Git Stars Git Stars

#diffusion-models Repositories

473
Total Repositories
1.1M
Total Stars
2,361
Avg Stars/Repo
401
mit-han-lab/radial-attention

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

mit-han-lab
โญ 609 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2025-11-11 ๐Ÿ“… Created 2025-06-19
402
damian0815/compel

A prompting enhancement library for transformers-type text embedding systems

damian0815
โญ 608 Jupyter Notebook ๐Ÿ‘ค damian0815 User ๐Ÿ• Updated 2026-10-10 ๐Ÿ“… Created 2023-01-17
403
AI-Guru/music-generation-research

A straightforward collection of Music Generation research resources.

AI-Guru
โญ 605 ๐Ÿ‘ค AI-Guru User ๐Ÿ• Updated 2025-01-20 ๐Ÿ“… Created 2021-06-02
404
NUS-HPC-AI-Lab/Enhance-A-Video

Enhance-A-Video: Better Generated Video for Free

NUS-HPC-AI-Lab
โญ 595 Python ๐Ÿ‘ค NUS-HPC-AI-Lab Organization ๐Ÿ• Updated 2025-03-17 ๐Ÿ“… Created 2024-12-18
405
sail-sg/MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

sail-sg
โญ 591 Python ๐Ÿ‘ค sail-sg Organization ๐Ÿ• Updated 2024-04-23 ๐Ÿ“… Created 2023-03-17
406
alex4727/MotionStream

MotionStream: Real-Time Video Generation with Interactive Motion Controls

alex4727
โญ 590 ๐Ÿ‘ค alex4727 User ๐Ÿ• Updated 2026-03-01 ๐Ÿ“… Created 2025-10-09
407
TencentARC/BrushEdit

[TPAMI] The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"

TencentARC
โญ 590 Python ๐Ÿ‘ค TencentARC Organization ๐Ÿ• Updated 2025-09-03 ๐Ÿ“… Created 2024-12-16
408
omnichar/OmniChar

The open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.

omnichar
โญ 589 Python ๐Ÿ‘ค omnichar Organization ๐Ÿ• Updated 2026-10-29 ๐Ÿ“… Created 2026-06-11
409
zibojia/MiniMax-Remover

This is the official implementation of our paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"

zibojia
โญ 589 Python ๐Ÿ‘ค zibojia User ๐Ÿ• Updated 2025-07-27 ๐Ÿ“… Created 2025-05-26
410
ironjr/semantic-draw

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

ironjr
โญ 589 Jupyter Notebook ๐Ÿ‘ค ironjr User ๐Ÿ• Updated 2025-06-01 ๐Ÿ“… Created 2024-02-15
411
lumalabs/imm

Official implementation of Inductive Moment Matching

lumalabs
โญ 585 Python ๐Ÿ‘ค lumalabs Organization ๐Ÿ• Updated 2025-07-11 ๐Ÿ“… Created 2025-03-11
412
nachifur/RDDM

CVPR 2024: Residual Denoising Diffusion Models

nachifur
โญ 585 Python ๐Ÿ‘ค nachifur User ๐Ÿ• Updated 2026-06-09 ๐Ÿ“… Created 2023-08-25
413
zyxElsa/InST

Official implementation of the paper โ€œInversion-Based Style Transfer with Diffusion Modelsโ€ (CVPR 2023)

zyxElsa
โญ 585 Jupyter Notebook ๐Ÿ‘ค zyxElsa User ๐Ÿ• Updated 2024-06-18 ๐Ÿ“… Created 2022-11-23
414
Seed3D/Dora

[CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

Seed3D
โญ 584 Python ๐Ÿ‘ค Seed3D Organization ๐Ÿ• Updated 2025-07-02 ๐Ÿ“… Created 2024-12-23
415
Doby-Xu/WithAnyone

โœจ [ICLR'26] WithAnyone is capable of generating high-quality, controllable, and ID consistent images

Doby-Xu
โญ 583 Python ๐Ÿ‘ค Doby-Xu User ๐Ÿ• Updated 2026-09-29 ๐Ÿ“… Created 2025-10-14
416
LaurentMazare/diffusers-rs

An implementation of the diffusers api in Rust

LaurentMazare
โญ 582 Rust ๐Ÿ‘ค LaurentMazare User ๐Ÿ• Updated 2024-04-04 ๐Ÿ“… Created 2022-11-05
โญ 576 Jupyter Notebook ๐Ÿ‘ค LambdaLabsML Organization ๐Ÿ• Updated 2024-10-18 ๐Ÿ“… Created 2022-09-12
418
ant-research/AniDoc

