zlacker

[parent] [thread] 6 comments
1. dclowd+(OP)[view] [source] 2022-05-24 06:26:15
Looking at these… I can’t help but wonder if these are literal examples of AI imagination?
replies(1): >>joeyco+o
2. joeyco+o[view] [source] 2022-05-24 06:29:58
>>dclowd+(OP)
I've started to ask myself if my own creativity is a result of random sampling from the diffusion tapestry of associated memories and experience on that topic.
replies(2): >>albert+w2 >>Nition+qf
◧◩
3. albert+w2[view] [source] [discussion] 2022-05-24 06:51:34
>>joeyco+o
What else could creativity possible be?
◧◩
4. Nition+qf[view] [source] [discussion] 2022-05-24 08:52:48
>>joeyco+o
I do wonder what Dall-E 2 would output for a request along the lines of "A still life of a vase of flowers in a completely new art style."
replies(1): >>zimpen+Wl
◧◩◪
5. zimpen+Wl[view] [source] [discussion] 2022-05-24 09:55:20
>>Nition+qf
Don't have access to Dall-E 2 or Imagen but I do have [1] and [2] locally and they produced [3] with that prompt.

[1] https://github.com/nerdyrodent/VQGAN-CLIP.git [2] https://github.com/CompVis/latent-diffusion.git [3] https://imgur.com/a/dCPt35K

replies(1): >>Nition+yf2
◧◩◪◨
6. Nition+yf2[view] [source] [discussion] 2022-05-24 20:40:31
>>zimpen+Wl
Nice. Latent-diffusion has come out very traditional but the VQGAN/CLIP ones are fairly original.
replies(1): >>zimpen+Ui2
◧◩◪◨⬒
7. zimpen+Ui2[view] [source] [discussion] 2022-05-24 21:04:54
>>Nition+yf2
From my experiments, the LD one doesn't seem to have been trained on as big or as tagged data set - there's a whole bunch of "in the style of X" that the VQGAN knows* about but the LD doesn't. That might have something to do with it.
[go to top]