Git Stars Git Stars

#diffusion-transformer Repositories

Discover 32 active open source GitHub repositories tagged with #diffusion-transformer, accumulating 82,342 total stars (averaging 2,573 stars per project). Leading this topic is SWivid/F5-TTS with 15,634 stars.

32
Total Repositories
82,342
Total Stars
2,573
Avg Stars/Repo
Programming Languages: Python Jupyter Notebook
1
SWivid/F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

SWivid
โญ 15,634 Python ๐Ÿ‘ค SWivid User ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2024-10-08
2
Tencent-Hunyuan/HunyuanVideo

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Tencent-Hunyuan
โญ 12,817 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-10-08 ๐Ÿ“… Created 2024-11-28
โญ 12,176 Python ๐Ÿ‘ค Tongyi-MAI Organization ๐Ÿ• Updated 2026-02-09 ๐Ÿ“… Created 2025-11-26
4
Tencent-Hunyuan/HunyuanDiT

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Tencent-Hunyuan
โญ 4,292 Jupyter Notebook ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-10-08 ๐Ÿ“… Created 2024-05-10
5
PixArt-alpha/PixArt-alpha

PixArt-ฮฑ: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

PixArt-alpha
โญ 3,250 Python ๐Ÿ‘ค PixArt-alpha Organization ๐Ÿ• Updated 2024-10-31 ๐Ÿ“… Created 2023-10-12
6
bytedance/InfiniteYou

๐Ÿ”ฅ [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

bytedance
โญ 2,684 Python ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2025-08-22 ๐Ÿ“… Created 2025-02-14
7
Tencent-Hunyuan/HY-Motion-1.0

HY-Motion model for 3D human motion or 3D character animation generation.

Tencent-Hunyuan
โญ 2,679 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-11-13 ๐Ÿ“… Created 2025-12-29
โญ 2,509 Python ๐Ÿ‘ค HiDream-ai Organization ๐Ÿ• Updated 2025-07-16 ๐Ÿ“… Created 2025-04-06
9
Alpha-VLLM/Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation

Alpha-VLLM
โญ 2,251 Python ๐Ÿ‘ค Alpha-VLLM Organization ๐Ÿ• Updated 2025-02-16 ๐Ÿ“… Created 2024-03-28
10
River-Zhang/ICEdit

[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!

River-Zhang
โญ 2,095 Python ๐Ÿ‘ค River-Zhang User ๐Ÿ• Updated 2025-12-19 ๐Ÿ“… Created 2025-04-29
11
PixArt-alpha/PixArt-sigma

PixArt-ฮฃ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

PixArt-alpha
โญ 1,884 Python ๐Ÿ‘ค PixArt-alpha Organization ๐Ÿ• Updated 2024-10-31 ๐Ÿ“… Created 2024-02-29
12
Xiaojiu-z/EasyControl

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)

Xiaojiu-z
โญ 1,732 Python ๐Ÿ‘ค Xiaojiu-z User ๐Ÿ• Updated 2025-07-25 ๐Ÿ“… Created 2025-03-06
13
Fantasy-AMAP/fantasy-talking

[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

Fantasy-AMAP
โญ 1,629 Python ๐Ÿ‘ค Fantasy-AMAP Organization ๐Ÿ• Updated 2026-01-26 ๐Ÿ“… Created 2025-04-02
14
ByteDance-Seed/SeedVR

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

ByteDance-Seed
โญ 1,459 Python ๐Ÿ‘ค ByteDance-Seed Organization ๐Ÿ• Updated 2026-01-27 ๐Ÿ“… Created 2025-06-10
โญ 1,366 Python ๐Ÿ‘ค ali-vilab Organization ๐Ÿ• Updated 2025-04-21 ๐Ÿ“… Created 2025-01-03
16
bytedance/UNO

[ICCV 2025] ๐Ÿ”ฅ๐Ÿ”ฅ UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

bytedance
โญ 1,362 Python ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2025-09-12 ๐Ÿ“… Created 2025-04-01
17
shallowdream204/DreamClear

[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

shallowdream204
โญ 1,191 Python ๐Ÿ‘ค shallowdream204 User ๐Ÿ• Updated 2025-03-21 ๐Ÿ“… Created 2024-10-24
18
IceClear/SeedVR2

