Stylebreeder：透過文本到圖像模型探索和民主化藝術風格

Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models

June 20, 2024

作者: Matthew Zheng, Enis Simsar, Hidir Yesiltepe, Federico Tombari, Joel Simon, Pinar Yanardag

cs.AI

摘要

文字轉圖像模型正變得越來越受歡迎，通過實現高度詳細和具有創造性的視覺內容生成，徹底改變了數字藝術創作的格局。這些模型已被廣泛應用於各個領域，特別是在藝術生成方面，它們促進了廣泛的創意表達，並實現了對藝術創作的民主化訪問。在本文中，我們介紹了STYLEBREEDER，這是一個由95K用戶在Artbreeder上生成的680萬圖像和180萬提示的全面數據集。Artbreeder是一個擁有超過1300萬用戶的重要創意探索中心。我們通過這個數據集引入了一系列任務，旨在識別多樣的藝術風格，生成個性化內容，並基於用戶興趣推薦風格。通過記錄超越傳統類別如「赛博朋克」或「畢卡索」的獨特用戶生成風格，我們探索了獨特的、眾包風格可能提供對全球用戶集體創造心理的深刻洞察。我們還評估了不同的個性化方法以增強藝術表達，並引入了一個風格地圖集，將這些模型以LoRA格式提供給公眾使用。我們的研究展示了文字轉圖像擴散模型發掘和促進獨特藝術表達的潛力，進一步民主化AI在藝術中的應用，並促進更多元化和包容性的藝術社群。該數據集、代碼和模型可在https://stylebreeder.github.io 下載，並採用公共領域（CC0）許可。

English

Text-to-image models are becoming increasingly popular, revolutionizing the landscape of digital art creation by enabling highly detailed and creative visual content generation. These models have been widely employed across various domains, particularly in art generation, where they facilitate a broad spectrum of creative expression and democratize access to artistic creation. In this paper, we introduce STYLEBREEDER, a comprehensive dataset of 6.8M images and 1.8M prompts generated by 95K users on Artbreeder, a platform that has emerged as a significant hub for creative exploration with over 13M users. We introduce a series of tasks with this dataset aimed at identifying diverse artistic styles, generating personalized content, and recommending styles based on user interests. By documenting unique, user-generated styles that transcend conventional categories like 'cyberpunk' or 'Picasso,' we explore the potential for unique, crowd-sourced styles that could provide deep insights into the collective creative psyche of users worldwide. We also evaluate different personalization methods to enhance artistic expression and introduce a style atlas, making these models available in LoRA format for public use. Our research demonstrates the potential of text-to-image diffusion models to uncover and promote unique artistic expressions, further democratizing AI in art and fostering a more diverse and inclusive artistic community. The dataset, code and models are available at https://stylebreeder.github.io under a Public Domain (CC0) license.