
REPA
by sihyun-yu (personal account)
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (description from the project’s GitHub page)
Repository facts
- Stars
- 1,727
- Forks
- 100
- Open issues and pull requests
- 10
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- sihyun-yu · Personal account
- Created
- Oct 7, 2024
- Last push
- Mar 16, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 1,548: transformerlab/transformerlab-app
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
5,196 starsPythonAGPL-3.0Last push Oct 14, 2026
Rank 3,340: Alpha-VLLM/Lumina-T2X
Lumina-T2X is a unified framework for Text to Any Modality Generation
2,248 starsPythonMITLast push Feb 16, 2025
Rank 3,381: PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
2,212 starsPythonApache-2.0Last push Aug 24, 2026
Rank 3,525: 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…
2,098 starsPythonOther licenseLast push Dec 19, 2025
Rank 3,702: FoundationVision/LlamaGen
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
1,973 starsPythonMITLast push Aug 15, 2024
Rank 4,082: TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"
1,745 starsPythonOther licenseLast push Dec 17, 2024