Saved in:
Bibliographic Details
Main Authors: Wu, Chen, De la Torre, Fernando
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.13490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929250536259584
author Wu, Chen
De la Torre, Fernando
author_facet Wu, Chen
De la Torre, Fernando
contents Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors. For instance, changing a single token in the text can have unintended effects on the image. This paper shows a simple modification of classifier-free guidance can help disentangle image factors in text-to-image models. The key idea of our method, Contrastive Guidance, is to characterize an intended factor with two prompts that differ in minimal tokens: the positive prompt describes the image to be synthesized, and the baseline prompt serves as a "baseline" that disentangles other factors. Contrastive Guidance is a general method we illustrate whose benefits in three scenarios: (1) to guide domain-specific diffusion models trained on an object class, (2) to gain continuous, rig-like controls for text-to-image generation, and (3) to improve the performance of zero-shot image editors.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13490
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Contrastive Prompts Improve Disentanglement in Text-to-Image Diffusion Models
Wu, Chen
De la Torre, Fernando
Computer Vision and Pattern Recognition
Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors. For instance, changing a single token in the text can have unintended effects on the image. This paper shows a simple modification of classifier-free guidance can help disentangle image factors in text-to-image models. The key idea of our method, Contrastive Guidance, is to characterize an intended factor with two prompts that differ in minimal tokens: the positive prompt describes the image to be synthesized, and the baseline prompt serves as a "baseline" that disentangles other factors. Contrastive Guidance is a general method we illustrate whose benefits in three scenarios: (1) to guide domain-specific diffusion models trained on an object class, (2) to gain continuous, rig-like controls for text-to-image generation, and (3) to improve the performance of zero-shot image editors.
title Contrastive Prompts Improve Disentanglement in Text-to-Image Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.13490