#diffusion-models Repositories
473 repositories total
A summary of related works about flow matching, stochastic interpolants
Official inference code for BluePixel, a native 4K image editing model with 4-step distilled inference, built on FLUX.2 Klein and DCAE.
Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.
[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"
[NeurlPS2024] One-Step Effective Diffusion Network for Real-World Image Super-Resolution
[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generationโ
Open diffusion language model for code generation โ releasing pretraining, evaluation, inference, and checkpoints.
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
[IJCV 2026] FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds.
[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Flash Diffusion โ accelerating conditional diffusion models (AAAI 2025 Oral)
Implementation of โDreamDiffusion: Generating High-Quality Images from Brain EEG Signalsโ
PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model
Chinese translation of 'Machine Learning: A Probabilistic Perspective' (Kevin P. Murphy) and Python implementations of the algorithms in the book.
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
A watermarking tool to protect human artworks from being used in synthetic artworks.
This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"
Refine and improve the quality of small faces in MiniMax H3 videos. Track faces frame by frame, crop them, refine them with H3, and stitch them back in.
[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
[CVPR'26] ObjectClear: Precise Object and Effect Removal with Adaptive Target-Aware Attention
VisionโLanguageโAction models for Autonomous Driving (VLA4AD) resources, serving as the companion repository to the survey paper โA Survey on VisionโLanguageโAction Models for Autonomous Drivingโ.
Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]
[ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering""
[ICCV 2025] Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement ๐ฅ
Minimal implementation of scalable rectified flow transformers, based on SD3's approach
Official implementation of "FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on"
[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"
[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model