SoylentNews

NPC-131072 [soylentnews.org] writes:

From Machine Learning @ Berkeley Blog [berkeley.edu]

In recent months there has been a bit of an explosion in the AI generated art scene.

Ever since OpenAI released the weights and code for their CLIP [openai.com] model, various hackers, artists, researchers, and deep learning enthusiasts have figured out how to utilize CLIP as a an effective “natural language steering wheel” for various generative models, allowing artists to create all sorts of interesting visual art merely by inputting some text – a caption, a poem, a lyric, a word – to one of these models.

Original Submission