/7/31 | → |
| Wan text-to-video |
Wan-2.2 turbo text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.
text to video motion |
OK | 2025/7/31 | → |
| FLUX.1 Krea [dev] image-to-image | FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/7/30 | → |
| FLUX.1 Krea [dev] Redux image-to-image | FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities. | OK | 2025/7/30 | → |
| FLUX.1 Krea [dev] text-to-image | FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/7/30 | → |
| FLUX.1 Krea [dev] image-to-image | FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/7/30 | → |
| FLUX.1 Krea [dev] Redux image-to-image | FLUX.1 Krea [dev] Redux is a high-performance endpoint for the FLUX.1 Krea [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities. | OK | 2025/7/30 | → |
| FLUX.1 Krea [dev] text-to-image | FLUX.1 Krea [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use. | OK | 2025/7/30 | → |
| Wan v2.2 5B image-to-video | Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding | OK | 2025/7/30 | → |
| Flux Kontext Lora image-to-image |
Fast inpainting endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image inpainting with reference images, while using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.
image-editing image-inpainting image-to-image |
OK | 2025/7/29 | → |
| Wan v2.2 5B text-to-video | Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding | OK | 2025/7/28 | → |
| Wan-2.2 Text-to-Video A14B text-to-video |
Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts.
text to video motion |
OK | 2025/7/28 | → |
| Wan v2.2 A14B image-to-video | fal-ai/wan/v2.2-A14B/image-to-video | OK | 2025/7/28 | → |
| Hunyuan World image-to-image | Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles. | OK | 2025/7/28 | → |
| Hunyuan World image-to-3d | Hunyuan World 1.0 turns a single image into a panorama or a 3D world. It creates realistic scenes from the image, allowing you to explore and view it from different angles. | OK | 2025/7/28 | → |
| NSFW Checker vision |
Predict whether an image is NSFW or SFW.
filter safety utility |
OK | 2025/7/28 | → |
| OmniHuman image-to-video |
OmniHuman generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.
image-to-video lipsync |
OK | 2025/7/27 | → |
| Sky Raccoon text-to-image |
Generate images from a text prompt.
text-to-image |
OK | 2025/7/26 | → |
| Image Editing image-to-image | Retouch photos of faces. Remove blemishes and improve the skin. | OK | 2025/7/24 | → |
| Hidream E1 1 image-to-image | Edit images with natural language | OK | 2025/7/23 | → |
| LTX-Video 13B 0.9.8 Distilled video-to-video |
Extend videos using LTX Video-0.9.8 13B Distilled and custom LoRA
ltx-video extend |
OK | 2025/7/23 | → |
| RIFE video-to-video |
Interpolate videos with RIFE - Real-Time Intermediate Flow Estimation
interpolation |
OK | 2025/7/22 | → |
| RIFE image-to-image |
Interpolate images with RIFE - Real-Time Intermediate Flow Estimation
interpolation |
OK | 2025/7/22 | → |
| FILM video-to-video |
Interpolate videos with FILM - Frame Interpolation for Large Motion
interpolation |
OK | 2025/7/22 | → |
| FILM image-to-image |
Interpolate images with FILM - Frame Interpolation for Large Motion
interpolation |
OK | 2025/7/22 | → |
| MiniMax Voice Design text-to-speech |
Design a personalized voice from a text description, and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/7/18 | → |
| Luma Ray 2 Flash Modify video-to-video |
Ray2 Flash Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.
modify restyle |
OK | 2025/7/17 | → |
| LTX-Video 13B 0.9.8 Distilled image-to-video |
Generate long videos from prompts and images using LTX Video-0.9.8 13B Distilled and custom LoRA
video ltx-video image-to-video |
OK | 2025/7/17 | → |
| LTX-Video 13B 0.9.8 Distilled text-to-video |
Generate long videos from prompts using LTX Video-0.9.8 13B Distilled and custom LoRA
video ltx-video text-to-video |
OK | 2025/7/17 | → |
| LTX-Video 13B 0.9.8 Distilled video-to-video |
Generate long videos from prompts, images, and videos using LTX Video-0.9.8 13B Distilled and custom LoRA
video ltx-video video-to-video multicondition-to-video image-to-video |
OK | 2025/7/17 | → |
| Calligrapher image-to-image |
Use the text and font retaining capabilities of calligrapher to modify texts on your books, clothes and many more.
image-to-image |
OK | 2025/7/12 | → |
| Veo 3 Fast [Image to Video] image-to-video | Now with a 50% price drop. Generate videos from your image prompts using Veo 3 fast. | OK | 2025/7/9 | → |
| Veo 3 Fast text-to-video | Faster and more cost effective version of Google's Veo 3! | OK | 2025/7/9 | → |
| Ffmpeg Api json |
Get EBU R128 loudness normalization from audio files using FFmpeg API.
ffmpeg |
OK | 2025/7/8 | → |
| Vidu image-to-video |
Generate video clips from your multiple image references using Vidu Q1
stylized transform |
OK | 2025/7/8 | → |
| Bria image-to-image | Structure Reference allows generating new images while preserving the structure of an input image, guided by text prompts. Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data for safe and risk-free commercial use. | OK | 2025/7/8 | → |
| Pixverse video-to-video |
Add immersive sound effects and background music to your videos using PixVerse sound effects generation
audio utility |
OK | 2025/7/7 | → |
| Image Editing image-to-image |
Add details to faces, enhance face features, remove blur.
stylized transform realism |
OK | 2025/7/7 | → |
| ThinkSound video-to-video |
Generate realistic audio from a video with an optional text prompt
audio-generation video-to-audio |
OK | 2025/7/2 | → |
| ThinkSound video-to-video |
Generate realistic audio for a video with an optional text prompt and combine
audio-generation video-to-audio |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Add a darkening vignette effect around the edges of the image with adjustable strength
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply solarization effect by inverting pixel values above a threshold
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply sharpening effects with three modes: basic unsharp mask, smart sharpening with edge preservation, and Contrast Adaptive Sharpening (CAS).
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply a parabolic distortion effect with configurable coefficient and vertex position.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply film grain effect with different styles (modern, analog, kodak, fuji, cinematic, newspaper) and customizable intensity and scale
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply dodge and burn effects with multiple modes and adjustable intensity.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Blend two images together using smooth linear interpolation with a configurable blend factor.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Reduce color saturation using different methods (luminance Rec.709, luminance Rec.601, average, lightness) with adjustable factor.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply various color tints (sepia, red, green, blue, cyan, magenta, yellow, purple, orange, warm, cool, lime, navy, vintage, rose, teal, maroon, peach, lavender, olive) with adjustable strength.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Adjust color temperature, brightness, contrast, saturation, and gamma values for color correction.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Create chromatic aberration by shifting red, green, and blue channels horizontally or vertically with customizable shift amounts.
stylized transform |
OK | 2025/7/1 | → |
| Post Processing image-to-image |
Apply Gaussian or Kuwahara blur effects with adjustable radius and sigma parameters
stylized transform |
OK | 2025/7/1 | → |
| Pixverse video-to-video |
PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques
utility editing |
OK | 2025/6/30 | → |
| Pixverse video-to-video |
PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques
utility editing |
OK | 2025/6/30 | → |
| Pixverse video-to-video |
Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with PixVerse Lipsync model
animation lip sync |
OK | 2025/6/30 | → |
| Image Editing image-to-image |
Generate YouTube thumbnails with custom text
stylized transform |
OK | 2025/6/30 | → |
| Video video-to-video |
Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.
background-removal |
OK | 2025/6/30 | → |
| Luma Ray 2 Modify video-to-video |
Ray2 Modify is a video generative model capable of restyling or retexturing the entire shot, from turning live-action into CG or stylized animation, to changing wardrobe, props, or the overall aesthetic and swap environments or time periods, giving you control over background, location, or even weather.
modify restyle |
OK | 2025/6/28 | → |
| Topaz image-to-image |
Use the powerful and accurate topaz image enhancer to enhance your images.
image-to-image |
OK | 2025/6/27 | → |
| Bytedance image-to-image |
SeedEdit 3.0 is an image editing model independently developed by ByteDance. It excels in accurately following editing instructions and effectively preserving image content, especially excelling in handling real images
image-editing image-to-image |
Deprecated | 2025/6/27 | → |
| Flux Kontext Trainer training | LoRA trainer for FLUX.1 Kontext [dev] | OK | 2025/6/26 | → |
| Image Editing image-to-image |
Transform your character's hair into broccoli style while keeping the original characters likeness
stylized transform |
OK | 2025/6/26 | → |
| Image Editing image-to-image |
Transform your photos into wojak style while keeping the original characters likeness
stylized transform |
OK | 2025/6/26 | → |
| Image Editing image-to-image |
Transform your photos into cool plushies while keeping the original characters likeness
stylized transform |
OK | 2025/6/26 | → |
| Flux Kontext Lora text-to-image |
Super fast text-to-image endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
text-to-image |
OK | 2025/6/25 | → |
| Flux Kontext Lora image-to-image |
Fast endpoint for the FLUX.1 Kontext [dev] model with LoRA support, enabling rapid and high-quality image editing using pre-trained LoRA adaptations for specific styles, brand identities, and product-specific outputs.
image-editing image-to-image |
OK | 2025/6/25 | → |
| Omnigen V2 text-to-image |
OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!
multimodal editing try-on |
OK | 2025/6/25 | → |
| FASHN Virtual Try-On V1.6 image-to-image |
FASHN v1.6 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 864x1296 resolution from both on-model and flat-lay photo references.
try-on fashion clothing |
OK | 2025/6/24 | → |
| Ai Avatar image-to-video |
MultiTalk model generates a talking avatar video from an image and text. Converts text to speech automatically, then generates the avatar speaking with lip-sync.
stylized transform |
OK | 2025/6/23 | → |
| Ai Avatar image-to-video |
MultiTalk model generates a talking avatar video from an image and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.
stylized transform |
OK | 2025/6/23 | → |
| Ai Avatar image-to-video |
MultiTalk model generates a multi-person conversation video from an image and text inputs. Converts text to speech for each person, generating a realistic conversation scene.
stylized transform |
OK | 2025/6/23 | → |
| Ai Avatar image-to-video |
MultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.
stylized transform |
OK | 2025/6/23 | → |
| Video Understanding vision |
A video understanding model to analyze video content and answer questions about what's happening in the video based on user prompts.
utility vision |
OK | 2025/6/20 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
reframe |
OK | 2025/6/18 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
image-to-video video-to-video text-to-video |
OK | 2025/6/18 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
image-to-video video-to-video text-to-video |
OK | 2025/6/18 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
image-to-video video-to-video text-to-video |
OK | 2025/6/18 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
image-to-video video-to-video text-to-video |
OK | 2025/6/18 | → |
| Chain Of Zoom image-to-image | Extreme Super-Resolution via Scale Autoregression and Preference Alignment | OK | 2025/6/18 | → |
| Tripo3D image-to-3d |
State of the art Multiview to 3D Object generation. Generate 3D models from multiple images!
