PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

🔥 Official impl. of "DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing".

L2P: Unlocking Latent Potential for Pixel Generation

[CVPR 2026 Highlight] Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers

[CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

Q-Insight Family: Q-Insight, VQ-Insight and RALI (NeurIPS 2025 Spotlight, AAAI 2026 Oral, and ICLR 2026 Oral)

Official repository for “PixelGen: Improving Pixel Diffusion with Perceptual Loss”

[ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

[ICLR 2026] Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Implementaion of paper "Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution"

Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

🎁 7,400,000+ Unsplash images made available for research and machine learning

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

Official Repo for Self-Forcing++ High Quality Long Video Generation

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Official repository for LTX-Video

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space

🔥🔥🔥[AAAI 2026] Official code release of our paper "Fine-grained Image Quality Assessment for Perceptual Image Restoration". 首个面向图像恢复的细粒度IQA数据集FGRestore+方法FGResQ

Open-source SOTA multi-image editing model

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

The official repository of our ICLR 2026 paper "Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration".

[ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization