News for hackers. Stuff that matters.

flowery

Re:Text to Image Generation on Monday March 29, 2021 @10:06PM (#26630599)
I guess it is supposed to help us find tumors and whatnot, synthesize images rather than rely on an artist to do it, etc. But if you listen to a lot of ML talks they sometimes say, "we trained this on images but the technique works on any 2D or 1D signal" so it's applicable to signal problems in general.

What those are, I have no idea.

Re:Text to Image Generation 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 on Monday March 29, 2021 @08:34PM (#26630055)
"the answer to life the universe and everything" https://postimg.cc/w3g4TMvp
Re:Text to Image Generation on Monday March 29, 2021 @08:01PM (#26629836)
"super crab" ... it made a shrine with figurines and a logo https://postimg.cc/5jhgGtCv
Re:Text to Image Generation on Monday March 29, 2021 @06:19PM (#26629002)
"minimalist pumpkin" https://postimg.cc/1fvHzzq8
Re:Text to Image Generation on Monday March 29, 2021 @02:03AM (#26618151)
The gallery is truly valuable as a reference - thank you.
Re:Text to Image Generation on Monday March 29, 2021 @01:26AM (#26617982)
For some reason Colab let me run this all last night. Wow just wow. Eventually I got the feeling that it matters if I'm watching.

Each of these links has about 9 images and the prompts that made them. Sometimes the image does not look like an animal right off the bat, then it seems like you asked for something the network had to say.

https://postimg.cc/vDvYdBhC https://postimg.cc/XpHnpzT8 https://postimg.cc/HVspWgPn

That Syd Mead style ... mwa