Research map / Image generation / Text-to-image diffusion
Make Me Happier: Evoking Emotions Through Image Diffusion Models
Qing Lin, Jingfeng Zhang, Yew-Soon Ong, Mengmi Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add iterative emotion inference (IEI) to text-conditioned variant (ablation) | EmoEditor (text input) · EmoSet cross-valence (CAM-based) | ESMI (%): 5.85 -> 50.24 | Improved |
| add iterative emotion inference (IEI) to e_oh variant with L_emb (ablation) | EmoEditor (e_oh input) · EmoSet cross-valence (CAM-based) | ESMI (%): 7.36 -> 49.80 | Improved |
| add iterative emotion inference (IEI) to e_dir variant with L_emb (ablation) | EmoEditor (e_dir input) · EmoSet cross-valence (CAM-based) | ESMI (%): 8.51 -> 51.56 | Improved |
| replace text input with one-hot target emotion e_oh (ablation) | EmoEditor · EmoSet cross-valence (CAM-based) | ESMI (%): 5.85 -> 7.36 | Improved |
| replace one-hot e_oh with emotion editing direction e_dir (no IEI) (ablation) | EmoEditor · EmoSet cross-valence (CAM-based) | ESMI (%): 7.36 -> 8.51 | Improved |
| replace one-hot e_oh with emotion editing direction e_dir (with IEI and L_emb) (ablation) | EmoEditor · EmoSet cross-valence (CAM-based) | ESMI (%): 49.80 -> 51.56 | Improved |
| add alignment loss L_emb to e_oh variant with IEI (ablation) | EmoEditor · EmoSet cross-valence (CAM-based) | ESMI (%): 47.36 -> 49.80 | Improved |
| compare EmoEditor with Ip2p baseline | EmoEditor vs Ip2p · EmoSet cross-valence (CAM-based) | ESMI (%): 27.37 -> 51.56 | Improved |
| compare EmoEditor with LMS chain of large models | EmoEditor vs LMS · EmoSet cross-valence (CAM-based) | ESMI (%): 35.40 -> 51.56 | Improved |
| compare EmoEditor with EmoEdit on HA-based ESMI | EmoEditor vs EmoEdit · EmoSet cross-valence (HA-based) | ESMI (%): 37.53 -> 49.99 | Improved |
| evaluate with separate emotion predictor (CrossTest) versus NST | EmoEditor vs NST · EmoSet CrossTest | ESMI (%): 45.35 vs 43.95 | Hurt |
| Ip2p instead of EmoEditor on structure score | Ip2p vs EmoEditor · EmoSet cross-valence (CAM-based) | S_str (%): 34.82 vs 33.22 | Mixed |
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.
- EmoEdit — EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025) · better on 5 of 5 shared results
- SDEdit — SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (ICLR 2022) · better on 3 of 3 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
- EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025 · similarity 0.90)
- EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention (CVPR 2025 · similarity 0.86)
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment (ICML 2026 · similarity 0.86)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.85)
- A Unified and Interpretable Emotion Representation and Expression Generation (CVPR 2024 · similarity 0.85)
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.
