Research map / Image generation / Text-to-image diffusion
Dense Text-to-Image Generation with Attention Modulation
Yunji Kim, Jiyoung Lee, Jin-Hwa Kim, Jung-Woo Ha, Jun-Yan Zhu
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 attention modulation at cross-attention layers (ablation) | DenseDiffusion · MS-COCO dense captions | IoU: 18.35 -> 34.99 | Improved |
| add attention modulation at self-attention layers (ablation) | DenseDiffusion · MS-COCO dense captions | IoU: 29.57 -> 34.99 | Improved |
| add value-range adaptive modulation (ablation) | DenseDiffusion · MS-COCO dense captions | SOA-I: 76.51 -> 77.61 | Improved |
| add mask-area adaptive modulation (ablation) | DenseDiffusion · MS-COCO dense captions | SOA-I: SOA-I 73.62 -> 77.61; IoU 38.00 -> 34.99 | Mixed |
| apply DenseDiffusion attention modulation to Stable Diffusion | Stable Diffusion · MS-COCO dense captions | SOA-I: 73.08 -> 77.61 | Improved |
| run separate denoising per phrase (Composable Diffusion) instead of standard inference | Stable Diffusion · MS-COCO dense captions | SOA-I: 73.08 -> 55.88 | Hurt |
| use layout-aware modulation vs SD-Pww on layout fidelity | DenseDiffusion · MS-COCO dense captions | IoU: 23.76 -> 34.99 | Improved |
| add structure-diffusion parsing of phrases | Stable Diffusion · MS-COCO dense captions | SOA-I: 73.08 -> 70.97 | No clear effect |
Closest papers by meaning
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.90)
- Grounded Text-to-Image Synthesis with Attention Refocusing (CVPR 2024 · similarity 0.90)
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts (ICLR 2024 · similarity 0.89)
- Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model (AAAI 2024 · similarity 0.89)
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.88)
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.
