Inventing art styles with no artistic training data
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 13 of its 24 references that are in the map. First posted on arXiv 19 May 2023.
Builds on
13 of 24 references.
References · 13
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2017Neural Discrete Representation Learningcited by 4,650
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
- 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
- 2023Extracting Training Data from Diffusion Modelscited by 723
- 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
- 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
- 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200
- 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 163
- 2022Learning to generate line drawings that convey geometry and semanticscited by 82
1 more
Built on by
Citing papers per year: 2024: 2.
2 papers.