Wan: Open and Advanced Large-Scale Video Generative Models
Gradio demo for MatAnyone
Remove backgrounds from images and videos
The Ultimate Anime-themed SDXL model
A unified multimodal understanding and generation model.
A simple, high-quality voice conversion tool
Display code snippets for different chat providers
Generate videos from text prompts
Generate detailed images from a prompt and an image
Spanish finetune for the original F5 model.
Remove/Change background of video.
Run 3D human pose estimation with images
Combine and process audio files
Remove backgrounds from images