#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 repositories total
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
PixArt-ฮฑ: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
๐ฅ [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
HY-Motion model for 3D human motion or 3D character animation generation.
[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!
PixArt-ฮฃ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)
[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
[ICCV 2025] ๐ฅ๐ฅ UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning
[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025), UltraViCo (ICLR 2026) and UltraImage
This is a study aim to transfer the single concept by using DIT model self-attention capablity
[ECCV 2026 Oral] DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generationโ
[๐ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable SparseโLinear Attention
Frequently Asked Questions
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"
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.
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.