MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

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

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Benchmark dataset and code of MSRVTT-Personalization

Official code for "Opening up Open World Tracking" (CVPR 2022)

CVPR2025

[CVPR 2025🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

HunyuanVideo: A Systematic Framework For Large Video Generation Model

[CVPR'25]Tora: Trajectory-oriented Diffusion Transformer for Video Generation

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

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration

The official repository of UVOSAM

The official repository of EffiVED

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Fine-Grained Open Domain Image Animation with Motion Guidance

A new one shot face swap approach for image and video domains

pytorch implementation of openpose including Hand and Body Pose Estimation.

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)

Open-Sora: Democratizing Efficient Video Production for All

RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models [CVPR 2024]

Finetune ModelScope's Text To Video model using Diffusers 🧨

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

Fine-Grained Open Domain Image Animation with Motion Guidance