cs.CVNov 2, 2026

Flat Features, Detailed Images? Simple Detail Control for Diffusion Transformers

Authors: Qingtao Yu, Zhen Wang, Jiyang Zheng, Minghao Sun, Hongdong Li, Dylan Campbell

Organizations: The Australian National University · Microsoft · The University of Queensland

Abstract

Prompt engineering is commonly used to encourage text-to-image models to generate more detailed images. However, it does not provide reliable, continuous, or disentangled control. We analyze feature tokens produced with and without detail-enhancing prompts across six diffusion transformers and observe a common pattern: these prompts tend to increase the entropy of each token's energy distribution while largely preserving its ordering. That is, flattening the distribution increases the level of detail. Motivated by this counter-intuitive finding, we introduce a simple training-free approach that continuously adjusts the level of detail according to a scalar. Specifically, it shifts the squared channel magnitudes of each token toward a higher entropy distribution with a time-aware scheduler to concentrate the intervention at intermediate sampling steps. Across extensive experiments on different types of diffusion transformers, we show that our approach provides continuous control over detail metrics while largely preserving image quality and semantic structure. It requires only a few lines of code and adds negligible inference time overhead.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow

    Sep 9, 2026Junran Wang, Zehao Jin, Tianyu Luan +3Diffusion TransformerT2I Generation

  2. Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

    Oct 29, 2026Jiongfan Yang, Weichen Fan, Haiwen Diao +2Efficient ViTsTokenization

  3. AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers

    Oct 12, 2026Javad Rajabi, Koorosh Roohi, David B. Lindell +1Diffusion TransformerDiffusion-Based Image Generation