AI Paper Atlas

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

EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model

Shengqi Dang, Yi He, Long Ling, Ziqing Qian, Nanxuan Zhao, Nan Cao

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 20 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 V-A density weighting d(v,a) to the loss (ablation)EmotiCrafter · Density weighting ablationV-Error: 1.546 -> 1.510Improved
add V-A density weighting d(v,a) to the loss (ablation)EmotiCrafter · Density weighting ablationCLIPScore: 21.977 -> 23.067Improved
add V-A density weighting d(v,a) to the loss (ablation)EmotiCrafter · Density weighting ablationA-Error: 1.829 -> 1.828No clear effect
increase residual scale factor alpha (ablation)EmotiCrafter · Emotional image generationV/A-ErrorImproved
increase residual scale factor alpha (ablation)EmotiCrafter · Emotional image generationCLIPScoreHurt
rewrite prompts with emotion features via learned mapping network instead of GPT-4EmotiCrafter vs GPT-4+SDXL · ContinuityLPIPS-Continuous: 0.361 -> 0.220Improved
use emotion-embedding network instead of GPT-4 rewritingEmotiCrafter vs GPT-4+SDXL · User study IV-Error: 1.229 -> 0.692Improved
use emotion-embedding network instead of GPT-4 rewritingEmotiCrafter vs GPT-4+SDXL · User study IIEmotion Smoothness: 3.195 -> 4.240Improved
embed V-A into prompt features instead of injecting into SDXL UNet (cross-attention)EmotiCrafter vs Cross Attention · Emotional image generationA-Error: 1.923 -> 1.828Improved
embed V-A into prompt features instead of injecting into UNetEmotiCrafter vs Cross Attention/Time Embedding · Emotional image generationCLIPScore: 26.566 -> 23.067Hurt

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