AI Paper Atlas

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

Long-Text-to-Image Generation via Compositional Prompt Decomposition

Jen-Yuan Huang, Tong Lin, Yilun Du

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 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 PRISM compositional decomposition to Qwen-ImageQwen-Image · DetailMasterCharacter Presence accuracy: 40.46 -> 46.84Improved
add PRISM to Qwen-ImageQwen-Image · DetailMaster long promptsHPSv3: 8.56 -> 12.05Improved
add PRISM decomposition vs fine-tuned LongAlign on prompts over 500 tokensPRISM-SD1.5 · DetailMaster prompts >500 tokensaccuracy: 7.4%Improved
combine PRISM with LongAlign reward tuningPRISM-SD1.5 · DetailMasterSpatial Relation accuracy: 20.88 -> 24.47Improved
increase number of components N from 3 to 5 (ablation)PRISM-SD1.5 · DetailMastergain over compute-matched fine-tuningImproved
add multiple components instead of a single component (non-compositional) (ablation)PRISM-SD1.5 · DetailMasteraccuracyImproved
learned decomposition instead of simple sentence splitting (ablation)PRISM-SD1.5 · DetailMasteraccuracyImproved
add PRISM LoRA adaptation to FLUX-Dev.FLUX-Dev. · DetailMaster (appendix)Character Presence accuracy: 34.33 -> 31.05Hurt
add PRISM LoRA adaptation to SD-3.5 MediumSD-3.5 Medium · DetailMaster (appendix)Character Presence accuracy: 31.19 -> 33.03Improved
add PRISM to SD-1.5 (vs LongAlign) on standard-length promptsPRISM-SD1.5 · GenEvalGenEval score: 0.5075 -> 0.4960No clear effect

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