無藝術生成模型：無需圖形藝術知識的藝術創作

Art-Free Generative Models: Art Creation Without Graphic Art Knowledge

November 29, 2024

作者: Hui Ren, Joanna Materzynska, Rohit Gandikota, David Bau, Antonio Torralba

cs.AI

摘要

我們探討一個問題：“創作藝術所需的先前藝術知識量為何？”為了研究這個問題，我們提出了一個文本到圖像生成模型，該模型在沒有訪問與藝術相關的內容的情況下進行訓練。然後，我們引入了一種簡單而有效的方法，僅使用少量選定藝術風格的示例來學習一個藝術適配器。我們的實驗表明，使用我們的方法生成的藝術被用戶認為與在大型、藝術豐富數據集上訓練的模型生成的藝術相媲美。最後，通過數據歸因技術，我們說明了來自藝術和非藝術數據集的示例如何促成了新藝術風格的創作。

English

We explore the question: "How much prior art knowledge is needed to create art?" To investigate this, we propose a text-to-image generation model trained without access to art-related content. We then introduce a simple yet effective method to learn an art adapter using only a few examples of selected artistic styles. Our experiments show that art generated using our method is perceived by users as comparable to art produced by models trained on large, art-rich datasets. Finally, through data attribution techniques, we illustrate how examples from both artistic and non-artistic datasets contributed to the creation of new artistic styles.