stylized multiview |
OK | 2025/6/18 | → |
| MiniMax Hailuo 02 [Standard] (Image to Video) image-to-video | MiniMax Hailuo-02 Image To Video API (Standard, 768p, 512p): Advanced image-to-video generation model with 768p and 512p resolutions | OK | 2025/6/18 | → |
| MiniMax Hailuo 02 [Pro] (Image to Video) image-to-video | MiniMax Hailuo-02 Image To Video API (Pro, 1080p): Advanced image-to-video generation model with 1080p resolution | OK | 2025/6/18 | → |
| MiniMax Hailuo 02 [Pro] (Text to Video) text-to-video | MiniMax Hailuo-02 Text To Video API (Pro, 1080p): Advanced video generation model with 1080p resolution | OK | 2025/6/18 | → |
| MiniMax Hailuo 02 [Standard] (Text to Video) text-to-video | MiniMax Hailuo-02 Text To Video API (Standard, 768p): Advanced video generation model with 768p resolution | OK | 2025/6/18 | → |
| PASD image-to-image |
Pixel-Aware Diffusion Model for Realistic Image Super-Resolution and Personalized Stylization
utility editing |
OK | 2025/6/17 | → |
| Bria 3.2 Text-to-Image text-to-image |
Bria’s Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Excels in Text-Rendering and Aesthetics.
image generation |
OK | 2025/6/17 | → |
| Object Removal image-to-image |
Removes box-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.
utility editing |
OK | 2025/6/16 | → |
| Object Removal image-to-image |
Removes mask-selected objects and their visual effects, seamlessly reconstructing the scene with contextually appropriate content.
utility editing |
OK | 2025/6/16 | → |
| Object Removal image-to-image |
Removes objects and their visual effects using natural language, replacing them with contextually appropriate content
utility editing |
OK | 2025/6/16 | → |
| Seedance 1.0 Pro text-to-video | Seedance 1.0 Pro, a high quality video generation model developed by Bytedance. | OK | 2025/6/16 | → |
| Seedance 1.0 Pro image-to-video | Seedance 1.0 Pro, a high quality video generation model developed by Bytedance. | OK | 2025/6/16 | → |
| DWPose Pose Prediction video-to-video |
Predict poses from videos.
pose utility |
OK | 2025/6/15 | → |
| Hunyuan 3D 2.1 image-to-3d |
Hunyuan3D-2.1 is a scalable 3D asset creation system that advances state-of-the-art 3D generation through Physically-Based Rendering (PBR).
image-to-3d |
OK | 2025/6/14 | → |
| Seedance 1.0 Lite image-to-video | Seedance 1.0 Lite | OK | 2025/6/13 | → |
| Seedance 1.0 Lite text-to-video | Seedance 1.0 Lite | OK | 2025/6/13 | → |
| Recraft image-to-image |
Converts a given raster image to SVG format using Recraft model.
stylized transform |
OK | 2025/6/12 | → |
| Imagen 4 text-to-image | Google’s highest quality image generation model | OK | 2025/6/12 | → |
| Wan-2.1 LoRA Trainer training |
Train custom LoRAs for Wan-2.1 T2V 1.3B
lora training |
OK | 2025/6/11 | → |
| Wan-2.1 LoRA Trainer training |
Train custom LoRAs for Wan-2.1 T2V 14B
lora training |
OK | 2025/6/11 | → |
| Wan-2.1 LoRA Trainer training |
Train custom LoRAs for Wan-2.1 I2V 720P
lora training |
OK | 2025/6/11 | → |
| Wan-2.1 LoRA Trainer training |
Train custom LoRAs for Wan-2.1 FLF2V 720P
lora training |
OK | 2025/6/11 | → |
| Bytedance text-to-image | Seedream 3.0 is a bilingual (Chinese and English) text-to-image model that excels at text-to-image generation. | OK | 2025/6/10 | → |
| Ffmpeg Api image-to-image |
ffmpeg endpoint for first, middle and last frame extraction from videos
utility editing |
OK | 2025/6/9 | → |
| Ffmpeg Api Merge Audio-Video video-to-video |
Merge videos with standalone audio files or audio from video files.
ffmpeg |
OK | 2025/6/9 | → |
| Luma Photon image-to-image |
Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.
image-to-image |
OK | 2025/6/8 | → |
| Luma Photon image-to-image |
Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.
image-to-image |
OK | 2025/6/8 | → |
| Veo 3 text-to-video | Veo 3 by Google, the most advanced AI video generation model in the world. With sound on! | OK | 2025/6/5 | → |
| Image Editing image-to-image |
The reframe endpoint intelligently adjusts an image's aspect ratio while preserving the main subject's position, composition, pose, and perspective
stylized transform |
OK | 2025/6/5 | → |
| Wan Vace 1 3b video-to-video |
Vace a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
video-to-video |
OK | 2025/6/4 | → |
| Image Editing image-to-image |
Transform any person into their baby version, while preserving the original pose and expression with childlike features.
stylized transform |
OK | 2025/6/3 | → |
| Luma Ray 2 Flash Reframe video-to-video |
Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.
reframe outpaint flash |
OK | 2025/6/3 | → |
| Luma Ray 2 Reframe video-to-video |
Adjust and enhance videos with Ray-2 Reframe. This advanced tool seamlessly reframes videos to your desired aspect ratio, intelligently inpainting missing regions to ensure realistic visuals and coherent motion, delivering exceptional quality and creative flexibility.
reframe outpaint |
OK | 2025/6/3 | → |
| Luma Photon Flash Reframe image-to-image |
This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched speed and quality for creators at a fraction of the cost.
flash reframe outpainting |
OK | 2025/6/3 | → |
| Luma Photon Reframe image-to-image |
Extend and reframe images with Luma Photon Reframe. This advanced tool intelligently expands your visuals, seamlessly blending new content to enhance creativity and adaptability, offering unmatched personalization and quality for creators at a fraction of the cost.
outpainting reframe |
OK | 2025/6/3 | → |
| Chatterboxhd speech-to-speech | Transform voices using Resemble AI's Chatterbox. Convert audio to new voices or your own samples, with expressive results and built-in perceptual watermarking. | OK | 2025/6/2 | → |
| Chatterboxhd text-to-speech | Generate expressive, natural speech with Resemble AI's Chatterbox. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking. | OK | 2025/6/2 | → |
| FLUX.1 [schnell] Redux image-to-image | FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities. | OK | 2025/6/2 | → |
| FLUX.1 [dev] Redux image-to-image | FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities. | OK | 2025/6/2 | → |
| FLUX.1 [dev] image-to-image | FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use. | OK | 2025/6/2 | → |
| FLUX.1 [schnell] text-to-image | Fastest inference in the world for the 12 billion parameter FLUX.1 [schnell] text-to-image model. | OK | 2025/6/2 | → |
| FLUX.1 [dev] text-to-image | FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use. | OK | 2025/6/2 | → |
| Image Editing image-to-image |
Remove all text and writing from images while preserving the background and natural appearance.
stylized transform |
OK | 2025/6/2 | → |
| Image Editing image-to-image |
Restore and enhance old or damaged photos by removing imperfections, adding color while preserving the original character and details of the image.
stylized transform |
OK | 2025/6/2 | → |
| Chatterbox speech-to-speech |
Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.
speech-to-speech |
OK | 2025/6/1 | → |
| Chatterbox text-to-speech |
Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. Use the first tts from resemble ai.
text-to-speech |
OK | 2025/6/1 | → |
| Image Editing image-to-image |
Add realistic weather effects like snowfall, rain, or fog to your photos while maintaining the scene's mood.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Transform your photos to any time of day, from golden hour to midnight, with appropriate lighting and atmosphere.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Transform your photos into artistic masterpieces inspired by famous styles like Van Gogh's Starry Night or any artistic style you choose.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Place your subject in any scene you imagine, from enchanted forests to urban settings, with professional composition and lighting
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Turn your casual photos into stunning professional studio portraits with perfect lighting and high-end photography style.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Remove unwanted objects or people from your photos while seamlessly blending the background.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Experiment with different hairstyles, from bald to any style you can imagine, while maintaining natural lighting and realistic results.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Enhance facial features with professional retouching while maintaining a natural, realistic look
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Change facial expressions in photos to any emotion you desire, from smiles to serious looks.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Perfect your photos with professional color grading, balanced tones, and vibrant yet natural colors
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Transform your photos into vibrant cool cartoons with bold outlines and rich colors.
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
Replace your photo's background with any scene you desire, from beach sunsets to urban landscapes, with perfect lighting and shadows
stylized transform |
OK | 2025/5/29 | → |
| Image Editing image-to-image |
See how you or others might look at different ages, from younger to older, while preserving core facial features.
stylized transform |
OK | 2025/5/29 | → |
| FLUX.1 Kontext [max] image-to-image | Experimental version of FLUX.1 Kontext [max] with multi image handling capabilities | OK | 2025/5/29 | → |
| FLUX.1 Kontext [pro] image-to-image | Experimental version of FLUX.1 Kontext [pro] with multi image handling capabilities | OK | 2025/5/29 | → |
| Hunyuan Avatar image-to-video |
HunyuanAvatar is a High-Fidelity Audio-Driven Human Animation model for Multiple Characters .
stylized transform |
OK | 2025/5/29 | → |
| FLUX.1 Kontext [max] image-to-image | FLUX.1 Kontext [max] is a model with greatly improved prompt adherence and typography generation meet premium consistency for editing without compromise on speed. | OK | 2025/5/29 | → |
| FLUX.1 Kontext [max] text-to-image | FLUX.1 Kontext [max] text-to-image is a new premium model brings maximum performance across all aspects – greatly improved prompt adherence. | OK | 2025/5/29 | → |
| Kling 2.1 Master text-to-video | Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision. | OK | 2025/5/29 | → |
| Kling 2.1 Master image-to-video |
Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.
