AI Paper Atlas

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

SIMPLEPOSTER: A SIMPLE BASELINE FOR PRODUCT POSTER GENERATION

Benlei Cui, Fangao Zeng, Weitao Jiang, Yuwen Zhai, Haiwen Hong, Longtao Huang, Hui Xue, Wenxiang Shang, Pipei Huang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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 character position encoding (ablation)SimplePoster · SimplePoster benchmarkSen.ACC: 24.94% -> 71.33%Improved
add character position encoding (ablation)SimplePoster · SimplePoster benchmarkNED: 0.5484 -> 0.8062Improved
add character position encoding (ablation)FLUX.1-dev LoRA · multilingual multi-lineSen. Acc: 0.0461 -> 0.2571Improved
add character position encoding (ablation)FLUX.1-dev LoRA · multilingual single-lineNED: 0.6326 -> 0.6765Improved
add ControlNet with frozen backboneFLUX-Fill · subject extension ratesubject extension rate: 41% -> 23.6%Improved
LoRA tuning instead of ControlNet (ablation)FLUX-Fill · subject extension ratesubject extension rate: 23.6% -> 2.8%Improved
full-parameter tuning instead of LoRA (ablation)FLUX-Fill · subject extension ratesubject extension rate: 2.8% -> 0.6%Improved
train 3K images for 300 epochs instead of 3 epochs (ablation)FLUX-Fill full tuning · subject extension ratesubject extension rate: 17.3% -> 3.6%Improved
train 3K images for 10 epochs instead of 3 epochs (ablation)FLUX-Fill full tuning · subject extension ratesubject extension rate: 17.3% -> 9.3%Improved
scale data from 3K to 300K images (ablation)FLUX-Fill full tuning · subject extension ratesubject extension rate: 3.6% -> 0.6%Improved
SimplePoster vs PosterMaker subject preservationSimplePoster · SimplePoster benchmarksubject preservation rate: 85.3% -> 98.7%Improved
SimplePoster vs Gemini2.5Flash prompt followingSimplePoster · SimplePoster benchmarkprompt following: 3.82 -> 3.55Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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