Skip to content
NewA calmer, faster ZeroHour

Structured Residual Connectivity Matters for Diffusion Transformers

Hugging Face daily papersby Yuhe Liu, Xinyin Ma, Gongfan Fang ()1 min read
AI summary · grok-4.7Summaries by Vani AI

Structured residual paths in diffusion transformers cut FID and training iterations with almost no extra parameters.

The paper redesigns residual connections in Diffusion Transformers so each block can selectively retrieve earlier spatial and semantic features instead of summing a single residual stream. The structured local and long-range paths add under 0.1% parameters and cut training iterations by up to 1.73×. Applied to REPA-XL/2, FID falls from 5.9 to 4.34 without guidance and reaches 1.39 with classifier-free guidance.

Key facts
  • DiTs use a uniform residual stream unlike U-Net skip connections.
  • Structured local and long-range paths let blocks retrieve earlier features.
  • Training needs up to 1.73× fewer iterations with under 0.1% extra parameters.
  • REPA-XL/2 improves from 5.9 to 4.34 FID, and 1.39 FID with guidance.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Diffusion Transformers (DiTs) have established themselves as a scalable backbone for high-fidelity image synthesis. However, unlike U-Net based diffusion models that rely on rigid, hand-crafted skip connections, DiTs predominantly use a uniform residual stream that integrates all preceding layers as a monolithic state.

Hugging Face daily papers

By Yuhe Liu, Xinyin Ma, Gongfan Fang · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.