[CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)

Code release for https://kovenyu.com/WonderWorld/

Simulation platform for general-purpose robotics & embodied AI learning.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

[CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

[NeurIPS'2024]: DiffGS: Functional Gaussian Splatting Diffusion

[arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

[SIGGRAPH 2024] Motion I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Official inference repo for FLUX.1 models

This repo contains the code for 1D tokenizer and generator

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Open-Sora: Democratizing Efficient Video Production for All

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation [TMLR 2024]

[WIP] Layer Diffusion for WebUI (via Forge)

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Aligning LMMs with Factually Augmented RLHF

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

General technology for enabling AI capabilities w/ LLMs and MLLMs

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods…

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.