IDM VTON
High-fidelity Virtual Try-on
High-fidelity Virtual Try-on
Generate personalized images that keep your face identity
Inpaint objects out of your videos
Apply the motion of a video on a portrait
Generate lip‑synced video from a face image and audio
Remove/Change background of video.
Image generator/identifier/reposer
Generate realistic virtual try‑on and pose‑transfer images
Generate images with SD3.5
Quickly edit the expression of a face
Generate new images from a subject photo and text prompt
Generate personalized portraits of a specific person from photos
Generate chat responses using a language model
Chat with an AI assistant for detailed responses
Generate text responses to user queries
Generate a 3D model from a single image
Generate a 3D mesh from a single image
Generate 3D models from images
Generate images from text prompts with Stable Diffusion 3
Generate images fast with SD3.5 turbo
Generate images with SD3.5
Generate images from text prompts in seconds
Generate images from your text prompts
Generate image variations
Canny Edges FLUX.1 control
Depth Control for FLUX
Inpaint images with text prompts
Generate virtual try‑on images
Generate videos from text prompts (optional image)
Unified Framework for Generalized Video Face Restoration
Edit images with color and edge scribbles
Flexible Photo Recrafting While Preserving Your Identity
Large Animatable Human Model
Hunyuan T1模型体验
Generate images from text prompts
Generate realistic dialogue from a script, using Dia!
Text-to-Video
Generate any application by Vibe Coding it
Kolors Character to keep character developed with Flux
Audio-Driven Multi-Person Conversational Video Generation
ultra-fast video model, LTX 0.9.8 13B distilled
Generate audio from video and text prompts
Higgs Audio Demo
Kontext image editing on FLUX[dev]
Image-to-3D Generation
Generate detailed images from text prompts with AI enhancement
Expressive Zeroshot TTS
Generate a short video with audio from an image and prompt
Wan: Open and Advanced Large-Scale Video Generative Models
Execute custom code from environment variable
Consistency generation of portrait and subject
Universal Image Editing is worth a single LoRA
Generate videos from text prompts or images
Fast 4 step inference with Qwen Image Edit 2509
Generate Hollywood Style Actors on your Local Machine
MiniMax-Remover is a fast and effective video object remover
Generate speech in a custom voice from reference audio
Generate or edit images from text prompts
Generate detailed images from your text prompts
Edit image perspective by adjusting camera angle
Generate edited images with detailed control
Clarity AI Upscaler Reproduction
Generate sharp, focused images from blurry photos with interactive refocusing
Generate images from text prompts in seconds
Generate a short video from an image and prompt
Image edit, text to image, image upscale, remove watermark
Audio-driven talking-head video generation (Meituan LongCat)
text to video, image to video, video extend
text to video, image to video, video extend
Video generation with a synchronized soundtrack
Ultra-fast local NVFP4 video + synchronized audio generation
generate a video from an image with a text prompt
A gradio platform for demonstrating MOSS-VoiceGenerator