[NeurIPS'25 Spotlight] Official repository for "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment"

Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View, 3DV2025

UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, and inpainting.

[ACM MM 2025] HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

[CVPR 2025 Highlight] VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

Official PyTorch implementation of "SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation"

[CVPR 2024] On the Content Bias in Fréchet Video Distance

[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Scalable and memory-optimized training of diffusion models

[ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

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

[arXiv 2024] Novel View Extrapolation with Video Diffusion Priors

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

[ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

[ICCV 2025] Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer

official repo of paper for "CamI2V: Camera-Controlled Image-to-Video Diffusion Model"

The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

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

Official codebase for "Score-based Diffusion Models in Function Space"

Official repository for "Regularization by Texts for Latent Diffusion Inverse Solvers" (ICLR2025 spotlight)

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

[ICCV'25] Official implementation of "Reangle-A-Video: 4D Video Generation as Video-to-Video Translation"

[ICCV2025] Official repository of "FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems"