 | This is the sandbox page where you will draft your initial Wikipedia contribution.
If you're starting a new article, you can develop it here until it's ready to go live. If you're working on improvements to an existing article, copy only one section at a time of the article to this sandbox to work on, and be sure to use an edit summary linking to the article you copied from. Do not copy over the entire article. You can find additional instructions here. Remember to save your work regularly using the "Publish page" button. (It just means 'save'; it will still be in the sandbox.) You can add bold formatting to your additions to differentiate them from existing content. |
Digital painting edit
Digital painting[1] mainly refers to the process of creating paintings on computer software based on computers or graphic tables. Through pixel simulation, digital brushes in digital software (see the software in Digital painting) can imitate traditional painting paints and tools, such as oil, acrylic acid, pastel, charcoal, and airbrush. Users of the software can also customize the pixel size to achieve the unique visual effect (customized brushes).
AI picture generator art edit
1960 早期作画（草线图），引用AI art内容总结。The image generator is based on the generation adversarial network (GAN), which is a machine learning framework that allows two "algorithms" to compete with each other and iterate[2][3]. It is usually used to let the computer find the best solution by itself. It can be used to generate pictures that have visual effects similar to traditional fine art. The essential idea of image generators is that people can use text descriptions to let AI convert their text into visual picture content. Anyone can turn their language into a painting through a picture generator[4]. And some artists can use image generators to generate their paintings instead of drawing from scratch, and then they use the generated paintings as a basis to improve them and finally create new digital paintings. This greatly reduces the threshold of painting and challenges the traditional definition of painting art.
Generation Process edit
Generally, the user can set the input, and the input content includes detailed picture content that the user wants. For example, the content can be a scene's content, characters, weather, character relationships, specific items, etc. It can also include selecting a specific artist style, screen style, image pixel size, brightness, etc. Then picture generators will return several similar pictures[5] generated according to the input (generally, 4 pictures are given now). After receiving the results generated by picture generators, the user can select one picture as the result he wants, or let the generator redraw and return to new pictures.
In addition, it is worth mentioning the whole process: it is also similar to the "generator" and "discriminator" modules[6] in GANs.
Awards and recognition edit
In 2018, the artificial intelligence art auction was held at Christie's auction house in New York. The auction price of an artificial intelligence work "Edmond de Bellamy"[7] created by a collective in Paris named "Obvious" was $432500, far exceeding its original estimate.
At the end of August 2022, a person named Allen Jason won the first prize in the Colorado State Fair's fine art competition through the digital art work "Théâtre D'opéra Spatial[8][9]" made from a AI picture generator Midjourney.
- ^ Jackson, Wallace (2015). Digital Painting Techniques Using Corel Painter 2016 (1st ed.). Berkeley, CA: Imprint: Apress. pp. intro. ISBN 9781484217368.
- ^ Andrej Karpathy; Pieter Abbeel; Greg Brockman; Peter Chen; Vicki Cheung; Rocky Duan; Ian Goodfellow; Durk Kingma; Jonathan Ho; Rein Houthooft; Tim Salimans; John Schulman; Ilya Sutskever; Wojciech Zaremba (2016-06-16). "Generative Models, OpenAI". OpenAI. Retrieved 2022-10-09.
{{cite web}}: CS1 maint: multiple names: authors list (link) - ^ Ramesh, Aditya; Pavlov, Mikhail; Goh, Gabriel; Gray, Scott; Voss, Chelsea; Radford, Alec; Chen, Mark; Sutskever, Ilya (2021-02-26). "Zero-Shot Text-to-Image Generation". arXiv:2102.12092 [cs].
- ^ Roose, Kevin (2022-09-02). "An A.I.-Generated Picture Won an Art Prize. Artists Aren't Happy". The New York Times. Retrieved 2022-10-04.
- ^ Ramesh, Aditya; Pavlov, Mikhail; Goh, Gabriel; Gray, Scott; Voss, Chelsea; Radford, Alec; Chen, Mark; Sutskever, Ilya (2021-02-26). "Zero-Shot Text-to-Image Generation". arXiv:2102.12092 [cs].
- ^ Andrej Karpathy; Pieter Abbeel; Greg Brockman; Peter Chen; Vicki Cheung; Rocky Duan; Ian Goodfellow; Durk Kingma; Jonathan Ho; Rein Houthooft; Tim Salimans; John Schulman; Ilya Sutskever; Wojciech Zaremba (2016-06-16). "Generative Models, OpenAI". OpenAI. Retrieved 2022-10-09.
{{cite web}}: CS1 maint: multiple names: authors list (link) - ^ Cohn, Gabe (2018-10-25). "AI Art at Christie's Sells for $432,500". The New York Times. ISSN 0362-4331. Retrieved 2022-10-04.
- ^ "2022 Fine Arts Placings of the Colorado State Fair" (PDF).
{{cite web}}: CS1 maint: url-status (link) - ^ Roose, Kevin (2022-09-02). "An A.I.-Generated Picture Won an Art Prize. Artists Aren't Happy". The New York Times. Retrieved 2022-10-04.