Research map / Image generation / Text-to-image diffusion
Improving image synthesis with diffusion-negative sampling
Alakh Desai, Nuno Vasconcelos
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 diffusion-negative prompt via automatic captioning | Stable Diffusion · A&E dataset | CLIP Score (Min. Object): 0.242 -> 0.258 | Improved |
| add diffusion-negative prompt via automatic captioning | Stable Diffusion · A&E dataset | human preference correctness: 18.90% -> 64.22% | Improved |
| add diffusion-negative prompt to Attend & Excite | Attend & Excite · A&E dataset | Inception Score: 11.86 -> 13.12 | Improved |
| add diffusion-negative prompt to Attend & Excite | Attend & Excite · A&E dataset | CLIP Score (Min. Object): 0.264 -> 0.276 | Improved |
| add diffusion-negative prompt via automatic captioning | Stable Diffusion · H&H Hand prompts | CLIP Score: 0.309 -> 0.321 | Improved |
| add diffusion-negative prompt via automatic captioning | Stable Diffusion · H&H Human prompts | Inception Score: 9.95 -> 10.13 | Improved |
| replace human captioning of diffusion-negative image with BLIP2 automatic captioning (ablation) | DNP · A&E human-eval subset | CLIP Score (Min. Object): 0.253 -> 0.250 | No clear effect |
Closest papers by meaning
- Dynamic Negative Guidance of Diffusion Models (ICLR 2025 · similarity 0.89)
- Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.88)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.88)
- On Discrete Prompt Optimization for Diffusion Models (ICML 2024 · similarity 0.88)
- Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis (NeurIPS 2024 · 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.
