Optimizing Prompts for Text-to-Image Generation
Open accessThe DOI matches its OpenAlex record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation, a general framework that automatically adapts original user input to model-preferred prompts. Specifically, we first perform supervised fine-tuning with a pretrained language model on a small collection of manually engineered prompts. Then we use reinforcement learning to explore better prompts. We define a reward function that encourages the policy to generate more aesthetically pleasing images while preserving the original user intentions. Experimental results on Stable Diffusion show that our method outperforms manual prompt engineering in terms of both automatic metrics and human preference ratings. Moreover, reinforcement learning further boosts performance, especially on out-of-domain prompts. The pretrained checkpoints are available at https://aka.ms/promptist. The demo can be found at https://aka.ms/promptist-demo.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., & Guo, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01043 · Cited by 720
Multimodal Few-Shot Learning with Frozen Language Models
Tsimpoukelli, M., Menick, J., Cabi, S., Eslami, S. M. A., Vinyals, O., & Hill, F. (2021) · arXiv · doi:10.48550/arxiv.2106.13884 · Cited by 355
Large Language Models Are Human-Level Prompt Engineers
Zhou, Y., Muresanu, A. I., Han, Z., Paster, K., Pitis, S., Chan, H., & Ba, J. (2022) · arXiv · doi:10.48550/arxiv.2211.01910 · Cited by 330
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Jaques, N., Ghandeharioun, A., Shen, J. H., Ferguson, C., Lapedriza, A., Jones, N., Gu, S., & Picard, R. (2019) · arXiv · doi:10.48550/arxiv.1907.00456 · Cited by 126
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2020) · arXiv · doi:10.48550/arxiv.2012.15723 · Cited by 124
Cited by
Automatic Prompt Optimization with “Gradient Descent” and Beam Search
Pryzant, R., Iter, D., Li, J., Lee, Y., Zhu, C., & Zeng, M. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.494 · Cited by 191
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Pryzant, R., Iter, D., Li, J., Lee, Y. T., Zhu, C., & Zeng, M. (2023) · arXiv · doi:10.48550/arxiv.2305.03495 · Cited by 191
PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation
Feng, Y., Wang, X., Wong, K. K., Wang, S., Lu, Y., Zhu, M., Wang, B., & Chen, W. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3327168 · Cited by 124
Liu, M., Zhang, L. J., & Zhang, D. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108569 · Cited by 43
Ai, Q., Zhan, J., & Liu, Y. (2025) · arXiv · doi:10.48550/arxiv.2501.02842
Metadata
- Authors
- Hao, Y., Chi, Z., Dong, L., & Wei, F.
- Venue
- neural information processing systems
- Published
- 2023-01-01
- Pages
- 66923-66939
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133208667
- Cited by
- 67
- References
- 6
- FWCI
- 7.62
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.