| Autor: |
Ren, Hui, Materzynska, Joanna, Gandikota, Rohit, Bau, David, Torralba, Antonio |
| Rok vydání: |
2024 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
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. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
