4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator

TensorRT and ONNX version of LEDNet for low light enhancement

Wan: Open and Advanced Large-Scale Video Generative Models

Dynamic 3D Foundation Model using Causal Transformer. [ICLR 2026]

Reference PyTorch implementation and models for DINOv3

[ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Official SeedVR2 Video Upscaler for ComfyUI

Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

[CVPR'26] ObjectClear: Precise Object and Effect Removal with Adaptive Target-Aware Attention

[SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."

[CVPR2025 Highlight] SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration

A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and power…

[CVPR 2025] 3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement

[ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization

Author's Implementation for E-LatentLPIPS

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

Concept Sliders for Precise Control of Diffusion Models

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

Official inference repo for FLUX.1 models

BokehMe: When Neural Rendering Meets Classical Rendering (CVPR 2022 Oral)

Official Repo For Pixel-LLM Codebase

Arbitrary-steps Image Super-resolution via Diffusion Inversion (CVPR 2025)