Counting Guidance for High Fidelity Text-to-Image Synthesis

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kang, Wonjun, Galim, Kevin, Koo, Hyung Il, Cho, Nam Ik
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929741670383616
author Kang, Wonjun
Galim, Kevin
Koo, Hyung Il
Cho, Nam Ik
author_facet Kang, Wonjun
Galim, Kevin
Koo, Hyung Il
Cho, Nam Ik
contents Recently, there have been significant improvements in the quality and performance of text-to-image generation, largely due to the impressive results attained by diffusion models. However, text-to-image diffusion models sometimes struggle to create high-fidelity content for the given input prompt. One specific issue is their difficulty in generating the precise number of objects specified in the text prompt. For example, when provided with the prompt "five apples and ten lemons on a table," images generated by diffusion models often contain an incorrect number of objects. In this paper, we present a method to improve diffusion models so that they accurately produce the correct object count based on the input prompt. We adopt a counting network that performs reference-less class-agnostic counting for any given image. We calculate the gradients of the counting network and refine the predicted noise for each step. To address the presence of multiple types of objects in the prompt, we utilize novel attention map guidance to obtain high-quality masks for each object. Finally, we guide the denoising process using the calculated gradients for each object. Through extensive experiments and evaluation, we demonstrate that the proposed method significantly enhances the fidelity of diffusion models with respect to object count. Code is available at https://github.com/furiosa-ai/counting-guidance.
format Preprint
id arxiv_https___arxiv_org_abs_2306_17567
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Counting Guidance for High Fidelity Text-to-Image Synthesis
Kang, Wonjun
Galim, Kevin
Koo, Hyung Il
Cho, Nam Ik
Computer Vision and Pattern Recognition
Recently, there have been significant improvements in the quality and performance of text-to-image generation, largely due to the impressive results attained by diffusion models. However, text-to-image diffusion models sometimes struggle to create high-fidelity content for the given input prompt. One specific issue is their difficulty in generating the precise number of objects specified in the text prompt. For example, when provided with the prompt "five apples and ten lemons on a table," images generated by diffusion models often contain an incorrect number of objects. In this paper, we present a method to improve diffusion models so that they accurately produce the correct object count based on the input prompt. We adopt a counting network that performs reference-less class-agnostic counting for any given image. We calculate the gradients of the counting network and refine the predicted noise for each step. To address the presence of multiple types of objects in the prompt, we utilize novel attention map guidance to obtain high-quality masks for each object. Finally, we guide the denoising process using the calculated gradients for each object. Through extensive experiments and evaluation, we demonstrate that the proposed method significantly enhances the fidelity of diffusion models with respect to object count. Code is available at https://github.com/furiosa-ai/counting-guidance.
title Counting Guidance for High Fidelity Text-to-Image Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.17567