Research map / Image generation / Text-to-image diffusion
RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
Liyao Jiang, Ruichen Chen, Chao Gao, Di Niu
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 RAISE refinement | FLUX.1-dev · GenEval | Overall: 0.67 -> 0.94 | Improved |
| add RAISE refinement | FLUX.1-dev · DrawBench | VQAScore: 0.778 -> 0.885 | Improved |
| add RAISE refinement | FLUX.1-schnell · GenEval | Overall: 0.66 -> 0.93 | Improved |
| add RAISE refinement | SANA-1.5 4.8B · GenEval | Overall: 0.72 -> 0.93 | Improved |
| add a second refinement round (ablation) | RAISE · GenEval | Overall: 0.89 -> 0.92 | Improved |
| allow up to 3 rounds (ablation) | RAISE · GenEval | Overall: 0.92 -> 0.93 | Improved |
| allow up to 4 rounds (ablation) | RAISE · GenEval | Overall: 0.93 -> 0.94 | Improved |
| add vision tool grounding (ablation) | RAISE · GenEval | Overall: 0.93 -> 0.94 | Improved |
| add vision tool grounding (ablation) | RAISE · GenEval | Attribute Binding: 0.84 -> 0.87 | Improved |
| add instructional editing (ablation) | RAISE · GenEval | Attribute Binding: 0.83 -> 0.87 | Improved |
| add instructional editing (ablation) | RAISE · GenEval | Overall: 0.93 -> 0.94 | Improved |
| add RAISE vs ReflectionFlow samples | RAISE · GenEval | Avg. samples generated: 18.6 vs. 32 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Reflect-DiT — Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection (ICCV 2025) · better on 1 of 1 shared result
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
- Improving Long-Text Alignment for Text-to-Image Diffusion Models (ICLR 2025 · similarity 0.90)
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.90)
- PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought (CVPR 2024 · similarity 0.90)
- Discriminative Probing and Tuning for Text-to-Image Generation (CVPR 2024 · similarity 0.90)
- Information Theoretic Text-to-Image Alignment (ICLR 2025 · similarity 0.90)
- DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models (NeurIPS 2026 · similarity 0.90)
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.
