Research map / Image generation / Text-to-image diffusion
Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models
Seunghwan Choi, Jooyeol Yun, Youngdo Lee, Jaegul Choo
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 residual embedding to the distilled embedding (ablation) | Ours · attribute concept dataset (SD3) | concept similarity and exclusiveness | Improved |
| add distilled and residual embeddings on top of custom training prompt (ablation) | Textual Inversion with custom prompt · attribute concept dataset (SD3) | concept similarity and exclusiveness | Improved |
| use VLM-written custom training prompt describing non-target attributes | Textual Inversion · attribute concept dataset (SD3) | concept exclusiveness | Improved |
| compare against TokenVerse, ProSpect | Ours · attribute concept dataset (SD3) | concept exclusiveness | Mixed |
Closest papers by meaning
- DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models (CVPR 2025 · similarity 0.87)
- Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation (CVPR 2025 · similarity 0.86)
- FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models (NeurIPS 2024 · similarity 0.86)
- Text-to-Image Generation for Abstract Concepts (AAAI 2024 · similarity 0.86)
- Localizing and Editing Knowledge In Text-to-Image Generative Models (ICLR 2024 · similarity 0.85)
- Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions (CVPR 2025 · 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.
