HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

[NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"

Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Open-source unified multimodal model

[ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

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

Enjoy the magic of Diffusion models!

WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

A pipeline parallel training script for diffusion models.

[ICLR'25] Official PyTorch implementation of "Framer: Interactive Frame Interpolation".

Official inference repo for FLUX.1 models

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

List of papers on 4D Generation.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Official implementation of AnimateDiff.

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

High-resolution models for human tasks.

A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.

[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Face analysis tools for modern research, equipped with state-of-the-art Face Parsing and Face Alignment

Generative Models by Stability AI