_marquee-video-model |
OK | 2025/5/29 | → |
| Kling 2.1 (pro) image-to-video | Kling 2.1 Pro is an advanced endpoint for the Kling 2.1 model, offering professional-grade videos with enhanced visual fidelity, precise camera movements, and dynamic motion control, perfect for cinematic storytelling. | OK | 2025/5/28 | → |
| Kling 2.1 (standard) image-to-video | Kling 2.1 Standard is a cost-efficient endpoint for the Kling 2.1 model, delivering high-quality image-to-video generation | OK | 2025/5/28 | → |
| FLUX.1 Kontext [pro] text-to-image | The FLUX.1 Kontext [pro] text-to-image delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, and flawless typography. | OK | 2025/5/28 | → |
| FLUX.1 Kontext [dev] image-to-image | Frontier image editing model. | OK | 2025/5/28 | → |
| FLUX.1 Kontext [pro] image-to-image | FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes. | OK | 2025/5/28 | → |
| Lipsync video-to-video |
Generate realistic lipsync from any audio using VEED's latest model
lipsync video-to-video avatar |
OK | 2025/5/28 | → |
| Avatars text-to-video |
Generate high-quality videos with UGC-like avatars from text
lipsync text-to-video |
OK | 2025/5/28 | → |
| Avatars audio-to-video |
Generate high-quality videos with UGC-like avatars from audio
lipsync audio-to-video |
OK | 2025/5/28 | → |
| Hunyuan Portrait image-to-video |
HunyuanPortrait is a diffusion-based framework for generating lifelike, temporally consistent portrait animations.
animation lip sync |
OK | 2025/5/27 | → |
| Wan VACE 14B video-to-video |
VACE is a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
image-to-video video-to-video text-to-video |
OK | 2025/5/27 | → |
| Bagel image-to-json |
Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.
image-to-text vlm |
OK | 2025/5/21 | → |
| Bagel image-to-image |
Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both images and text.
image-to-image image-editing |
OK | 2025/5/21 | → |
| Bagel text-to-image |
Bagel is a 7B parameter from Bytedance-Seed multimodal model that can generate both text and images.
text-to-image multimodal |
OK | 2025/5/21 | → |
| Lyria2 text-to-audio |
Lyria 2 is Google's latest music generation model, you can generate any type of music with this model.
music stylized |
OK | 2025/5/20 | → |
| Imagen 4 Ultra text-to-image | Google’s highest quality image generation model | OK | 2025/5/20 | → |
| Imagen 4 text-to-image | Google’s highest quality image generation model | OK | 2025/5/20 | → |
| Kling 1.6 Elements image-to-video | Generate video clips from your multiple image references using Kling 1.6 (standard) | OK | 2025/5/20 | → |
| Kling 1.6 Elements image-to-video | Generate video clips from your multiple image references using Kling 1.6 (pro) | OK | 2025/5/20 | → |
| DreamO text-to-image |
DreamO is an image customization framework designed to support a wide range of tasks while facilitating seamless integration of multiple conditions.
stylized realism |
OK | 2025/5/19 | → |
| LTX Video-0.9.7 13B Distilled video-to-video |
Extend videos using LTX Video-0.9.7 13B Distilled and custom LoRA
video ltx-video video-to-video extend-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B Distilled video-to-video |
Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA
video ltx-video video-to-video multicondition-to-video image-to-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B Distilled image-to-video |
Generate videos from prompts and images using LTX Video-0.9.7 13B Distilled and custom LoRA
video ltx-video image-to-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B video-to-video |
Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B and custom LoRA
video ltx-video video-to-video multicondition-to-video image-to-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B video-to-video |
Extend videos using LTX Video-0.9.7 13B and custom LoRA
video ltx-video video-to-video extend-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B image-to-video |
Generate videos from prompts and images using LTX Video-0.9.7 13B and custom LoRA
video ltx-video image-to-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B text-to-video |
Generate videos from prompts using LTX Video-0.9.7 13B and custom LoRA
video ltx-video text-to-video |
OK | 2025/5/17 | → |
| LTX Video-0.9.7 13B Distilled text-to-video |
Generate videos from prompts using LTX Video-0.9.7 13B Distilled and custom LoRA
video ltx-video text-to-video |
OK | 2025/5/17 | → |
| Flux Lora text-to-image |
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2025/5/15 | → |
| LTX Video-0.9.7 LoRA video-to-video |
Generate videos from prompts, images, and videos using LTX Video-0.9.7 and custom LoRA
video ltx-video video-to-video multicondition-to-video image-to-video |
OK | 2025/5/15 | → |
| LTX Video-0.9.7 LoRA image-to-video |
Generate videos from prompts and images using LTX Video-0.9.7 and custom LoRA
video ltx-video image-to-video |
OK | 2025/5/15 | → |
| LTX Video-0.9.7 LoRA text-to-video |
Deprecated.
Use fal-ai/ltx-video-13b-dev or fal-ai/ltx-video-13b-distilled instead.
video ltx-video text-to-video |
Deprecated | 2025/5/15 | → |
| Pixverse image-to-video |
Create seamless transition between images using PixVerse v4.5
stylized transform |
OK | 2025/5/15 | → |
| Pixverse image-to-video |
Generate fast high quality video clips from text and image prompts using PixVerse v4.5
stylized transform |
OK | 2025/5/15 | → |
| Pixverse image-to-video |
Generate high quality video clips from text and image prompts using PixVerse v4.5
stylized transform |
OK | 2025/5/15 | → |
| Pixverse text-to-video |
Generate high quality and fast video clips from text and image prompts using PixVerse v4.5 fast
stylized transform |
OK | 2025/5/15 | → |
| Pixverse text-to-video |
Generate high quality video clips from text and image prompts using PixVerse v4.5
stylized transform |
OK | 2025/5/15 | → |
| Pixverse image-to-video |
Generate high quality video clips with different effects using PixVerse v4.5
image-to-video |
OK | 2025/5/15 | → |
| Hunyuan Custom image-to-video |
HunyuanCustom revolutionizes video generation with unmatched identity consistency across multiple input types. Its innovative fusion modules and alignment networks outperform competitors, maintaining subject integrity while responding flexibly to text, image, audio, and video conditions.
image-to-video |
OK | 2025/5/14 | → |
| Framepack F1 image-to-video |
Framepack is an efficient Image-to-video model that autoregressively generates videos.
image to video motion |
OK | 2025/5/13 | → |
| ACE-Step audio-to-audio |
Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step
audio-to-audio audio-outpaint audio-extend |
OK | 2025/5/11 | → |
| ACE-Step audio-to-audio |
Modify a portion of provided audio with lyrics and/or style using ACE-Step
audio-to-audio audio-inpaint audio-repaint |
OK | 2025/5/11 | → |
| ACE-Step audio-to-audio |
Generate music from a lyrics and example audio using ACE-Step
audio-to-audio audio-edit |
OK | 2025/5/11 | → |
| ACE-Step text-to-audio |
Generate music from a simple prompt using ACE-Step
text-to-audio text-to-music |
OK | 2025/5/11 | → |
| Rembg Enhance (Remove Background Enhance) image-to-image |
Rembg-enhance is optimized for 2D vector images, 3D graphics, and photos by leveraging matting technology.
background removal image editing utility segmentation high resolution rembg |
OK | 2025/5/9 | → |
| Vidu Start End to Video image-to-video |
Vidu Q1 Start-End to Video generates smooth transition 1080p videos between specified start and end images.
stylized transform |
OK | 2025/5/9 | → |
| Vidu Text to Video text-to-video |
Vidu Q1 Text to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity
stylized transform |
OK | 2025/5/9 | → |
| Vidu Image to Video image-to-video |
Vidu Q1 Image to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity from a single image
stylized transform |
OK | 2025/5/9 | → |
| ACE-Step text-to-audio |
Generate music with lyrics from text using ACE-Step
text-to-audio text-to-music |
OK | 2025/5/8 | → |
| LTX Video Trainer training |
Train LTX Video 0.9.7 for custom styles and effects.
ltx-video fine-tuning |
OK | 2025/5/8 | → |
| Recraft Creative Upscale image-to-image |
Enhances a given raster image using the 'creative upscale' tool, increasing image resolution, making the image sharper and cleaner.
upscaling |
OK | 2025/5/7 | → |
| Recraft Crisp Upscale image-to-image |
Enhances a given raster image using 'crisp upscale' tool, boosting resolution with a focus on refining small details and faces.
upscaling |
OK | 2025/5/7 | → |
| Recraft V3 Create Style training |
Recraft V3 Create Style is capable of creating unique styles for Recraft V3 based on your images.
style vector personalization |
OK | 2025/5/7 | → |
| Recraft V3 image-to-image |
Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.
vector typography style |
OK | 2025/5/7 | → |
| Recraft V3 text-to-image |
Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.
vector typography style |
OK | 2025/5/7 | → |
| Ltx Video V097 video-to-video | Deprecated. Use fal-ai/ltx-video-13b-dev or fal-ai/ltx-video-13b-distilled instead. | Deprecated | 2025/5/6 | → |
| MiniMax Voice Cloning text-to-speech |
Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/5/6 | → |
| MiniMax Speech-02 Turbo text-to-speech |
Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/5/6 | → |
| LTX Video-0.9.7 video-to-video |
Deprecated.
Use fal-ai/ltx-video-13b-dev or fal-ai/ltx-video-13b-distilled instead.
video image-to-video text-to-video |
Deprecated | 2025/5/6 | → |
| MiniMax Speech-02 HD text-to-speech |
Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/5/6 | → |
| LTX Video-0.9.7 text-to-video |
Deprecated.
Use fal-ai/ltx-video-13b-dev or fal-ai/ltx-video-13b-distilled instead.
video text-video |
Deprecated | 2025/5/6 | → |
| LTX Video-0.9.7 image-to-video |
Deprecated.
Use fal-ai/ltx-video-13b-dev or fal-ai/ltx-video-13b-distilled instead.
video image-to-video |
Deprecated | 2025/5/6 | → |
| Minimax Image Subject Reference image-to-image |
Generate images from text and a reference image using MiniMax Image-01 for consistent character appearance.
stylized transform |
OK | 2025/5/6 | → |
| MiniMax (Hailuo AI) Text to Image text-to-image |
Generate high quality images from text prompts using MiniMax Image-01. Longer text prompts will result in better quality images.
stylized realism |
OK | 2025/5/6 | → |
| Hidream I1 Full image-to-image |
HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.
image-to-image hidream |
OK | 2025/5/5 | → |
| Pony V7 text-to-image |
Pony V7 is a finetuned text to image for superior aesthetics and prompt following.
diffusion style |
OK | 2025/5/5 | → |
| Trellis image-to-3d |
Generate 3D models from multiple images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/5/2 | → |
| Ideogram image-to-image |
Extend existing images with Ideogram V3's reframe feature. Create expanded versions and adaptations while preserving main image and adding new creative directions through prompt guidance.
realism typography |
OK | 2025/5/1 | → |
| Ideogram Text to Image text-to-image |
Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.
realism typography |
OK | 2025/5/1 | → |
| Ideogram Replace Background image-to-image | Replace backgrounds existing images with Ideogram V3's replace background feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance. | OK | 2025/5/1 | → |
| Ideogram image-to-image |
Reimagine existing images with Ideogram V3's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.
realism typography |
OK | 2025/5/1 | → |
| Ideogram V3 Edit image-to-image |
Transform existing images with Ideogram V3's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.
realism typography |
OK | 2025/5/1 | → |
| Hidream E1 Full image-to-image | Edit images with natural language | Deprecated | 2025/4/29 | → |
| F Lite text-to-image | F Lite is a 10B parameter diffusion model created by Fal and Freepik, trained exclusively on copyright-safe and SFW content. | OK | 2025/4/28 | → |
| F Lite (texture mode) text-to-image | F Lite is a 10B parameter diffusion model created by Fal and Freepik, trained exclusively on copyright-safe and SFW content. This is a high texture density variant of the model. | OK | 2025/4/28 | → |
| Moondream2 vision |
Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.
