Perceptual video quality assessment based on multi-method fusion.

A suite of image and video neural tokenizers

Memory optimized finetuning scripts for CogVideoX & Mochi using TorchAO and DeepSpeed

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

High-resolution models for human tasks.

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

📹 A more flexible CogVideoX that can generate videos at any resolution and creates videos from images.

PantoMatrix: Co-Speech Talking Head and Gestures Generation

[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

[ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Towards Variable and Coordinated Holistic Co-Speech Motion Generation, CVPR 2024

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.

This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].

[CVPR'24] DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

Video-Infinity generates long videos quickly using multiple GPUs without extra training.

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

VideoSys: An easy and efficient system for video generation

Open-Sora: Democratizing Efficient Video Production for All

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

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

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

3D Gaussian Splat Editor

HaMeR: Reconstructing Hands in 3D with Transformers

4DHumans: Reconstructing and Tracking Humans with Transformers