Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"

This is the official implementation of our Señorita-2M [Weights and Dataset] : A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

Rectified Flow Inversion (RF-Inversion) - ICLR 2025

Enjoy the magic of Diffusion models!

[NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

[SIGGRAPH-ASIA 2025] Official implementation of "VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models"

[arXiv 2025] VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

MetaDrive: Lightweight driving simulator for everyone

VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

[arXiv 2025] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]

[ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

A pipeline parallel training script for diffusion models.

TripoSR: Fast 3D Object Reconstruction from a Single Image

Official code for 4Diffusion: Multi-view Video Diffusion Model for 4D Generation.

Video-P2P: Video Editing with Cross-attention Control

MagicEdit: High-Fidelity Temporally Coherent Video Editing

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Make self forcing endless. Add cache purging. Add prompt controllability.

Tooling for the Common Objects In 3D dataset.