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

IceClear
โญ 940 ๐Ÿ‘ค IceClear User ๐Ÿ• Updated 2026-01-27 ๐Ÿ“… Created 2025-06-05
โญ 923 Python ๐Ÿ‘ค wileewang User ๐Ÿ• Updated 2025-05-14 ๐Ÿ“… Created 2024-12-24
20
NVlabs
โญ 899 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2026-01-23 ๐Ÿ“… Created 2025-12-16
โญ 899 Python ๐Ÿ‘ค megvii-research Organization ๐Ÿ• Updated 2024-12-11 ๐Ÿ“… Created 2024-05-21
22
Junchao-cs/SolarWM

Open data and scalable training for long-horizon video world models.

Junchao-cs
โญ 857 Python ๐Ÿ‘ค Junchao-cs User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-08-21
23
thu-ml/DiT-Extrapolation

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025), UltraViCo (ICLR 2026) and UltraImage

thu-ml
โญ 834 Python ๐Ÿ‘ค thu-ml Organization ๐Ÿ• Updated 2026-06-06 ๐Ÿ“… Created 2025-02-21
24
TTPlanetPig/Comfyui_Object_Migration

This is a study aim to transfer the single concept by using DIT model self-attention capablity

TTPlanetPig
โญ 786 Python ๐Ÿ‘ค TTPlanetPig User ๐Ÿ• Updated 2024-11-20 ๐Ÿ“… Created 2024-11-15
25
bytedance/DreamID-V

[ECCV 2026 Oral] DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

bytedance
โญ 707 Python ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2026-05-22 ๐Ÿ“… Created 2025-12-17
26
yousef-rafat/miniDiffusion

A reimplementation of Stable Diffusion 3.5 in pure PyTorch

yousef-rafat
โญ 705 Python ๐Ÿ‘ค yousef-rafat User ๐Ÿ• Updated 2025-06-14 ๐Ÿ“… Created 2025-03-07
27
Tencent-Hunyuan/HunyuanImage-2.1

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generationโ€‹

Tencent-Hunyuan
โญ 674 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2025-10-14 ๐Ÿ“… Created 2025-09-04
28
ivcylc/OpenMusic

OpenMusic: SOTA Text-to-music (TTM) Generation

ivcylc
โญ 633 Python ๐Ÿ‘ค ivcylc User ๐Ÿ• Updated 2025-06-26 ๐Ÿ“… Created 2024-05-24
29
lucasnewman/f5-tts-mlx

Implementation of F5-TTS in MLX

lucasnewman
โญ 632 Python ๐Ÿ‘ค lucasnewman User ๐Ÿ• Updated 2025-03-19 ๐Ÿ“… Created 2024-10-13
30
wangjiangshan0725/RF-Solver-Edit

[๐Ÿš€ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

wangjiangshan0725
โญ 630 Python ๐Ÿ‘ค wangjiangshan0725 User ๐Ÿ• Updated 2025-05-01 ๐Ÿ“… Created 2024-11-05
31
damo-cv/RealisDance

The official implementation of RealisDance

damo-cv
โญ 611 Python ๐Ÿ‘ค damo-cv Organization ๐Ÿ• Updated 2025-06-20 ๐Ÿ“… Created 2024-09-10
32
thu-ml/SLA

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparseโ€“Linear Attention

thu-ml
โญ 553 Python ๐Ÿ‘ค thu-ml Organization ๐Ÿ• Updated 2026-10-18 ๐Ÿ“… Created 2025-09-25

Frequently Asked Questions

1

What is the most popular #diffusion-transformer repository on GitHub?

The top ranked open source #diffusion-transformer project on GitHub is SWivid/F5-TTS with 15,634 stars. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

2

Which programming languages are most used in #diffusion-transformer repositories?

Among the top ranked #diffusion-transformer projects on GitHub, the most common programming languages are Python, Jupyter Notebook.

3

How is the #diffusion-transformer repository ranking calculated?

We track 32 active open source repositories tagged with #diffusion-transformer (500+ stars), totaling 82,342 stars with an average of 2,573 stars per repository. Rankings update daily from the GitHub API.