AI Paper Atlas

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

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?

Qirui Jiao, Daoyuan Chen, Yilun Huang, Xika Lin, Ying Shen, Yaliang Li

ICML 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters

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
raise text-encoder token limit from 77 to 512 without long-prompt training (ablation)SD-XL · DetailMaster Character Locationsaccuracy (%): 9.39 -> 10.45Improved
add long-prompt training at a 77-token limit (ablation)SD-XL · DetailMaster Character Locationsaccuracy (%): 9.39 -> 10.93Improved
combine 512-token limit with long-prompt training (ablation)SD-XL · DetailMaster Character Locationsaccuracy (%): 9.39 -> 12.52Improved
combine 512-token limit with long-prompt training (ablation)SD-XL · DetailMaster Entity Relationshipsaccuracy (%): 8.43 -> 13.07Improved
long-prompt training at 77 limit on style attribute versus 512 limit short training (ablation)SD-XL · DetailMaster Scene Attributes (Style)accuracy (%): 66.22 -> 53.72Hurt
use T5 encoder (longer input) instead of CLIPDeepFloyd IF vs SD1.5/SD-XL · DetailMaster Character Locationsaccuracy (%): 10.95 -> 14.28Improved
add long-prompt training and 512 token limit (ParaDiffusion) versus conventional training at same capacityDeepFloyd IF · DetailMaster Character Locationsaccuracy (%): 14.28 -> 20.32Improved
add T5 adapter with only 128-token training limit (LLM4GEN)SD1.5 · DetailMaster Character Locationsaccuracy (%): 8.68 -> 9.22No clear effect
add iterative layout refinement (LLM Blueprint)SD1.5 · DetailMaster Character Locationsaccuracy (%): 8.68 -> 18.44Improved
optimise SD1.5 for long promptsSD1.5 · DetailMaster Scene Attributes (Style)accuracy (%): 80.90 -> 50.11Hurt
increase prompt length10 evaluated T2I models · DetailMasteraccuracyHurt

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