Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Song, Yiren, Huang, Shijie, Yao, Chen, Ye, Xiaojun, Ci, Hai, Liu, Jiaming, Zhang, Yuxuan, Shou, Mike Zheng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.06062
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911963239415808
author Song, Yiren
Huang, Shijie
Yao, Chen
Ye, Xiaojun
Ci, Hai
Liu, Jiaming
Zhang, Yuxuan
Shou, Mike Zheng
author_facet Song, Yiren
Huang, Shijie
Yao, Chen
Ye, Xiaojun
Ci, Hai
Liu, Jiaming
Zhang, Yuxuan
Shou, Mike Zheng
contents The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essential for art education and research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences of brushstrokes, yet they fall short of replicating the authentic processes of artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion processes generate images through iterative denoising, also diverge substantially from artists' painting process. To address these challenges, we introduce ProcessPainter, a text-to-video model that is initially pre-trained on synthetic data and subsequently fine-tuned with a select set of artists' painting sequences using the LoRA model. This approach successfully generates painting processes from text prompts for the first time. Furthermore, we introduce an Artwork Replication Network capable of accepting arbitrary-frame input, which facilitates the controlled generation of painting processes, decomposing images into painting sequences, and completing semi-finished artworks. This paper offers new perspectives and tools for advancing art education and image generation technology.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06062
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ProcessPainter: Learn Painting Process from Sequence Data
Song, Yiren
Huang, Shijie
Yao, Chen
Ye, Xiaojun
Ci, Hai
Liu, Jiaming
Zhang, Yuxuan
Shou, Mike Zheng
Computer Vision and Pattern Recognition
Artificial Intelligence
The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essential for art education and research, yet remains largely underexplored. Traditional stroke-based rendering methods break down images into sequences of brushstrokes, yet they fall short of replicating the authentic processes of artists, with limitations confined to basic brushstroke modifications. Text-to-image models utilizing diffusion processes generate images through iterative denoising, also diverge substantially from artists' painting process. To address these challenges, we introduce ProcessPainter, a text-to-video model that is initially pre-trained on synthetic data and subsequently fine-tuned with a select set of artists' painting sequences using the LoRA model. This approach successfully generates painting processes from text prompts for the first time. Furthermore, we introduce an Artwork Replication Network capable of accepting arbitrary-frame input, which facilitates the controlled generation of painting processes, decomposing images into painting sequences, and completing semi-finished artworks. This paper offers new perspectives and tools for advancing art education and image generation technology.
title ProcessPainter: Learn Painting Process from Sequence Data
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.06062