Hugging Face's logo
Papers
arxiv:2211.15462

Investigating Prompt Engineering in Diffusion Models

Published on Nov 21, 2022
Upvote
-
Authors:
Sam Witteveen ,
Martin Andrews

Abstract

Techniques are introduced to evaluate the impact of specific words and phrases on the output of Text2Img diffusion models like DALL-E 2, Imagen, Mid Journey, and Stable Diffusion, aiding artists in prompt selection.

AI-generated summary

With the spread of the use of Text2Img diffusion models such as DALL-E 2, Imagen, Mid Journey and Stable Diffusion, one challenge that artists face is selecting the right prompts to achieve the desired artistic output. We present techniques for measuring the effect that specific words and phrases in prompts have, and (in the Appendix) present guidance on the selection of prompts to produce desired effects.

View arXiv page View PDF Add to collection

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2211.15462
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2211.15462 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2211.15462 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2211.15462 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.