Vision |
OK | 2025/4/26 | → |
| Moondream2 vision |
Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.
Vision |
OK | 2025/4/26 | → |
| Moondream2 vision |
Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.
image-to-image |
OK | 2025/4/26 | → |
| Moondream2 vision |
Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.
image-to-image |
OK | 2025/4/26 | → |
| Step1X Edit image-to-image |
Step1X-Edit transforms your photos with simple instructions into stunning, professional-quality edits—rivaling top proprietary tools.
editing |
OK | 2025/4/25 | → |
| Tripo3D image-to-3d |
State of the art Image to 3D Object generation. Generate 3D model from a single image!
image-to-3d stylized |
OK | 2025/4/25 | → |
| Image2svg image-to-image |
Image2SVG transforms raster images into clean vector graphics, preserving visual quality while enabling scalable, customizable SVG outputs with precise control over detail levels.
utility editing |
OK | 2025/4/25 | → |
| Uno image-to-image |
An AI model that transforms input images into new ones based on text prompts, blending reference visuals with your creative directions.
image-to-image |
OK | 2025/4/24 | → |
| MAGI-1 video-to-video |
MAGI-1 extends videos with an exceptional understanding of physical interactions and prompts
video-to-video |
OK | 2025/4/23 | → |
| MAGI-1 text-to-video |
MAGI-1 is a video generation model with exceptional understanding of physical interactions and cinematic prompts
text-to-video |
OK | 2025/4/23 | → |
| MAGI-1 image-to-video |
MAGI-1 generates videos from images with exceptional understanding of physical interactions and prompting
image-to-video |
OK | 2025/4/23 | → |
| gpt-image-1 text-to-image | OpenAI's latest image generation and editing model: gpt-1-image. | OK | 2025/4/23 | → |
| gpt-image-1 image-to-image | OpenAI's latest image generation and editing model: gpt-1-image. | OK | 2025/4/23 | → |
| Pixverse image-to-video |
Generate high quality video clips with different effects using PixVerse v4
image-to-video |
OK | 2025/4/23 | → |
| MAGI-1 (Distilled) video-to-video |
MAGI-1 distilled extends videos faster with an exceptional understanding of physical interactions and prompts
video-to-video video-extend |
OK | 2025/4/23 | → |
| MAGI-1 (Distilled) image-to-video |
MAGI-1 distilled generates videos faster from images with exceptional understanding of physical interactions and prompting
image-to-video |
OK | 2025/4/23 | → |
| Dia Tts audio-to-audio |
Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.
speech |
OK | 2025/4/22 | → |
| Framepack image-to-video |
Framepack is an efficient Image-to-video model that autoregressively generates videos.
image to video motion |
OK | 2025/4/22 | → |
| Dia text-to-speech |
Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.
text-to-speech |
OK | 2025/4/22 | → |
| MAGI-1 (Distilled) text-to-video |
MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts
text-to-video |
OK | 2025/4/22 | → |
| Pipecat's Smart Turn model speech-to-text | An open source, community-driven and native audio turn detection model by Pipecat AI. | OK | 2025/4/21 | → |
| Juggernaut Flux Lora image-to-image | Juggernaut Base Flux LoRA Inpainting by RunDiffusion is a drop-in replacement for Flux [Dev] inpainting that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility. | OK | 2025/4/21 | → |
| FASHN Virtual Try-On V1.5 image-to-image |
FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.
try-on fashion clothing |
OK | 2025/4/21 | → |
| Plushify image-to-image | Turn any image into a cute plushie! | OK | 2025/4/20 | → |
| Instant Character image-to-image |
InstantCharacter creates high-quality, consistent characters from text prompts, supporting diverse poses, styles, and appearances with strong identity control.
personalization customization |
OK | 2025/4/18 | → |
| Wan-2.1 First-Last-Frame-to-Video image-to-video |
Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.
image to video motion |
OK | 2025/4/17 | → |
| Turbo Flux Trainer training | A blazing fast FLUX dev LoRA trainer for subjects and styles. | OK | 2025/4/17 | → |
| Framepack image-to-video |
Framepack is an efficient Image-to-video model that autoregressively generates videos.
image to video motion |
OK | 2025/4/17 | → |
| Kling 2.0 Master image-to-video | Generate video clips from your images using Kling 2.0 Master | OK | 2025/4/14 | → |
| Kling 2.0 Master text-to-video | Generate video clips from your prompts using Kling 2.0 Master | OK | 2025/4/14 | → |
| Cartoonify image-to-image |
Transform images into 3D cartoon artwork using an AI model that applies cartoon stylization while preserving the original image's composition and details.
stylized transform |
OK | 2025/4/14 | → |
| Vace video-to-video |
Vace a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.
video-to-video image-to-video text-to-video |
OK | 2025/4/11 | → |
| Hidream I1 Full text-to-image | HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds. | OK | 2025/4/11 | → |
| Hidream I1 Dev text-to-image | HiDream-I1 dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds. | OK | 2025/4/11 | → |
| Hidream I1 Fast text-to-image |
HiDream-I1 fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within 16 steps.
|
OK | 2025/4/11 | → |
| finegrain eraser image-to-image |
Finegrain Eraser removes any object selected with a mask—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.
utility editing |
OK | 2025/4/10 | → |
| finegrain eraser image-to-image |
Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.
utility editing |
OK | 2025/4/9 | → |
| finegrain eraser image-to-image |
Finegrain Eraser removes objects—along with their shadows, reflections, and lighting artifacts—using only natural language, seamlessly filling the scene with contextually accurate content.
utility editing |
OK | 2025/4/9 | → |
| Video Sound Effects Generator video-to-video |
Add sound effects to your videos
sound-effects sfx cassetteai |
OK | 2025/4/7 | → |
| Speech-to-Text speech-to-text | Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription. | OK | 2025/4/4 | → |
| Speech-to-Text speech-to-text |
Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.
streaming |
OK | 2025/4/4 | → |
| Speech-To-text speech-to-text |
Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.
streaming |
OK | 2025/4/4 | → |
| Speech-to-Text speech-to-text |
Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.
|
OK | 2025/4/4 | → |
| Sound Effects Generator text-to-audio |
Create stunningly realistic sound effects in seconds - CassetteAI's Sound Effects Model generates high-quality SFX up to 30 seconds long in just 1 second of processing time
sound sfx sound-effects cassetteai |
OK | 2025/4/3 | → |
| Sync Lipsync 2.0 video-to-video |
Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model
animation lip sync |
OK | 2025/4/1 | → |
| FLUX.1 [dev] text-to-image | FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use. | OK | 2025/4/1 | → |
| StarVector image-to-image |
AI vectorization model that transforms raster images into scalable SVG graphics, preserving visual details while enabling infinite scaling and easy editing capabilities.
image-to-image |
OK | 2025/4/1 | → |
| PixVerse v4: Image to Video Fast image-to-video | Generate fast high quality video clips from text and image prompts using PixVerse v4 | OK | 2025/4/1 | → |
| PixVerse v4: Image to Video image-to-video | Generate high quality video clips from text and image prompts using PixVerse v4 | OK | 2025/4/1 | → |
| PixVerse v3.5: Effects image-to-video | Generate high quality video clips with different effects using PixVerse v3.5 | OK | 2025/4/1 | → |
| PixVerse v4: Text to Video text-to-video | Generate high quality video clips from text and image prompts using PixVerse v4 | OK | 2025/4/1 | → |
| PixVerse v3.5: Transition image-to-video | Create seamless transition between images using PixVerse v3.5 | OK | 2025/4/1 | → |
| PixVerse v4: Text to Video Fast text-to-video | Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast | OK | 2025/4/1 | → |
| Ghiblify Images image-to-image |
Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork
stylized transform |
OK | 2025/3/31 | → |
| Orpheus TTS text-to-speech |
Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.
text to speech voice synthesis high-fidelity |
OK | 2025/3/31 | → |
| Sana v1.5 1.6B text-to-image |
Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.
text to image 4k lightweight |
OK | 2025/3/31 | → |
| Sana v1.5 4.8B text-to-image |
Sana v1.5 4.8B is a powerful text-to-image model that generates ultra-high quality 4K images with remarkable detail.
text to image 4k high-quality |
OK | 2025/3/31 | → |
| Sana Sprint text-to-image |
Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.
text to image 4k high-speed |
OK | 2025/3/31 | → |
| music generator text-to-audio |
CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.
music cassetteai |
OK | 2025/3/27 | → |
| Kling LipSync Text-to-Video text-to-video |
Kling LipSync is a text-to-video model that generates realistic lip movements from text input.
text to video lipsync |
OK | 2025/3/27 | → |
| Kling LipSync Audio-to-Video text-to-video |
Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.
audio to video lipsync |
OK | 2025/3/27 | → |
| LatentSync video-to-video |
LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.
animation lip sync |
OK | 2025/3/25 | → |
| Wan-2.1 Text-to-Video with LoRAs text-to-video |
Add custom LoRAs to Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from images
"text to video" "motion" "lora" |
OK | 2025/3/25 | → |
| Wan-2.1 LoRA Trainer training |
Train custom LoRAs for Wan-2.1 I2V 480P
lora training |
OK | 2025/3/24 | → |
| Thera image-to-image | Fix low resolution images with fast speed and quality of thera. | OK | 2025/3/24 | → |
| MixDehazer image-to-image | An advanced dehaze model to remove atmospheric haze, restoring clarity and detail in images through intelligent neural network processing. | OK | 2025/3/24 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Gemini Flash Edit Multi Image image-to-image |
Gemini Flash Edit is a model that can edit single image using a text prompt and a reference image.
editing |
OK | 2025/3/20 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Hunyuan3D image-to-3d |
Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2025/3/20 | → |
| Gemini Flash Edit Multi Image image-to-image |
Gemini Flash Edit Multi Image is a model that can edit multiple images using a text prompt and a reference image.
editing |
OK | 2025/3/20 | → |
| Luma Ray 2 Flash (Image to Video) image-to-video |
Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.
motion transformation |
OK | 2025/3/17 | → |
| Luma Ray 2 Flash text-to-video |
Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.
motion transformation |
OK | 2025/3/17 | → |
| Pika Effects (v1.5) image-to-video |
Pika Effects are AI-powered video effects designed to modify objects, characters, and environments in a fun, engaging, and visually compelling manner.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Image to Video Turbo (v2) image-to-video |
Turbo is the model to use when you feel the need for speed. Turn your image to stunning video up to 3x faster – all with high quality outputs.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Text to Video (v2.2) text-to-video |
Start with a simple text input to create dynamic generations that defy expectations in up to 1080p. Experience better image clarity and crisper, sharper visuals.
