AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models

Yu Xue, Haoxuan Qu, ZHUOLING Li, Hongbin Xu, Jianxiong Yin, Simon See, Hossein Rahmani, Jun Liu

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SPA (bundle and slide) (ablation)HRDiT on FLUX · 4K generationFID: 75.85 -> 64.91Improved
add HAP attention pruning (ablation)HRDiT on FLUX · 4K generationlatency (s): 212 -> 116Improved
add HAP attention pruning (ablation)HRDiT on FLUX · 4K generationFID: 64.82 -> 64.91No clear effect
add slide operation to bundle (ablation)SPA · 4K generation FLUXFID: 69.43 -> 64.91Improved
use SPA instead of downscaling token indices (ablation)HRDiT on FLUX · 4K generationFID: 74.87 -> 64.91Improved
use head-adaptive scopes instead of fixed local window (ablation)HAP · 4K generation FLUXFID: 69.47 -> 64.91Improved
use head-adaptive scopes instead of random windows (ablation)HAP · 4K generation FLUXFID: 73.45 -> 64.91Improved
estimate scope quality with final-image loss instead of intermediate-feature loss (ablation)HAP · 4K generation FLUXFID: 68.02 -> 64.91Improved
raise attention cost ratio r_c from 0.01 to 0.1 (ablation)HAP · 4K generation FLUXFID: 94.51 -> 64.91Improved
raise attention cost ratio r_c from 0.1 to 0.5 (ablation)HAP · 4K generation FLUXlatency (s): 116 -> 155Hurt
increase candidate scopes N_scope from 10 to 50 (ablation)HAP · 4K generation FLUXFID: 66.03 -> 64.91Improved
increase bundle size N from 3 to 5 (ablation)SPA · 4K generation FLUXFID: 65.87 -> 64.91Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy