Investigating CoT Reasoning in Autoregressive Image Generation

[arXiv 2025] Official pytorch implementation of "FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors"

[CVPR 2024] BIVDiff: A Training-free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models

SmartEraser, built with a new removing paradigm called Masked-Region Guidance. This paradigm retains the masked region in the input, using it as guidance for the removal process.

MINIMA: Modality Invariant Image Matching

cursor IDE enjoy VIP

Official implementation of "Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation"

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

HunyuanVideo: A Systematic Framework For Large Video Generation Model

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

More relighting!

Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

The best OSS video generation models

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Official repository for LTX-Video

VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

Boosting Generative Novel View Synthesis with Sparse and Unposed Images

LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors

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

Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

A generative world for general-purpose robotics & embodied AI learning.

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

An official implementation of PRM, a feed-forward framework for high-quality 3D mesh generation from a single image.

Grounding Image Matching in 3D with MASt3R

MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

DUSt3R: Geometric 3D Vision Made Easy