SoylentNews is people
SoylentNews is powered by your submissions, so send in your scoop. Only 19 submissions in the queue.
SoylentNews
From Machine Learning @ Berkeley Blog
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 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.
[The linked story provides about 3 dozen stunning examples of inputs and generated images as well as an extensive links to resources, preprints, and journal articles.--martyb]
This discussion has been archived.
No new comments can be posted.
Alien Dreams: An Emerging Art Scene
|
Log In/Create an Account
| Top
| 9 comments
| Search Discussion
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
If you didn't get caught, did you really do it?
(Score: 4, Informative) by FatPhil on Monday July 05 2021, @09:19PM
You can see that deep down it's not actually evolved that far in those intervening years. That one was of course deliberately trained on a very restricted training set for lulz, don't be fooled into thinking that the AI itself is twisted. The ability to stimulate the generation with textual keywords was always programmed into the AI, the internal model of what it's learnt is basically independent of the method it got the input. Show me the realtime demo of you speaking too it, accompanied with what the AI thinks the visuals should be. Let me play!
Great minds discuss ideas; average minds discuss events; small minds discuss people; the smallest discuss themselves