NVIDIA FastGen: Fast Generation from Diffusion Models

Advancing Open-source World Models

A curated list of papers on reinforcement learning for video generation

Community trainer for Lightricks' LTX Video model 🎬 ⚡️

Foundation Models and Data for Human-Human and Human-AI interactions.

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

SkyReels-V2: Infinite-length Film Generative model

[CVPR 2025] Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

[Arxiv 2025] ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions

[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

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.

Lets make video diffusion practical!

Enjoy the magic of Diffusion models!

Wan: Open and Advanced Large-Scale Video Generative Models

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer

[CVPR 2025 Highlight] X-Dyna: Expressive Dynamic Human Image Animation

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

Subjects200K dataset

Official inference repo for FLUX.1 models

[ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

GenXD: Generating Any 3D and 4D Scenes. ICLR 2025

Official repository of In-Context LoRA for Diffusion Transformers

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.