editing effects animation |
OK | 2025/3/14 | → |
| Invisible Watermark image-to-image |
Invisible Watermark is a model that can add an invisible watermark to an image.
utility editing |
OK | 2025/3/14 | → |
| Pika Text to Video (v2.1) text-to-video |
Start with a simple text input to create dynamic generations that defy expectations. Anything you dream can come to life with sharp details, impressive character control and cinematic camera moves.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Text to Video Turbo (v2) text-to-video |
Pika v2 Turbo creates videos from a text prompt with high quality output.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Image to Video (v2.2) image-to-video |
Turn photos into mind-blowing, dynamic videos in up to 1080p. Experience better image clarity and crisper, sharper visuals.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Scenes (v2.2) image-to-video |
Pika Scenes v2.2 creates videos from a images with high quality output.
editing effects animation |
OK | 2025/3/14 | → |
| Pika Image to Video (v2.1) image-to-video |
Turn photos into mind-blowing, dynamic videos. Your images can can come to life with sharp details, impressive character control and cinematic camera moves.
editing effects animation |
OK | 2025/3/14 | → |
| Pikadditions (v2) video-to-video |
Pikadditions is a powerful video-to-video AI model that allows you to add anyone or anything to any video with seamless integration.
editing effects animation |
OK | 2025/3/14 | → |
| CSM-1B text-to-audio |
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
conversational text to speech |
OK | 2025/3/13 | → |
| Wan Effects image-to-video |
Wan Effects generates high-quality videos with popular effects from images
motion effects |
OK | 2025/3/13 | → |
| Vidu Image to Video image-to-video |
Vidu Image to Video generates high-quality videos with exceptional visual quality and motion diversity from a single image
motion image to video |
OK | 2025/3/12 | → |
| Vidu Start-End to Video image-to-video |
Vidu Start-End to Video generates smooth transition videos between specified start and end images.
motion transition |
OK | 2025/3/12 | → |
| Vidu Reference to Video image-to-video |
Vidu Reference to Video creates videos by using a reference images and combining them with a prompt.
motion reference |
OK | 2025/3/12 | → |
| Vidu Template to Video image-to-video |
Vidu Template to Video lets you create different effects by applying motion templates to your images.
motion template |
OK | 2025/3/12 | → |
| Wan-2.1 Pro Image-to-Video image-to-video |
Wan-2.1 Pro is a premium image-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from images
image to video motion |
OK | 2025/3/11 | → |
| Wan-2.1 Pro Text-to-Video text-to-video |
Wan-2.1 Pro is a premium text-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from text prompts
text to video motion |
OK | 2025/3/11 | → |
| Veo 2 (Image to Video) image-to-video |
Veo 2 creates videos from images with realistic motion and very high quality output.
motion transformation |
OK | 2025/3/11 | → |
| Wan-2.1 Image-to-Video with LoRAs image-to-video |
Add custom LoRAs to Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images
image to video motion lora |
OK | 2025/3/8 | → |
| Kling 1.5 text-to-video | Generate video clips from your prompts using Kling 1.5 (pro) | OK | 2025/3/6 | → |
| Kling 1.0 text-to-video |
Generate video clips from your prompts using Kling 1.0
motion |
OK | 2025/3/6 | → |
| Kling 1.6 text-to-video | Generate video clips from your prompts using Kling 1.6 (pro) | OK | 2025/3/6 | → |
| Kling 1.6 text-to-video | Generate video clips from your prompts using Kling 1.6 (std) | OK | 2025/3/6 | → |
| Hunyuan Video Image-to-Video Inference image-to-video |
Image to Video for the high-quality Hunyuan Video I2V model.
motion |
OK | 2025/3/6 | → |
| Juggernaut Flux Lightning text-to-image |
Juggernaut Lightning Flux by RunDiffusion provides blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.
image generation |
OK | 2025/3/5 | → |
| Juggernaut Flux Pro image-to-image |
Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.
image generation |
OK | 2025/3/5 | → |
| Rundiffusion Photo Flux text-to-image |
RunDiffusion Photo Flux provides insane realism. With this enhancer, textures and skin details burst to life, turning your favorite prompts into vivid, lifelike creations. Recommended to keep it at 0.65 to 0.80 weight. Supports resolutions up to 1536x1536.
image generation lora |
OK | 2025/3/5 | → |
| Juggernaut Flux Base LoRA text-to-image |
Juggernaut Base Flux LoRA by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.
image generation |
OK | 2025/3/5 | → |
| Juggernaut Flux Base image-to-image |
Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.
image generation |
OK | 2025/3/5 | → |
| LTX Video-0.9.5 video-to-video |
Generate videos from prompts and videos using LTX Video-0.9.5
video video-to-video |
OK | 2025/3/5 | → |
| LTX Video-0.9.5 text-to-video |
Generate videos from prompts using LTX Video-0.9.5
video text-video |
OK | 2025/3/5 | → |
| LTX Video-0.9.5 video-to-video |
Generate videos from prompts,images, and videos using LTX Video-0.9.5
video image-to-video text-to-video |
OK | 2025/3/5 | → |
| Juggernaut Flux Pro text-to-image |
Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.
image generation |
OK | 2025/3/5 | → |
| Juggernaut Flux Base text-to-image |
Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.
image generation |
OK | 2025/3/5 | → |
| LTX Video-0.9.5 image-to-video |
Generate videos from prompts and images using LTX Video-0.9.5
video image-to-video |
Deprecated | 2025/3/5 | → |
| CogView text-to-image |
Generate high quality images from text prompts using CogView4. Longer text prompts will result in better quality images.
stylized |
OK | 2025/3/4 | → |
| Topaz Video Upscale video-to-video |
Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.
upscaling high-res |
OK | 2025/3/4 | → |
| DiffRhythm: Lyrics to Song text-to-audio |
DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.
music |
OK | 2025/3/4 | → |
| DocRes-dewarp image-to-image |
Enhance wraped, folded documents with the superior quality of docres for sharper, clearer results.
image-enhancement |
OK | 2025/3/3 | → |
| DocRes image-to-image |
Enhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.
image-enhancement |
OK | 2025/3/3 | → |
| SWIN2SR image-to-image |
Enhance low-resolution images with the superior quality of Swin2SR for sharper, clearer results.
image-enhancement |
OK | 2025/2/28 | → |
| Ideogram V2A Remix image-to-image |
Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.
realism typography |
OK | 2025/2/27 | → |
| Kling 1.6 text-to-video | Generate video clips from your prompts using Kling 1.6 (pro) | OK | 2025/2/27 | → |
| Ideogram V2A Turbo Remix image-to-image |
Rapidly create image variations with Ideogram V2A Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.
realism typography |
OK | 2025/2/27 | → |
| ElevenLabs TTS Multilingual v2 text-to-audio |
Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.
audio |
OK | 2025/2/27 | → |
| Wan-2.1 1.3B Text-to-Video text-to-video |
Wan-2.1 1.3B is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text promptsat faster speeds.
text to video motion |
OK | 2025/2/27 | → |
| Ideogram V2A Turbo text-to-image |
Accelerated image generation with Ideogram V2A Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.
realism typography |
OK | 2025/2/27 | → |
| ElevenLabs Speech to Text speech-to-text |
Generate text from speech using ElevenLabs advanced speech-to-text model.
speech |
OK | 2025/2/27 | → |
| ElevenLabs Audio Isolation audio-to-audio |
Isolate audio tracks using ElevenLabs advanced audio isolation technology.
audio |
OK | 2025/2/27 | → |
| ElevenLabs TTS Turbo v2.5 text-to-speech |
Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.
audio |
OK | 2025/2/27 | → |
| Ideogram V2A text-to-image |
Generate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.
realism typography |
OK | 2025/2/27 | → |
| EVF-SAM2 Segmentation image-to-image |
EVF-SAM2 combines natural language understanding with advanced segmentation capabilities, allowing you to precisely mask image regions using intuitive positive and negative text prompts.
segmentation mask |
OK | 2025/2/26 | → |
| DDColor image-to-image |
Bring colors into old or new black and white photos with DDColor.
image-recolorization faces utility |
OK | 2025/2/26 | → |
| Wan-2.1 Text-to-Video text-to-video |
Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts
text to video motion |
OK | 2025/2/25 | → |
| Wan-2.1 Image-to-Video image-to-video |
Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images
image to video motion |
OK | 2025/2/25 | → |
| Video Prompt Generator llm |
Generate video prompts using a variety of techniques including camera direction, style, pacing, special effects and more.
motion transformation chat claude gpt |
OK | 2025/2/25 | → |
| Segment Anything Model 2 image-to-image |
SAM 2 is a model for segmenting images automatically. It can return individual masks or a single mask for the entire image.
segmentation mask |
OK | 2025/2/25 | → |
| MiniMax (Hailuo AI) Video 01 Director - Image to Video image-to-video |
Generate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.
motion transformation camera-controls |
OK | 2025/2/24 | → |
| DRCT-Super-Resolution image-to-image |
Upscale your images with DRCT-Super-Resolution.
upscaling high-res |
OK | 2025/2/24 | → |
| Veo 2 text-to-video |
Veo 2 creates videos with realistic motion and high quality output. Explore different styles and find your own with extensive camera controls.
motion transformation |
OK | 2025/2/21 | → |
| NAFNet-deblur image-to-image |
Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.
image-restoration deblur denoise |
OK | 2025/2/21 | → |
| NAFNet-denoise image-to-image |
Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.
image-restoration deblur denoise |
OK | 2025/2/21 | → |
| Post Processing image-to-image |
Post Processing is an endpoint that can enhance images using a variety of techniques including grain, blur, sharpen, and more.
stylized utility |
OK | 2025/2/18 | → |
| Skyreels V1 (Image-to-Video) image-to-video |
SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips
motion |
OK | 2025/2/18 | → |
| Flow-Edit image-to-image |
The model provides you high quality image editing capabilities.
editing |
OK | 2025/2/14 | → |
| Kokoro TTS (Mandarin Chinese) text-to-audio |
A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (Hindi) text-to-audio |
A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (Brazilian Portuguese) text-to-audio |
A natural and expressive Brazilian Portuguese text-to-speech model optimized for clarity and fluency.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (Spanish) text-to-audio |
A natural-sounding Spanish text-to-speech model optimized for Latin American and European Spanish.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (French) text-to-audio |
An expressive and natural French text-to-speech model for both European and Canadian French.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (British English) text-to-audio |
A high-quality British English text-to-speech model offering natural and expressive voice synthesis.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS text-to-audio |
Kokoro is a lightweight text-to-speech model that delivers comparable quality to larger models while being significantly faster and more cost-efficient.
speech |
OK | 2025/2/14 | → |
| Kokoro TTS (Japanese) text-to-audio |
A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.
