2000 character limit reached
Inventing art styles with no artistic training data (2305.12015v2)
Published 19 May 2023 in cs.CV and cs.AI
Abstract: We propose two procedures to create painting styles using models trained only on natural images, providing objective proof that the model is not plagiarizing human art styles. In the first procedure we use the inductive bias from the artistic medium to achieve creative expression. Abstraction is achieved by using a reconstruction loss. The second procedure uses an additional natural image as inspiration to create a new style. These two procedures make it possible to invent new painting styles with no artistic training data. We believe that our approach can help pave the way for the ethical employment of generative AI in art, without infringing upon the originality of human creators.
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation, August 2013. arXiv:1308.3432 [cs].
- Matthew Butterick. Stable Diffusion litigation · Joseph Saveri Law Firm & Matthew Butterick. https://stablediffusionlitigation.com/ on May 16, 2023.
- Extracting Training Data from Diffusion Models, January 2023. arXiv:2301.13188 [cs].
- Learning to generate line drawings that convey geometry and semantics. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7905–7915, New Orleans, LA, USA, June 2022. IEEE.
- Kyle Chayka. Is A.I. Art Stealing from Artists? The New Yorker, February 2023. Section: infinite scroll.
- Anisotropic Stroke Control for Multiple Artists Style Transfer. In Proceedings of the 28th ACM International Conference on Multimedia, pages 3246–3255, October 2020. arXiv:2010.08175 [cs].
- Benj Edwards. Have AI image generators assimilated your art? New tool lets you check, September 2022.
- Image style transfer using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2414–2423, 2016.
- E.H. Gombrich. The Preference for the Primitive: Episodes in the History of Western Taste and Art. Phaidon Press, 2002.
- Ernst Gombrich. Art and Illusion. December 2000.
- Generative adversarial nets. pages 2672–2680, 2014.
- Paul Haeberli. Paint by numbers: abstract image representations. ACM SIGGRAPH Computer Graphics, 24(4):207–214, September 1990.
- Denoising diffusion probabilistic models. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 6840–6851. Curran Associates, Inc., 2020.
- Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res., 23(47):1–33, 2022.
- Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
- Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples, February 2023. arXiv:2302.04578 [cs].
- Controlling strokes in fast neural style transfer using content transforms. The Visual Computer, 38(12):4019–4033, December 2022.
- Variational inference with normalizing flows. arXiv preprint arXiv:1505.05770, 2015.
- GLAZE: Protecting Artists from Style Mimicry by Text-to-Image Models, April 2023. arXiv:2302.04222 [cs].
- Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2020.
- Neural discrete representation learning. Advances in neural information processing systems, 30, 2017.
- Artists file class-action lawsuit saying AI artwork violates copyright laws. NPR, February 2023.
- Understanding straight-through estimator in training activation quantized neural nets. 2019.
- Vector-quantized image modeling with improved vqgan. arXiv preprint arXiv:2110.04627, 2021.
- Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017.