[CVPR'25] Official Implementations for Paper - AniDoc: Animation Creation Made Easier

ant-research
โญ 575 Python ๐Ÿ‘ค ant-research Organization ๐Ÿ• Updated 2025-04-15 ๐Ÿ“… Created 2024-12-18
419
kuleshov-group/awesome-discrete-diffusion-models

A curated list for awesome discrete diffusion models resources.

kuleshov-group
โญ 575 ๐Ÿ‘ค kuleshov-group Organization ๐Ÿ• Updated 2025-09-09 ๐Ÿ“… Created 2023-03-10
420
dailenson/One-DM

Official Code for ECCV 2024 paper โ€” One-Shot Diffusion Mimicker for Handwritten Text Generation

dailenson
โญ 573 Python ๐Ÿ‘ค dailenson User ๐Ÿ• Updated 2025-10-15 ๐Ÿ“… Created 2024-07-15
421
Human3DAIGC/Make-A-Character

Official repo for Make-A-Character: High Quality Text-to-3D Character Generation within Minutes

Human3DAIGC
โญ 573 ๐Ÿ‘ค Human3DAIGC User ๐Ÿ• Updated 2025-04-27 ๐Ÿ“… Created 2023-12-24
422
kijai/ComfyUI-Marigold

Marigold depth estimation in ComfyUI

kijai
โญ 572 Python ๐Ÿ‘ค kijai User ๐Ÿ• Updated 2025-05-16 ๐Ÿ“… Created 2023-12-12
423
muzishen/IMAGHarmony

๐Ÿงฉ IMAGHarmony ๐Ÿงฉ: Controllable image editing with consistent object quantity and layout. A structure-aware framework that ensures high fidelity and coherence in complex multi-object edits. It integrates harmony-aware attention and preference-guided noise selection to enable precise, stable, and semantically aligned generation.

muzishen
โญ 571 Python ๐Ÿ‘ค muzishen User ๐Ÿ• Updated 2026-03-24 ๐Ÿ“… Created 2024-11-17
โญ 570 Python ๐Ÿ‘ค erwold User ๐Ÿ• Updated 2024-11-26 ๐Ÿ“… Created 2024-11-25
425
mazzzystar/disco-diffusion-wrapper

Implementation of disco-diffusion wrapper that could run on your own GPU with batch text input.

mazzzystar
โญ 570 Jupyter Notebook ๐Ÿ‘ค mazzzystar User ๐Ÿ• Updated 2024-03-02 ๐Ÿ“… Created 2022-05-03
426
microsoft/foldingdiff

Diffusion models of protein structure; trigonometry and attention are all you need!

microsoft
โญ 568 Jupyter Notebook ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2022-06-30
427
Vchitect/VEnhancer

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Vchitect
โญ 564 Python ๐Ÿ‘ค Vchitect Organization ๐Ÿ• Updated 2024-09-16 ๐Ÿ“… Created 2024-07-10
428
lukemelas/realfusion

Official code for "RealFusion: 360ยฐ Reconstruction of Any Object from a Single Image" (CVPR 2023)

lukemelas
โญ 564 Python ๐Ÿ‘ค lukemelas User ๐Ÿ• Updated 2024-06-02 ๐Ÿ“… Created 2023-02-06
429
Tangshitao/MVDiffusion

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)

Tangshitao
โญ 561 Python ๐Ÿ‘ค Tangshitao User ๐Ÿ• Updated 2024-01-06 ๐Ÿ“… Created 2023-06-27
430
alibaba-yuanjing-aigclab/ViViD

ViViD: Video Virtual Try-on using Diffusion Models

alibaba-yuanjing-aigclab
โญ 557 Python ๐Ÿ‘ค alibaba-yuanjing-aigclab Organization ๐Ÿ• Updated 2024-06-21 ๐Ÿ“… Created 2024-05-20
431
WHU-USI3DV/VistaDream

[ICCV 2025 & TPAMI] VistaDream: Sampling Multiview-Consistent Images for Single-View Scene Reconstruction

WHU-USI3DV
โญ 555 Python ๐Ÿ‘ค WHU-USI3DV Organization ๐Ÿ• Updated 2026-10-22 ๐Ÿ“… Created 2024-10-21
432
MrForExample/ComfyUI-AnimateAnyone-Evolved

Improved AnimateAnyone implementation that allows you to use the opse image sequence and reference image to generate stylized video

MrForExample
โญ 555 Python ๐Ÿ‘ค MrForExample User ๐Ÿ• Updated 2024-06-14 ๐Ÿ“… Created 2024-01-18
433
dome272/Wuerstchen

Official implementation of Wรผrstchen: Efficient Pretraining of Text-to-Image Models

dome272
โญ 555 Jupyter Notebook ๐Ÿ‘ค dome272 User ๐Ÿ• Updated 2024-04-06 ๐Ÿ“… Created 2023-05-24
434
Jeff-LiangF/streamv2v

Official Pytorch implementation of StreamV2V.

Jeff-LiangF
โญ 552 Python ๐Ÿ‘ค Jeff-LiangF User ๐Ÿ• Updated 2025-12-29 ๐Ÿ“… Created 2024-05-25
435
ant-research/DepthLab

Official implementation of "DepthLab: From Partial to Complete"

ant-research
โญ 550 Python ๐Ÿ‘ค ant-research Organization ๐Ÿ• Updated 2025-02-14 ๐Ÿ“… Created 2024-12-19
436
ali-vilab/Infusion

Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

ali-vilab
โญ 549 Python ๐Ÿ‘ค ali-vilab Organization ๐Ÿ• Updated 2024-07-15 ๐Ÿ“… Created 2024-04-17
437
liming-ai/ControlNet_Plus_Plus

[ECCV 2024] ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.

liming-ai
โญ 547 Python ๐Ÿ‘ค liming-ai User ๐Ÿ• Updated 2025-01-12 ๐Ÿ“… Created 2024-04-11
438
cvignac/DiGress

code for the paper "DiGress: Discrete Denoising diffusion for graph generation"

cvignac
โญ 547 Python ๐Ÿ‘ค cvignac User ๐Ÿ• Updated 2026-09-10 ๐Ÿ“… Created 2022-09-27
439
dllm-labs/mojo-dllm

Local inference for diffusion language models (LLaDA, Dream), written in Mojo

dllm-labs
โญ 546 Python ๐Ÿ‘ค dllm-labs Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-10-04
440
CUHK-AIM-Group/U-KAN

[AAAI' 25] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

CUHK-AIM-Group
โญ 545 Python ๐Ÿ‘ค CUHK-AIM-Group Organization ๐Ÿ• Updated 2025-06-23 ๐Ÿ“… Created 2024-06-04
โญ 538 Python ๐Ÿ‘ค playht Organization ๐Ÿ• Updated 2026-06-11 ๐Ÿ“… Created 2025-05-22
442
Visionary-Laboratory/visionary

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

Visionary-Laboratory
โญ 537 Python ๐Ÿ‘ค Visionary-Laboratory Organization ๐Ÿ• Updated 2026-10-15 ๐Ÿ“… Created 2025-12-07
443
Xiaojiu-z/Stable-Hair

Pytorch Implementation of: "Stable-Hair: Real-World Hair Transfer via Diffusion Model" (AAAI 2025)

Xiaojiu-z
โญ 533 Python ๐Ÿ‘ค Xiaojiu-z User ๐Ÿ• Updated 2025-03-14 ๐Ÿ“… Created 2024-07-16
444
wyf0912/SinSR

[CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step

wyf0912
โญ 533 Python ๐Ÿ‘ค wyf0912 User ๐Ÿ• Updated 2024-09-12 ๐Ÿ“… Created 2023-11-23
445
magic-research/piecewise-rectified-flow

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)

magic-research
โญ 532 Jupyter Notebook ๐Ÿ‘ค magic-research Organization ๐Ÿ• Updated 2025-09-08 ๐Ÿ“… Created 2024-02-16
446
Stanford-TML/EDGE

Official PyTorch Implementation of EDGE (CVPR 2023)

Stanford-TML
โญ 530 Python ๐Ÿ‘ค Stanford-TML Organization ๐Ÿ• Updated 2024-01-05 ๐Ÿ“… Created 2023-03-28
447
priorMDM/priorMDM

The official implementation of the paper "Human Motion Diffusion as a Generative Prior"

priorMDM
โญ 530 Python ๐Ÿ‘ค priorMDM User ๐Ÿ• Updated 2026-04-21 ๐Ÿ“… Created 2023-03-01
448
modelscope/ms-cookbook

ModelScope Purple Book | ModelScope Cookbook: A hands-on guide to open-source model applications for developers, covering model selection, inference, fine-tuning, evaluation, RAG, agents, and AIGCโ€”from running your first model to building real-world applications.

modelscope
โญ 529 HTML ๐Ÿ‘ค modelscope Organization ๐Ÿ• Updated 2026-11-04 ๐Ÿ“… Created 2026-09-11
449
nv-tlabs/SCube

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

nv-tlabs
โญ 529 Python ๐Ÿ‘ค nv-tlabs Organization ๐Ÿ• Updated 2025-10-14 ๐Ÿ“… Created 2024-10-25
450
instantX-research/InstantIR

InstantIR: Blind Image Restoration with Instant Generative Reference ๐Ÿ”ฅ

instantX-research
โญ 527 Python ๐Ÿ‘ค instantX-research Organization ๐Ÿ• Updated 2024-11-14 ๐Ÿ“… Created 2024-10-20