speech |
OK | 2025/2/14 | → |
| Zonos-Audio-Clone text-to-audio |
Clone voice of any person and speak anything in their voice using zonos' voice cloning.
voice cloning |
OK | 2025/2/14 | → |
| Kokoro TTS (Italian) text-to-audio |
A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.
speech |
OK | 2025/2/14 | → |
| Luma Ray 2 (Image to Video) image-to-video |
Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.
motion transformation |
OK | 2025/2/14 | → |
| GOT OCR 2.0 vision |
GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.
optical character recognition high-res utility |
OK | 2025/2/12 | → |
| FLUX.1 [dev] Control LoRA Canny image-to-image |
FLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.
lora style transfer |
OK | 2025/2/11 | → |
| FLUX.1 [dev] Control LoRA Depth image-to-image |
FLUX Control LoRA Depth is a high-performance endpoint that uses a control image using a depth map to transfer structure to the generated image and another initial image to guide color.
lora style transfer |
OK | 2025/2/11 | → |
| ben-v2-image image-to-image |
A fast and high quality model for image background removal.
background removal |
OK | 2025/2/11 | → |
| FLUX.1 [dev] Control LoRA Canny text-to-image |
FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.
lora style transfer |
OK | 2025/2/11 | → |
| FLUX.1 [dev] Control LoRA Depth text-to-image |
FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.
lora style transfer |
OK | 2025/2/11 | → |
| MiniMax (Hailuo AI) Video 01 Director text-to-video |
Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control.
motion transformation camera-controls |
OK | 2025/2/11 | → |
| Ben-Video-Bg-Rm video-to-video |
A model for high quality and smooth background removal for videos.
segmentation background removal |
OK | 2025/2/11 | → |
| Imagen3 text-to-image | Imagen3 is a high-quality text-to-image model that generates realistic images from text prompts. | OK | 2025/2/10 | → |
| Imagen3 Fast text-to-image | Imagen3 Fast is a high-quality text-to-image model that generates realistic images from text prompts. | OK | 2025/2/10 | → |
| Ideogram Upscale image-to-image |
Ideogram Upscale enhances the resolution of the reference image by up to 2X and might enhance the reference image too. Optionally refine outputs with a prompt for guided improvements.
upscaling high-res |
OK | 2025/2/10 | → |
| Hunyuan Video Image-to-Video LoRA Inference image-to-video |
Image to Video for the Hunyuan Video model using a custom trained LoRA.
motion |
OK | 2025/2/3 | → |
| CodeFormer image-to-image |
Fix distorted or blurred photos of people with CodeFormer.
image-restoration faces utility |
OK | 2025/1/31 | → |
| Lumina Image 2 text-to-image |
Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
diffusion typography style |
OK | 2025/1/31 | → |
| Hunyuan Video (Video-to-Video) video-to-video |
Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.
video to video motion |
OK | 2025/1/30 | → |
| Hunyuan Video LoRA Inference (Video-to-Video) video-to-video |
Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.
video to video motion lora |
OK | 2025/1/30 | → |
| PixVerse v3.5 text-to-video | Generate high quality video clips from text prompts using PixVerse v3.5 | OK | 2025/1/29 | → |
| PixVerse v3.5: Image to Video Fast image-to-video | Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast | OK | 2025/1/29 | → |
| PixVerse v3.5 Fast text-to-video | Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast | OK | 2025/1/29 | → |
| PixVerse v3.5: Image to Video image-to-video | Generate high quality video clips from text and image prompts using PixVerse v3.5 | OK | 2025/1/29 | → |
| DeepSeek Janus-Pro text-to-image |
DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework
stylized |
OK | 2025/1/28 | → |
| YuE: Lyrics to Song text-to-audio |
YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs.
music |
OK | 2025/1/28 | → |
| Luma Ray 2 text-to-video |
Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.
motion transformation |
OK | 2025/1/27 | → |
| Kling Kolors Virtual TryOn v1.5 image-to-image |
Kling Kolors Virtual TryOn v1.5 is a high quality image based Try-On endpoint which can be used for commercial try on.
try-on fashion clothing |
OK | 2025/1/23 | → |
| FFmpeg API Metadata json |
Get encoding metadata from video and audio files using FFmpeg API.
ffmpeg |
OK | 2025/1/22 | → |
| FFmpeg API Waveform json |
Get waveform data from audio files using FFmpeg API.
ffmpeg |
OK | 2025/1/22 | → |
| FFmpeg API Compose video-to-video |
Compose videos from multiple media sources using FFmpeg API.
ffmpeg |
OK | 2025/1/22 | → |
| MiniMax (Hailuo AI) Video 01 Subject Reference image-to-video |
Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content
subject transformation |
OK | 2025/1/20 | → |
| MoonDreamNext Batch vision |
MoonDreamNext Batch is a multimodal vision-language model for batch captioning.
multimodal |
OK | 2025/1/17 | → |
| FLUX.1 [dev] Canny with LoRAs image-to-image |
Utilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.
controlnet detection lora editing composition |
OK | 2025/1/16 | → |
| FLUX1.1 [pro] text-to-image | FLUX1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor. | OK | 2025/1/16 | → |
| FLUX1.1 [pro] ultra Fine-tuned text-to-image |
FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.
high-res realism |
OK | 2025/1/16 | → |
| FLUX.1 [pro] Fill Fine-tuned image-to-image |
FLUX.1 [pro] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 [pro] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
editing |
OK | 2025/1/16 | → |
| Hunyuan Video LoRA Inference text-to-video | Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability | OK | 2025/1/16 | → |
| Train Hunyuan LoRA training |
Train Hunyuan Video lora on people, objects, characters and more!
lora personalization |
OK | 2025/1/14 | → |
| CogVideoX-5B text-to-video | Generate videos from prompts using CogVideoX-5B | OK | 2025/1/14 | → |
| TransPixar V1 text-to-video | Transform text into stunning videos with TransPixar - an AI model that generates both RGB footage and alpha channels, enabling seamless compositing and creative video effects. | OK | 2025/1/14 | → |
| sync.so -- lipsync 1.9.0-beta video-to-video |
Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization.
animation lip sync |
OK | 2025/1/13 | → |
| Sa2VA 8B Video vision |
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
multimodal vision |
OK | 2025/1/13 | → |
| Sa2VA 4B Video vision |
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
multimodal vision |
OK | 2025/1/13 | → |
| Sa2VA 4B Image vision |
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
multimodal vision |
OK | 2025/1/13 | → |
| Sa2VA 8B Image vision |
Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels
multimodal vision |
OK | 2025/1/13 | → |
| MoonDreamNext vision |
MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.
multimodal vision |
OK | 2025/1/9 | → |
| MoonDreamNext Detection image-to-image |
MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.
multimodal |
OK | 2025/1/9 | → |
| Kling 1.6 image-to-video | Generate video clips from your images using Kling 1.6 (pro) | OK | 2025/1/7 | → |
| Kling 1.6 text-to-video | Generate video clips from your prompts using Kling 1.6 (std) | OK | 2025/1/7 | → |
| Kling 1.6 image-to-video | Generate video clips from your images using Kling 1.6 (std) | OK | 2025/1/7 | → |
| Auto-Captioner video-to-video |
Automatically generates text captions for your videos from the audio as per text colour/font specifications
captioning video |
OK | 2025/1/3 | → |
| Train Flux LoRA training |
Train styles, people and other subjects at blazing speeds.
lora personalization |
OK | 2025/1/1 | → |
| Switti 1024 text-to-image | Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models. | OK | 2024/12/31 | → |
| Switti 512 text-to-image | Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models. | OK | 2024/12/31 | → |
| MMAudio V2 Text to Audio text-to-audio |
MMAudio generates synchronized audio given text inputs. It can generate sounds described by a prompt.
audio fast |
OK | 2024/12/20 | → |
| Sad Talker image-to-video |
Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
animation |
OK | 2024/12/20 | → |
| Dubbing video-to-video |
This endpoint delivers seamlessly localized videos by generating lip-synced dubs in multiple languages, ensuring natural and immersive multilingual experiences
animation lip sync dubbing |
OK | 2024/12/20 | → |
| Bria Expand Image image-to-image |
Bria Expand expands images beyond their borders in high quality. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us
outpainting |
OK | 2024/12/19 | → |
| Bria Text-to-Image Fast text-to-image |
Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us
image generation |
OK | 2024/12/19 | → |
| Bria Text-to-Image Base text-to-image |
Bria's Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us
image generation |
OK | 2024/12/19 | → |
| Bria GenFill image-to-image |
Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us
image editing |
OK | 2024/12/19 | → |
| Bria Background Replace image-to-image |
Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use
image editing |
OK | 2024/12/19 | → |
| Bria Eraser image-to-image |
Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us
image editing object removal |
OK | 2024/12/19 | → |
| FLUX.1 [dev] Fill with LoRAs image-to-image |
FLUX.1 [dev] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
editing lora |
OK | 2024/12/19 | → |
| Bria Text-to-Image HD text-to-image |
Bria's Text-to-Image model for HD images. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us
image generation |
OK | 2024/12/19 | → |
| Bria Product Shot image-to-image |
Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.
product photography |
OK | 2024/12/19 | → |
| Bria RMBG 2.0 image-to-image |
Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04
background removal image segmentation high resolution utility rembg |
OK | 2024/12/19 | → |
| try-on image-to-image |
Image based high quality Virtual Try-On
try-on fashion clothing |
OK | 2024/12/17 | → |
| Leffa Pose Transfer image-to-image |
Leffa Pose Transfer is an endpoint for changing pose of an image with a reference image.
pose utility |
OK | 2024/12/17 | → |
| FLUX1.1 [pro] ultra text-to-image |
FLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.
high-res realism |
OK | 2024/12/17 | → |
| Leffa Virtual TryOn image-to-image |
Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.
try-on fashion clothing |
OK | 2024/12/17 | → |
| MiniMax (Hailuo AI) Music text-to-audio |
Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.
music |
OK | 2024/12/17 | → |
| MiniMax (Hailuo AI) Video 01 Live image-to-video |
Generate video clips from your images using MiniMax Video model
motion transformation |
OK | 2024/12/16 | → |
| Recraft 20b text-to-image |
Recraft 20b is a new and affordable text-to-image model.
image generation vector art typograph style |
OK | 2024/12/16 | → |
| Hyper3D Rodin image-to-3d |
Rodin by Hyper3D generates realistic and production ready 3D models from text or images.
stylized |
OK | 2024/12/16 | → |
| MiniMax (Hailuo AI) Video 01 Live text-to-video |
Generate video clips from your prompts using MiniMax model
motion transformation |
OK | 2024/12/16 | → |
| Ideogram V2 Edit image-to-image |
Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.
realism typography |
OK | 2024/12/14 | → |
| Trellis image-to-3d |
Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.
stylized |
OK | 2024/12/13 | → |
| MMAudio V2 video-to-video |
MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.
