![]() ![]() Check out ai_curio on Twitter for an endless stream of examples.Ĭopyright © 2021 IDG Communications, Inc. ![]() And these notebooks, themselves free to use under an MIT license, have spread across the internet like fanzines of decades past, being remixed, altered, translated, and used to produce astonishing works of art. To fill that gap, Ryan Murdoch and Katherine Crowson developed Colab notebooks that combined CLIP with other open source models, such as BigGAN and VQGAN, to make prompt-based generative artworks. While CLIP was fully open sourced, OpenAI’s generative neural network, DALL-E, was not. First up, there’s OpenAI’s CLIP (Contrastive Language-Image Pre-training) model, a multimodal model for generating text and image vector embeddings. Depending on the requirements a user may prefer a more turn-key solution that allows them to get up and running fast, or a more robust platform that gives them more power to customize the solution to their more exacting. However, I think the open source components that have ignited this year’s explosion in generative art also deserve some recognition. Database software comes in a wide variety of packages and the best platform for one user might not be the best for another. ![]() The winners of the Bossies have traditionally been libraries, frameworks, platforms, and operating systems - the backbone of open source.
0 Comments
Leave a Reply. |