sihyun-yu/REPA
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligns noisy diffusion states with frozen pretrained visual encoder representations (DINOv2, CLIP, MAE, etc.) to accelerate Diffusion Transformer training by 17.5x while achieving FID=1.42 on ImageNet. Supports multiple encoder architectures and scales to 512×512 resolution and text-to-image generation via configurable projection depth and alignment coefficients. Built on SiT/DiT frameworks with accelerate-based distributed training and automatic checkpoint management.
1,582 stars. No commits in the last 6 months.
Stars
1,582
Forks
81
Language
Python
License
MIT
Category
Last pushed
Mar 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sihyun-yu/REPA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...