Art-Free Generative Models: Art Creation Without Graphic Art Knowledge
Abstract
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.
Community
We explore the question: "How much prior art knowledge is needed to create art?". To find out, we designed a text-to-image generation model that skips training on art-related content entirely. Then, we developed a straightforward method to create an "art adapter," which learns artistic styles using just a handful of examples. Our experiments reveal that the art generated this way is rated by users as on par with pieces from models trained on massive, art-heavy 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.
Project website: https://joaanna.github.io/art-free-diffusion/
Our Art-Free Diffusion Model is here: https://huggingface.co/rhfeiyang/art-free-diffusion-v1
Our Art-Free SAM dataset is here: https://huggingface.co/datasets/rhfeiyang/Art-Free-SAM
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching (2024)
- Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model (2024)
- ArtBrain: An Explainable end-to-end Toolkit for Classification and Attribution of AI-Generated Art and Style (2024)
- Bridging Text and Image for Artist Style Transfer via Contrastive Learning (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend