ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jia, Chengyou, Xia, Changliang, Dang, Zhuohang, Wu, Weijia, Qian, Hangwei, Luo, Minnan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910716308488192
author Jia, Chengyou
Xia, Changliang
Dang, Zhuohang
Wu, Weijia
Qian, Hangwei
Luo, Minnan
author_facet Jia, Chengyou
Xia, Changliang
Dang, Zhuohang
Wu, Weijia
Qian, Hangwei
Luo, Minnan
contents Despite the significant advancements in text-to-image (T2I) generative models, users often face a trial-and-error challenge in practical scenarios. This challenge arises from the complexity and uncertainty of tedious steps such as crafting suitable prompts, selecting appropriate models, and configuring specific arguments, making users resort to labor-intensive attempts for desired images. This paper proposes Automatic T2I generation, which aims to automate these tedious steps, allowing users to simply describe their needs in a freestyle chatting way. To systematically study this problem, we first introduce ChatGenBench, a novel benchmark designed for Automatic T2I. It features high-quality paired data with diverse freestyle inputs, enabling comprehensive evaluation of automatic T2I models across all steps. Additionally, recognizing Automatic T2I as a complex multi-step reasoning task, we propose ChatGen-Evo, a multi-stage evolution strategy that progressively equips models with essential automation skills. Through extensive evaluation across step-wise accuracy and image quality, ChatGen-Evo significantly enhances performance over various baselines. Our evaluation also uncovers valuable insights for advancing automatic T2I. All our data, code, and models will be available in \url{https://chengyou-jia.github.io/ChatGen-Home}
format Preprint
id arxiv_https___arxiv_org_abs_2411_17176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
Jia, Chengyou
Xia, Changliang
Dang, Zhuohang
Wu, Weijia
Qian, Hangwei
Luo, Minnan
Computer Vision and Pattern Recognition
Artificial Intelligence
Despite the significant advancements in text-to-image (T2I) generative models, users often face a trial-and-error challenge in practical scenarios. This challenge arises from the complexity and uncertainty of tedious steps such as crafting suitable prompts, selecting appropriate models, and configuring specific arguments, making users resort to labor-intensive attempts for desired images. This paper proposes Automatic T2I generation, which aims to automate these tedious steps, allowing users to simply describe their needs in a freestyle chatting way. To systematically study this problem, we first introduce ChatGenBench, a novel benchmark designed for Automatic T2I. It features high-quality paired data with diverse freestyle inputs, enabling comprehensive evaluation of automatic T2I models across all steps. Additionally, recognizing Automatic T2I as a complex multi-step reasoning task, we propose ChatGen-Evo, a multi-stage evolution strategy that progressively equips models with essential automation skills. Through extensive evaluation across step-wise accuracy and image quality, ChatGen-Evo significantly enhances performance over various baselines. Our evaluation also uncovers valuable insights for advancing automatic T2I. All our data, code, and models will be available in \url{https://chengyou-jia.github.io/ChatGen-Home}
title ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.17176