Research map / Image generation / Text-to-image diffusion
Affective Image Editing: Shaping Emotional Factors via Text Descriptions
Peixuan Zhang, Shuchen Weng, Chengxuan Zhu, Binghao Tang, Zijian Jia, Si Li, Boxin Shi
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 emotional spectrum building (ablation) | AIEdiT · EmoTIPS editing | KLD: 2.6160 -> 2.4373 | Improved |
| add emotional spectrum building (ablation) | AIEdiT · EmoTIPS editing | FID: 29.67 -> 27.93 | Improved |
| add multi-head cross-attention blocks in emotional mapper (ablation) | AIEdiT · EmoTIPS editing | KLD: 2.4894 -> 2.4373 | Improved |
| add multi-head cross-attention blocks in emotional mapper (ablation) | AIEdiT · EmoTIPS editing | FID: 28.98 -> 27.93 | Improved |
| add key semantic extraction (linear layer scaling) (ablation) | AIEdiT · EmoTIPS editing | Sem-C: 0.657 -> 0.685 | Improved |
| add key semantic extraction (linear layer scaling) (ablation) | AIEdiT · EmoTIPS editing | KLD: 2.5139 -> 2.4373 | Improved |
| add MLLM-supervised sentiment alignment loss (ablation) | AIEdiT · EmoTIPS editing | FID: 31.03 -> 27.93 | Improved |
| add MLLM-supervised sentiment alignment loss (ablation) | AIEdiT · EmoTIPS editing | Sem-C: 0.651 -> 0.685 | Improved |
| increase noise-adding step t from 25 to 49 (ablation) | AIEdiT · EmoTIPS editing | FID: 20.40 -> 32.37 | Hurt |
| increase noise-adding step t from 25 to 49 (ablation) | AIEdiT · EmoTIPS editing | KLD: 2.4805 -> 2.4301 | Improved |
| use t=37 instead of 25 or 49 (ablation) | AIEdiT · EmoTIPS editing | user preference (%): 27.96 -> 45.32 | Improved |
| AIEdiT vs best baseline EmoEdit on user preference | AIEdiT · EmoTIPS editing | user preference (%): 22.44 -> 39.68 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- EmoEdit — EmoEdit: Evoking Emotions through Image Manipulation (CVPR 2025) · better on 4 of 4 shared results
- ControlNet — ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback (ECCV 2024) · better on 3 of 3 shared results
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · 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 0.86)
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.86)
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment (ICML 2026 · similarity 0.85)
- The Good, The Bad, and Why: Unveiling Emotions in Generative AI (ICML 2024 · similarity 0.85)
- EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning (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.