ai video fast |
OK | 2024/12/12 | → |
| Ideogram V2 text-to-image |
Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.
realism typography |
OK | 2024/12/4 | → |
| Ideogram V2 Turbo text-to-image |
Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.
realism typography |
OK | 2024/12/4 | → |
| Video Upscaler video-to-video |
The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.
video generation video to video ai video high fidelity motion |
OK | 2024/12/4 | → |
| Ideogram V2 Turbo Edit image-to-image |
Edit images faster with Ideogram V2 Turbo. Quick modifications and adjustments while preserving the high-quality standards and realistic outputs of Ideogram.
realism typography |
OK | 2024/12/4 | → |
| Ideogram V2 Turbo Remix image-to-image |
Rapidly create image variations with Ideogram V2 Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.
realism typography |
OK | 2024/12/4 | → |
| Ideogram V2 Remix image-to-image |
Reimagine existing images with Ideogram V2's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.
realism typography |
OK | 2024/12/4 | → |
| Kling 1.0 text-to-video |
Generate video clips from your prompts using Kling 1.0
motion |
OK | 2024/12/3 | → |
| Luma Photon Flash text-to-image | Generate images from your prompts using Luma Photon Flash. Photon Flash is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation. | OK | 2024/12/3 | → |
| AuraFlow text-to-image |
AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta.
typography style |
OK | 2024/12/2 | → |
| OmniGen v1 text-to-image |
OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!
multimodal editing try-on |
OK | 2024/11/29 | → |
| FLUX.1 [schnell] Redux image-to-image |
FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
style transfer |
OK | 2024/11/27 | → |
| Kling 1.5 text-to-video | Generate video clips from your prompts using Kling 1.5 (pro) | OK | 2024/11/25 | → |
| FLUX.1 [schnell] text-to-image | FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use. | OK | 2024/11/25 | → |
| FLUX1.1 [pro] Redux image-to-image |
FLUX1.1 [pro] Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
style transfer |
OK | 2024/11/21 | → |
| FLUX.1 [dev] Redux image-to-image |
FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
|
OK | 2024/11/21 | → |
| FLUX.1 [dev] Depth with LoRAs image-to-image |
Generate high-quality images from depth maps using Flux.1 [dev] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.
depth lora utility composition |
OK | 2024/11/21 | → |
| LTX Video (preview) image-to-video | Generate videos from images using LTX Video | OK | 2024/11/21 | → |
| FLUX1.1 [pro] ultra Redux image-to-image |
FLUX1.1 [pro] ultra Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
style transfer high-res |
OK | 2024/11/21 | → |
| FLUX.1 [pro] Fill image-to-image |
FLUX.1 [pro] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
editing |
OK | 2024/11/21 | → |
| FLUX.1 [pro] Redux image-to-image |
FLUX.1 [pro] Redux is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
style transfer |
Deprecated | 2024/11/21 | → |
| Kolors Image to Image image-to-image |
Photorealistic Image-to-Image
realism editing diffusion |
OK | 2024/11/19 | → |
| IC-Light-v2 for Image Relighting image-to-image |
An endpoint for re-lighting photos and changing their backgrounds per a given description
relighting editing |
OK | 2024/11/14 | → |
| Mochi 1 text-to-video | Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation. | OK | 2024/11/7 | → |
| Train Flux LoRAs For Portraits training |
FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.
lora personalization |
OK | 2024/11/7 | → |
| FLUX.1 [dev] Differential Diffusion image-to-image |
FLUX.1 Differential Diffusion is a rapid endpoint that enables swift, granular control over image transformations through change maps, delivering fast and precise region-specific modifications while maintaining FLUX.1 [dev]'s high-quality output.
transformation |
OK | 2024/11/6 | → |
| MiniMax (Hailuo AI) Video 01 image-to-video |
Generate video clips from your images using MiniMax Video model
motion transformation |
OK | 2024/10/30 | → |
| PuLID Flux image-to-image |
An endpoint for personalized image generation using Flux as per given description.
personalization style transfer |
OK | 2024/10/29 | → |
| Birefnet Background Removal image-to-image |
bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)
background removal segmentation high-res utility |
OK | 2024/10/28 | → |
| Stable Diffusion 3.5 Large text-to-image |
Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
diffusion typography style |
OK | 2024/10/27 | → |
| Stable Diffusion 3.5 Medium text-to-image |
Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
diffusion typography style |
OK | 2024/10/27 | → |
| Hunyuan Video text-to-video |
Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.
motion |
OK | 2024/10/22 | → |
| CogVideoX-5B image-to-video | Generate videos from images and prompts using CogVideoX-5B | OK | 2024/10/17 | → |
| F5 TTS text-to-audio |
F5 TTS
speech |
OK | 2024/10/17 | → |
| CogVideoX-5B video-to-video |
Generate videos from videos and prompts using CogVideoX-5B
editing |
OK | 2024/10/17 | → |
| LLaVA v1.5 13B vision |
Vision
multimodal vision |
Deprecated | 2024/10/5 | → |
| Kling 1.0 image-to-video |
Generate video clips from your images using Kling 1.0 (pro)
motion |
OK | 2024/10/4 | → |
| Kling 1.5 image-to-video | Generate video clips from your images using Kling 1.5 (pro) | OK | 2024/10/4 | → |
| Kling 1.0 image-to-video |
Generate video clips from your images using Kling 1.0
motion |
OK | 2024/10/4 | → |
| Kling 1.0 text-to-video |
Generate video clips from your prompts using Kling 1.0 (pro)
motion |
OK | 2024/10/4 | → |
| LTX Video (preview) text-to-video | Generate videos from prompts using LTX Video | OK | 2024/10/4 | → |
| FLUX.1 [pro] text-to-image | FLUX.1 [pro] new is an accelerated version of FLUX.1 [pro], maintaining professional-grade image quality while delivering significantly faster generation speeds. | Deprecated | 2024/10/3 | → |
| Live Portrait image-to-image |
Transfer expression from a video to a portrait.
expression animation |
OK | 2024/10/1 | → |
| FLUX.1 [dev] Inpainting with LoRAs text-to-image |
Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2024/9/18 | → |
| FLUX.1 [dev] with Controlnets and Loras image-to-image |
A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.
rf-inversion editing lora |
OK | 2024/9/17 | → |
| High Quality Stable Video Diffusion image-to-video | Generate short video clips from your images using SVD v1.1 | OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
Holistically-Nested Edge Detection (HED) preprocessor.
preprocess detection utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
Scribble preprocessor.
preprocess utility editing controlnet sketch |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
Depth Anything v2 preprocessor.
depth preprocess utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
MiDaS depth estimation preprocessor.
depth preprocess utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
Line art preprocessor.
preprocess utility sketch controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
Segment Anything Model (SAM) preprocessor.
segmentation preprocess utility mask controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
ZoeDepth preprocessor.
depth preprocess utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
TEED (Temporal Edge Enhancement Detection) preprocessor.
preprocess detection utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
M-LSD line segment detection preprocessor.
preprocess utility controlnet |
OK | 2024/9/16 | → |
| Image Preprocessors image-to-image |
PIDI (Pidinet) preprocessor.
detection preprocess utility controlnet |
OK | 2024/9/16 | → |
| Stable Video Diffusion text-to-video | Generate short video clips from your prompts using SVD v1.1 | OK | 2024/9/16 | → |
| ControlNeXt SVD video-to-video |
Animate a reference image with a driving video using ControlNeXt.
animation stylized |
OK | 2024/9/5 | → |
| FLUX.1 [dev] with Controlnets and Loras text-to-image |
A versatile endpoint for the FLUX.1 [dev] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.
lora controlnet ip-adapter |
OK | 2024/8/21 | → |
| Stable Diffusion V3 text-to-image |
Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.
diffusion style |
OK | 2024/8/20 | → |
| Segment Anything Model image-to-image |
SAM.
segmentation mask |
Deprecated | 2024/8/20 | → |
| Segment Anything Model 2 image-to-image |
SAM 2 is a model for segmenting images and videos in real-time.
segmentation mask real-time |
OK | 2024/8/15 | → |
| Segment Anything Model 2 video-to-video |
SAM 2 is a model for segmenting images and videos in real-time.
segmentation mask real-time |
OK | 2024/8/15 | → |
| FLUX.1 [dev] with Controlnets and Loras image-to-image |
FLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.
lora controlnet ip-adapter |
OK | 2024/8/14 | → |
| FLUX.1 [dev] with Controlnets and Loras image-to-image |
FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.
lora controlnet ip-adapter |
OK | 2024/8/14 | → |
| FLUX.1 [dev] with Controlnets and Loras image-to-image |
A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.
lora controlnet ip-adapter |
OK | 2024/8/13 | → |
| FLUX.1 [dev] with LoRAs image-to-image |
FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.
lora style transfer |
OK | 2024/8/13 | → |
| Fooocus Upscale or Vary text-to-image |
Default parameters with automated optimizations and quality improvements.
upscaling vary stylized |
OK | 2024/8/12 | → |
| FLUX.1 Subject text-to-image |
Super fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.
personalization customization |
OK | 2024/8/1 | → |
| Sana text-to-image | Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, with the ability to generate 4K images in less than a second. | OK | 2024/8/1 | → |
| PixArt-Σ text-to-image |
Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
diffusion |
OK | 2024/8/1 | → |
| FLUX.1 [dev] with LoRAs text-to-image |
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
lora personalization |
OK | 2024/8/1 | → |
| SDXL ControlNet Union text-to-image |
An efficent SDXL multi-controlnet text-to-image model.
diffusion controlnet composition |
OK | 2024/7/31 | → |
| SDXL ControlNet Union image-to-image |
An efficent SDXL multi-controlnet image-to-image model.
diffusion controlnet composition |
OK | 2024/7/31 | → |
| SDXL ControlNet Union image-to-image |
An efficent SDXL multi-controlnet inpainting model.
diffusion controlnet composition |
OK | 2024/7/31 | → |
| Kolors text-to-image |
Photorealistic Text-to-Image
realism diffusion |
OK | 2024/7/24 | → |
| AMT Frame Interpolation image-to-video |
Interpolate between image frames
interpolation editing |
OK | 2024/7/18 | → |
| MusePose video-to-video | Animate a reference image with a driving video using MusePose. | Deprecated | 2024/7/18 | → |
| FLUX.1 [dev] image-to-image |
FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
style transfer |
OK | 2024/7/11 | → |
| Live Portrait image-to-video |
Transfer expression from a video to a portrait.
expression animation |
OK | 2024/7/9 | → |
| Era 3D image-to-image | A powerful image to novel multiview model with normals. | OK | 2024/7/1 | → |
| Stable Cascade text-to-image |
Stable Cascade: Image generation on a smaller & cheaper latent space.
