News for hackers. Stuff that matters.
Re:Text to Image Generation by rajangdavis on Monday March 29, 2021 @12:29AM (#26617707)
This is incredible... The first few images could easily be used as album cover art.

Is there a way to perform a similar translation with music? For example, if you play in D Minor (the saddest of all keys), is there a way to map the key or some other musical characteristic to a word and have the images be generated with the intermediate being the primary source? Or would the approach be to map images to certain characteristics of music directly?

Re:Text to Image Generation by jquaint on Monday March 29, 2021 @12:36AM (#26617741)
I wonder if you could use another model that describes music and feed that text into this one?

Even something based on spotify's music labeling api would be super interesting!

Re:Text to Image Generation by coldcode on Monday March 29, 2021 @07:34AM (#26620133)
I will get excited when I see this making images bigger than 256 pixels.
Re:Text to Image Generation by flowery on Monday March 29, 2021 @09:42PM (#26630476)
Currently both Big Sleep and Deep Doze are generating 512x512. These ones are representative: https://postimg.cc/HVspWgPn Few are "collages", most images have full-area coherence.
Re:Text to Image Generation by aasasd on Monday March 29, 2021 @12:45AM (#26617788)
> as album cover art

Indeed, what I see is an album cover generator.

“A man painting a completely red image” is very much a dadaist collage. The only complaint is that the ‘man’ could be rather more recognizable as such.