Summary of Automated Black-box Prompt Engineering For Personalized Text-to-image Generation, by Yutong He et al.
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
by Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Nathaniel Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter
First submitted to arxiv on: 28 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces an algorithm called PRISM that automatically generates human-interpretable and transferable prompts for text-to-image generative models. The goal is to overcome the limitations of existing prompt engineering methods, which are laborious and often require white-box access to the underlying model. PRISM leverages in-context learning from large language models to refine a candidate prompt distribution given reference images. This approach allows for black-box access to multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PRISM is an algorithm that helps text-to-image generators produce better pictures when you tell them what to create. Right now, people have to make up their own instructions for these programs, but it’s hard work. PRISM makes it easier by using a special kind of learning from large language models. It looks at examples and figures out how to ask the right questions to get the desired results. This means you can use PRISM with different image-making tools without needing to know all the technical details. |
Keywords
* Artificial intelligence * Diffusion * Prompt