diffusion lcm |
OK | 2024/6/25 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
detection multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision detection |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
ocr multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
captioning multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
ocr multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision segmentation |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
captioning multimodal vision |
OK | 2024/6/22 | → |
| Florence-2 Large image-to-image |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
multimodal vision segmentation |
OK | 2024/6/22 | → |
| Florence-2 Large vision |
Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks
captioning multimodal vision |
OK | 2024/6/22 | → |
| Stable Diffusion XL text-to-image |
Run SDXL at the speed of light
diffusion lora embeddings high-res style |
OK | 2024/6/12 | → |
| Stable Diffusion V3 image-to-image |
Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.
diffusion editing style |
OK | 2024/6/12 | → |
| SoteDiffusion text-to-image |
Anime finetune of Würstchen V3.
lcm stylized |
OK | 2024/6/10 | → |
| Luma Photon text-to-image | Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation. | OK | 2024/6/3 | → |
| Stable Video Diffusion Turbo text-to-video |
Generate short video clips from your images using SVD v1.1 at Lightning Speed
lcm diffusion turbo |
OK | 2024/6/3 | → |
| DWPose Pose Prediction image-to-image |
Predict poses from images.
pose utility |
OK | 2024/6/1 | → |
| SD 1.5 Depth ControlNet image-to-image |
SD 1.5 ControlNet
diffusion editing manipulation controlnet |
OK | 2024/5/31 | → |
| CCSR Upscaler image-to-image |
SOTA Image Upscaler
upscaling |
OK | 2024/5/5 | → |
| Omni Zero image-to-image |
Any pose, any style, any identity
style transfer |
OK | 2024/4/25 | → |
| Lightning Models text-to-image |
Collection of SDXL Lightning models.
diffusion lightning |
OK | 2024/4/25 | → |
| Playground v2.5 text-to-image |
State-of-the-art open-source model in aesthetic quality
artistic style |
OK | 2024/4/25 | → |
| Hyper SDXL image-to-image |
Hyper-charge SDXL's performance and creativity.
diffusion editing |
OK | 2024/4/25 | → |
| Realistic Vision text-to-image |
Generate realistic images.
realism diffusion |
OK | 2024/4/25 | → |
| Dreamshaper text-to-image |
Dreamshaper model.
stylized diffusion |
OK | 2024/4/25 | → |
| Hyper SDXL image-to-image |
Hyper-charge SDXL's performance and creativity.
diffusion |
OK | 2024/4/25 | → |
| IP Adapter Face ID image-to-image |
High quality zero-shot personalization
ip-adapter personalization customization editing |
OK | 2024/4/22 | → |
| Stable Diffusion with LoRAs image-to-image |
Run Any Stable Diffusion model with customizable LoRA weights.
diffusion lora customization fine-tuning |
OK | 2024/4/18 | → |
| Stable Diffusion with LoRAs image-to-image |
Run Any Stable Diffusion model with customizable LoRA weights.
diffusion lora customization fine-tuning |
OK | 2024/4/17 | → |
| Stable Diffusion XL image-to-image |
Run SDXL at the speed of light
diffusion high-res lora ip-adapter controlnet |
OK | 2024/4/16 | → |
| Stable Diffusion XL image-to-image |
Run SDXL at the speed of light
diffusion high-res lora ip-adapter controlnet |
OK | 2024/4/16 | → |
| Stable Diffusion v1.5 text-to-image |
Stable Diffusion v1.5
diffusion |
OK | 2024/4/16 | → |
| Layer Diffusion XL text-to-image | SDXL with an alpha channel. | OK | 2024/4/13 | → |
| MuseTalk image-to-video |
MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.
animation lip sync real-time |
OK | 2024/4/11 | → |
| Stable Diffusion XL Lightning text-to-image |
Run SDXL at the speed of light
diffusion lightning real-time |
OK | 2024/4/11 | → |
| AuraSR image-to-image |
Upscale your images with AuraSR.
upscaling high-res |
OK | 2024/4/11 | → |
| Sad Talker image-to-video |
Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
animation |
OK | 2024/4/11 | → |
| Wizper (Whisper v3 -- fal.ai edition) speech-to-text |
[Experimental] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!
transcription speech |
OK | 2024/4/8 | → |
| NSFW Filter vision |
Predict the probability of an image being NSFW.
filter safety utility |
OK | 2024/3/22 | → |
| Moondream vision |
Answer questions from the images.
multimodal vision |
OK | 2024/3/20 | → |
| Fooocus text-to-image |
Fooocus extreme speed mode as a standalone app.
stylized |
OK | 2024/3/13 | → |
| Face to Sticker image-to-image |
Create stickers from faces.
sticker editing |
OK | 2024/3/11 | → |
| PhotoMaker image-to-image |
Customizing Realistic Human Photos via Stacked ID Embedding
editing customization realism personalization |
OK | 2024/3/8 | → |
| T2V Turbo - Video Crafter text-to-video |
Generate short video clips from your prompts
turbo |
OK | 2024/3/8 | → |
| ControlNet SDXL text-to-image |
Generate Images with ControlNet.
diffusion controlnet manipulation |
OK | 2024/2/28 | → |
| Creative Upscaler image-to-image |
Create creative upscaled images.
upscaling |
OK | 2024/2/27 | → |
| Birefnet Background Removal image-to-image |
bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)
background removal segmentation high-res utility |
OK | 2024/2/27 | → |
| Stable Diffusion XL Lightning image-to-image |
Run SDXL at the speed of light
diffusion lightning editing |
OK | 2024/2/21 | → |
| Playground v2.5 image-to-image |
State-of-the-art open-source model in aesthetic quality
inpaint artistic style |
OK | 2024/2/21 | → |
| Stable Diffusion XL Lightning image-to-image |
Run SDXL at the speed of light
diffusion lightning |
OK | 2024/2/21 | → |
| Hyper SDXL text-to-image |
Hyper-charge SDXL's performance and creativity.
diffusion real-time |
OK | 2024/2/21 | → |
| Playground v2.5 image-to-image |
State-of-the-art open-source model in aesthetic quality
artistic style |
OK | 2024/2/21 | → |
| AMT Interpolation video-to-video |
Interpolate between video frames
interpolation editing |
OK | 2024/2/21 | → |
| AnimateDiff text-to-video |
Animate your ideas!
animation stylized |
OK | 2024/2/21 | → |
| Whisper speech-to-text |
Whisper is a model for speech transcription and translation.
transcription translation speech |
OK | 2024/2/19 | → |
| Latent Consistency Models (v1.5/XL) image-to-image |
Run SDXL at the speed of light
lcm diffusion turbo real-time editing |
OK | 2024/2/19 | → |
| Latent Consistency Models (v1.5/XL) text-to-image |
Run SDXL at the speed of light
lcm diffusion turbo real-time |
OK | 2024/2/19 | → |
| Latent Consistency Models (v1.5/XL) image-to-image |
Run SDXL at the speed of light
lcm diffusion turbo real-time editing |
OK | 2024/2/19 | → |
| Fooocus text-to-image | Fooocus extreme speed mode as a standalone app. | OK | 2024/2/16 | → |
| LLaVA v1.6 34B vision |
Vision
multimodal vision |
OK | 2024/2/14 | → |
| AnimateDiff Turbo text-to-video |
Animate your ideas in lightning speed!
animation stylized turbo |
OK | 2024/2/13 | → |
| Illusion Diffusion text-to-image |
Create illusions conditioned on image.
composition stylized |
OK | 2024/2/13 | → |
| Fooocus Image Prompt text-to-image |
Default parameters with automated optimizations and quality improvements.
stylized |
OK | 2024/2/13 | → |
| Face Retoucher image-to-image |
Automatically retouches faces to smooth skin and remove blemishes.
editing |
OK | 2024/2/13 | → |
| Stable Video Diffusion Turbo image-to-video |
Generate short video clips from your images using SVD v1.1 at Lightning Speed
turbo |
OK | 2024/2/13 | → |
| Midas Depth Estimation image-to-image |
Create depth maps using Midas depth estimation.
depth utility |
OK | 2024/2/13 | → |
| AnimateDiff Turbo video-to-video |
Re-animate your videos in lightning speed!
animation stylized turbo |
OK | 2024/2/13 | → |
| Fooocus Inpainting text-to-image |
Default parameters with automated optimizations and quality improvements.
stylized editing |
OK | 2024/2/13 | → |
| MiniMax (Hailuo AI) Video 01 text-to-video |
Generate video clips from your prompts using MiniMax model
motion transformation |
OK | 2024/2/13 | → |
| AnimateDiff video-to-video |
Re-animate your videos!
animation stylized |
OK | 2024/2/13 | → |
| Clarity Upscaler image-to-image |
Clarity upscaler for upscaling images with high very fidelity.
upscaling |
OK | 2024/2/4 | → |
| Latent Consistency (SDXL & SDv1.5) text-to-image |
Produce high-quality images with minimal inference steps.
diffusion lcm real-time |
OK | 2024/2/4 | → |
| TripoSR image-to-3d | State of the art Image to 3D Object generation | OK | 2024/1/30 | → |
| DiffusionEdge text-to-image |
Diffusion based high quality edge detection
detection |
OK | 2024/1/8 | → |
| Stable Audio Open text-to-audio |
Open source text-to-audio model.
music |
OK | 2024/1/4 | → |
| Marigold Depth Estimation image-to-image |
Create depth maps using Marigold depth estimation.
depth utility |
OK | 2023/12/28 | → |
| PuLID image-to-image |
Tuning-free ID customization.
editing customization personalization |
OK | 2023/12/14 | → |
| ControlNet SDXL image-to-image |
Generate Images with ControlNet.
diffusion controlnet editing manipulation |
OK | 2023/12/1 | → |
| ControlNet SDXL image-to-image |
Generate Images with ControlNet.
diffusion controlnet editing manipulation |
OK | 2023/12/1 | → |
| Fooocus text-to-image |
Default parameters with automated optimizations and quality improvements.
stylized |
OK | 2023/11/16 | → |
| Optimized Latent Consistency (SDv1.5) image-to-image |
Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.
diffusion lcm real-time |
OK | 2023/11/9 | → |
| Animatediff SparseCtrl LCM text-to-video |
Animate Your Drawings with Latent Consistency Models!
lcm animation stylized |
OK | 2023/11/9 | → |
| Inpainting sdxl and sd image-to-image |
Inpaint images with SD and SDXL
editing diffusion |
OK | 2023/11/4 | → |
| ControlNet SDXL image-to-image |
Generate Images with ControlNet.
diffusion controlnet manipulation |
Deprecated | 2023/11/1 | → |
| Upscale Images image-to-image |
Upscale images by a given factor.
upscaling high-res |
OK | 2023/10/30 | → |
| Remove Background image-to-image |
Remove the background from an image.
background removal utility editing |
OK | 2023/10/5 | → |
| Stable Diffusion with LoRAs text-to-image |
Run Any Stable Diffusion model with customizable LoRA weights.
diffusion lora customization |
OK | 2023/9/26 | → |