Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalizations

real time face swap and one-click video deepfake with only a single image (uncensored)

Make one portrait alive!

A set of nodes to use Reference UNets

A general fine-tuning kit geared toward Stable Diffusion 2.1, Stable Diffusion 3, DeepFloyd, and SDXL.

ComfyUI nodes for LivePortrait

Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”.

Live2Diff: A Pipeline that processes Live video streams by a uni-directional video Diffusion model.

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

Official Pytorch implementation of StreamV2V.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

ViViD: Video Virtual Try-on using Diffusion Models

[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Your image is almost there!

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

Making large AI models cheaper, faster and more accessible

Code release for CVPR'24 submission 'OmniGlue'