Artificial intelligence art
Artificial intelligence art refers to any artwork created through the use of artificial intelligence.
Tools and processes
There are many mechanisms for creating AI art, including procedural 'rule-based' generation of images using mathematical patterns, algorithms which simulate brush strokes and other painted effects, and artificial intelligence or deep learning algorithms such as generative adversarial networks and transformers.
One of the first significant AI art systems is AARON, developed by Harold Cohen beginning in the late 1960s.[1] AARON is the most notable example of AI art in the era of GOFAI programming because of its use of a symbolic rule-based approach to generate technical images.[2] Cohen developed AARON with the goal of being able to code the act of drawing. In its primitive form, AARON created simple black and white drawings. Cohen would later finish the drawings by painting them. Throughout the years, he also began to develop a way for AARON to also paint. Cohen designed AARON to paint using special brushes and dyes that were chosen by the program itself without mediation from Cohen.[3]
Since their design in 2014, generative adversarial networks (GANs) are often used by AI artists. This system uses a "generator" to create new images and a "discriminator" to decide which created images are considered successful.[4] More recent models use Vector Quantized Generative Adversarial Network and Contrastive Language–Image Pre-training (VQGAN+CLIP).[5]
DeepDream, released by Google in 2015, uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dream-like psychedelic appearance in the deliberately over-processed images.[6][7][8]
Several programs made by large companies use AI to generate a variety of images based on various text prompts. They include OpenAI's DALL-E which released a series of images in January 2021, [9] Google Brain's Imagen and Parti which was announced in May 2022 and Microsofts' NUWA-Infinity.[10][11][12]
There are many other AI art generation programs including simple consumer-facing mobile apps and Jupyter notebooks that require powerful GPUs to run effectively. Examples include Midjourney, StyleGAN, and Stable Diffusion, among many others.[13]
Outpainting
Outpainting, introduced by OpenAI Dall-E,[14] is the process of extrapolating an image beyond its boundaries. The outpainting process keeps the theme of the image as well as the style.
Sales
An auction sale of artificial intelligence art was held at Christie's Auction House in New York in 2018, where the AI artwork Edmond de Belamy sold for $432,500, which was almost 45 times higher than its estimate of $7,000–$10,000. The artwork was created by "Obvious", a Paris-based collective.[15][16][17][18]
See also
References
- ^ McCorduck, Pamela (1991). AARONS's Code: Meta-Art. Artificial Intelligence, and the Work of Harold Cohen. New York: W. H. Freeman and Company. p. 210. ISBN 0-7167-2173-2.
- ^ Poltronieri, Fabrizio Augusto; Hänska, Max (2019-10-23). "Technical Images and Visual Art in the Era of Artificial Intelligence: From GOFAI to GANs". Proceedings of the 9th International Conference on Digital and Interactive Arts. Braga Portugal: ACM: 1–8. doi:10.1145/3359852.3359865. ISBN 978-1-4503-7250-3.
- ^ "Fine art print - crypto art". Kate Vass Galerie. Retrieved 2022-05-07.
- ^ Goodfellow, Ian; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua (2014). Generative Adversarial Nets (PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680.
- ^ Burgess, Phillip. "Generating AI "Art" with VQGAN+CLIP". Adafruit. Retrieved July 20, 2022.
- ^ Mordvintsev, Alexander; Olah, Christopher; Tyka, Mike (2015). "DeepDream - a code example for visualizing Neural Networks". Google Research. Archived from the original on 2015-07-08.
- ^ Mordvintsev, Alexander; Olah, Christopher; Tyka, Mike (2015). "Inceptionism: Going Deeper into Neural Networks". Google Research. Archived from the original on 2015-07-03.
- ^ Szegedy, Christian; Liu, Wei; Jia, Yangqing; Sermanet, Pierre; Reed, Scott E.; Anguelov, Dragomir; Erhan, Dumitru; Vanhoucke, Vincent; Rabinovich, Andrew (2015). "Going deeper with convolutions". IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7–12, 2015. IEEE Computer Society. pp. 1–9. arXiv:1409.4842. doi:10.1109/CVPR.2015.7298594.
- ^ "Here's DALL-E: An algorithm learned to draw anything you tell it". NBC News. 2021-01-27. Retrieved 2021-01-23.
- ^ "NUWA-Infinity". nuwa-infinity.microsoft.com. Retrieved 2022-08-10.
- ^ Vincent, James (May 24, 2022). "All these images were generated by Google's latest text-to-image AI". The Verge. Vox Media. Retrieved May 28, 2022.
- ^ Khan, Imad. "Google's Parti Generator Relies on 20 Billion Inputs to Create Photorealistic Images". CNET. Retrieved 23 June 2022.
- ^ Psychotic, Pharma. "Tools and Resources for AI Art". Archived from the original on 2022-06-04. Retrieved 2022-06-26.
- ^ Vincent, James (2022-09-05). "DALL-E can now help you imagine what's outside the frame of famous paintings". The Verge. Retrieved 2022-09-07.
- ^ "Is artificial intelligence set to become art's next medium?". Christie's. 2018-12-12. Retrieved 2019-05-21.
- ^ "Portrait by AI program sells for $432,000". BBC News. 2018-10-25. Retrieved 2019-05-21.
- ^ Cohn, Gabe (2018-10-25). "AI Art at Christie's Sells for $432,500". New York Times. Retrieved 2019-05-21.
- ^ Cohn, Gabe (2018-10-22). "Up for Bid, AI Art Signed 'Algorithm'". New York Times. Retrieved 2019-05-21.