[go: up one dir, main page]

Jump to content

Artbreeder

From Wikipedia, the free encyclopedia

Artbreeder
The logo for the 'General' category
Type of site
Content creation
Available inEnglish
Country of originUnited States[1]
Created byJoel Simon[2]
URLartbreeder.com
CommercialNo
Launched2018[2]
Current statusActive
Content license
CC0[3]

Artbreeder, formerly known as Ganbreeder,[4] is a collaborative, machine learning-based art website. Using the models StyleGAN and BigGAN,[4][5] the website allows users to generate and modify images of faces, landscapes, and paintings, among other categories.[6]

Overview

[edit]
An example of portraits in Artbreeder

On Artbreeder, users mainly interact through the remixing - referred to as 'breeding' - of other users' images found in the publicly accessible database of images.[1] The creation of new variations can be done by tweaking sliders on an image's page, known as "genes", which in the "Portraits" model can range from color balance to gender, facial hair, and glasses.[6] Additionally, any image can be "crossbred" with other publicly viewable images from the database, using a slider to control how much of each image should influence the resulting "child".[2][5]

The site also allows for uploading new images, which the model will attempt to convert into the latent space of the network.[6]

Notable usages

[edit]

The similarly AI-driven text adventure game AI Dungeon uses Artbreeder to generate profile pictures for its users,[7] and The Static Age's Andrew Paley has used Artbreeder to create the visuals for his music videos.[8][9] Artbreeder has been used to create portraits of characters from popular novels such as Harry Potter and Twilight.[10][11] They have also been used to add realistic features to ancient portraits.[12]

Artbreeder was used to create characters in the sequel to Ben Drowned with the titular villain, an AI-construct itself, created entirely using the website. [13]

Changes to Artbreeder

[edit]
An example of the pattern feature of Artbreeder, if you squint, you can see the Wikipedia logo.

ArtBreeder underwent an overhaul, introducing several features to enhance the user experience. Among these updates is the integration SD-XL, developed by stability.ai. Additionally, ArtBreeder also added a functionality known as ControlNet,[14] which enables users to create images based on specific poses. With ControlNet, users can incorporate various poses into their AI Artworks. More features that were introduced into Artbreeder, are Pattern, which creates AI Pattern Images,[15] Outpainting or Uncropping was also an added feature to Artbreeder, that allows the user to expand the image beyond the normal dimensions of the image.

Reception

[edit]

The artwork generated by users of the website has been described as "beautiful" and "surreal," drawing comparisons to "weird, incomprehensible dreams" that "somehow touch the deep, unconscious parts of [the] mind".[16] However, the generated faces were noted as "creepy and 'off'", and still nowhere near the quality attained by actual digital artists.[6]

Additionally, the site faced criticism for perceived confusing aspects of the AI's behavior. Jonathan Bartlett of Mind Matters News noted that "As is always the case with AI, sometimes the [gene] knobs don't work as expected and sometimes the results are... strange," while conceding that Artbreeder was still "probably the start of a new future of made-to-order stock images."[17] Writers from Hyperallergic also took issue with perceived racial biases in the Portraits model, citing a comment from a user who faced difficulty from the neural network while attempting to darken the skin of a portrait to match a source image.[18]

See also

[edit]

References

[edit]
  1. ^ a b Groskin, Luke (8 March 2021). "The uncanny art inspired by evolution and generated by 'crossbreeding' images". Aeon.
  2. ^ a b c Bailey, Jason (8 January 2020). "The Tools of Generative Art, from Flash to Neural Networks". ARTnews. Retrieved 3 March 2021.
  3. ^ "Support". Artbreeder. Retrieved 10 November 2021.
  4. ^ a b Simon, Joel. "About". Archived from the original on 2 March 2021. Retrieved 3 March 2021.
  5. ^ a b George & Carmichael (2021, pp. 7–25)
  6. ^ a b c d Lee, Giacomo (21 July 2020). "Will this creepy AI platform put artists out of a job?". Digital Arts Online. Archived from the original on 22 December 2020. Retrieved 3 March 2021.
  7. ^ @AiDungeon (1 May 2020). "How have you been liking the AI generated avatars? (All images created on @Artbreeder)" (Tweet) – via Twitter.
  8. ^ "Musician Andrew Paley Creates AI Videos: "Collaborating with a Machine Fit the Moment"". Red Herring. 1 September 2020.
  9. ^ Gerage, Alex (Spring 2021). "Human-Machine Collaboration Visualizes Music". Northwestern Engineering. Northwestern University.
  10. ^ Miller, Leon (5 May 2022). "AI-Created Harry Potter Images Reveal Scarily Book-Accurate Character Portraits". CBR. Retrieved 3 June 2022.
  11. ^ Bentz, Adam (17 May 2022). "Twilight Images Reveal Characters' Book-Accurate Looks Using AI". ScreenRant. Retrieved 3 June 2022.
  12. ^ Vincent, James (21 August 2020). "These photorealistic portraits of ancient Roman emperors were created using old statues and AI". The Verge. Retrieved 3 June 2022.
  13. ^ "Arcade Attack Podcast – September (4 of 4) 2020 - Alex Hall (Ben Drowned) - Interview". Arcade Attack. 28 September 2020. Retrieved 31 October 2022.
  14. ^ Simon, Joel (25 February 2024). "ControlNet Poser for Artbreeder". ArtBreeder.
  15. ^ Simon, Joel [@Artbreeder] (25 September 2023). "Artbreeder 𝗣𝗮𝘁𝘁𝗲𝗿𝗻𝘀 is a new tool to easily generate and draw patterns for creating AI images" (Tweet) – via Twitter.
  16. ^ Kulicki, Maks (22 May 2020). "3 Artificial Intelligence tools to enhance your creativity". Medium. Retrieved 3 March 2021.
  17. ^ Bartlett, Jonathan (22 October 2019). "The AI Revolution has come for Stock Art". Retrieved 3 March 2021.
  18. ^ Bond, Sarah E.; Junior, Nyasha (8 October 2020). "How Racial Bias in Tech Has Developed the "New Jim Code"". Hyperallergic. Archived from the original on 7 February 2021.

Bibliography

[edit]