zlacker

[parent] [thread] 5 comments
1. joeyco+(OP)[view] [source] 2022-05-24 06:29:58
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+82 >>Nition+2f
2. albert+82[view] [source] 2022-05-24 06:51:34
>>joeyco+(OP)
What else could creativity possible be?
3. Nition+2f[view] [source] 2022-05-24 08:52:48
>>joeyco+(OP)
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+yl
◧◩
4. zimpen+yl[view] [source] [discussion] 2022-05-24 09:55:20
>>Nition+2f
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+af2
◧◩◪
5. Nition+af2[view] [source] [discussion] 2022-05-24 20:40:31
>>zimpen+yl
Nice. Latent-diffusion has come out very traditional but the VQGAN/CLIP ones are fairly original.
replies(1): >>zimpen+wi2
◧◩◪◨
6. zimpen+wi2[view] [source] [discussion] 2022-05-24 21:04:54
>>Nition+af2
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]