Saved in:
Bibliographic Details
Main Authors: Yu, Chang, Peng, Junran, Zhu, Xiangyu, Zhang, Zhaoxiang, Tian, Qi, Lei, Zhen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.06345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929207565615104
author Yu, Chang
Peng, Junran
Zhu, Xiangyu
Zhang, Zhaoxiang
Tian, Qi
Lei, Zhen
author_facet Yu, Chang
Peng, Junran
Zhu, Xiangyu
Zhang, Zhaoxiang
Tian, Qi
Lei, Zhen
contents The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain multiple objects or spatial relationships. To get the desired images, a feasible way is to manually adjust the textual descriptions, i.e., narrating the texts or adding some words, which is labor-consuming. In this paper, we propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. By utilizing the quality guidance and the semantic guidance derived from the pre-trained diffusion model, our method can effectively learn the prompts to improve the matches between the input text and the generated images. Extensive experiments and analyses have validated the effectiveness of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering
Yu, Chang
Peng, Junran
Zhu, Xiangyu
Zhang, Zhaoxiang
Tian, Qi
Lei, Zhen
Computer Vision and Pattern Recognition
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain multiple objects or spatial relationships. To get the desired images, a feasible way is to manually adjust the textual descriptions, i.e., narrating the texts or adding some words, which is labor-consuming. In this paper, we propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. By utilizing the quality guidance and the semantic guidance derived from the pre-trained diffusion model, our method can effectively learn the prompts to improve the matches between the input text and the generated images. Extensive experiments and analyses have validated the effectiveness of the proposed method.
title Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.06345