AI Paper Atlas

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

CAP: Evaluation of Persuasive and Creative Image Generation

Aysan Aghazadeh, Adriana Kovashka

ICCV 2025 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 5 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
fine-tune LLM with CPO for AIM (ablation)AIM metric · human agreement, all adsKrippendorff alpha: 0.18 -> 0.68Improved
add component-based scoring instead of direct LLM scoring (ablation)persuasiveness metric · human agreement, all adsKrippendorff alpha: 0.27 -> 0.65Improved
add AIM alignment term to Pcomp (ablation)persuasiveness metric · human agreement, all adsKrippendorff alpha: 0.65 -> 0.80Improved
set reason weight alpha to 4 or 5 instead of 1 (ablation)AIM metric · human agreement subsetKrippendorff alpha: 0.51 -> 0.68Improved
use C_obj instead of LLM creativity scoringcreativity metric · human agreement, all adsKrippendorff alpha: 0.04 -> 0.54Improved
expand message with LLAMA3 before T2I (I_LLAMA3 vs I_AR)AuraFlow · PSA adsAIM: 0.31 -> 0.43Improved
expand message with LLAMA3 before T2IAuraFlow · PSA adsC_obj: 1.36 -> 1.87Improved
expand message with LLAMA3 before T2IAuraFlow · PSA adsP_comp+AIM: 0.42 -> 0.60Improved
expand message with LLM before T2IT2I models · commercial and PSA adsAIM, creativity, persuasiveness: 6%, 7%, 10% commercial; 39%, 38%, 43% PSAImproved
use QwenLM instead of LLAMA3 for message expansionAuraFlow · PSA adsC_obj: 1.87 -> 2.05Improved
add expansion with LLAMA3AuraFlow · commercial adsAIM: 0.50 -> 0.53Improved
swap MLLM or evaluation LLM (InternVL vs QwenVL, LLAMA3 vs QwenLM) (ablation)AIM metric · human agreement, all adsKrippendorff alpha: 0.68 -> 0.65No clear effect

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