Re:Nvidia releases Paint me Picture – A web app for GauGAN2
by Imnimo on Wednesday November 24, 2021 @11:54PM
(#29338331)
Yeah, the text-to-image seems to be highly dependent on whether the generator knows how to generate the specific objects the text model thinks should be in the image. I got much more consistent results using the semantic segmentation drawing as input:
(and for what it's worth, you're totally right that the UI is just an absolute disaster)
Re:Nvidia releases Paint me Picture – A web app for GauGAN2
by akersten on Thursday November 25, 2021 @12:11AM
(#29338403)
The picture you drew and had it turn into rocks is actually really cool!
I think I would have been more generous to the project had I known it could do that. Maybe I X'd out of the frustrating tutorial too early? :)
Re:Nvidia releases Paint me Picture – A web app for GauGAN2
by johnsolo1701 on Thursday November 25, 2021 @12:53AM
(#29338599)
Literally the first step after accepting the TOS:
Re:Nvidia releases Paint me Picture – A web app for GauGAN2
by egeozcan on Thursday November 25, 2021 @01:02AM
(#29338630)
Yes but the selection is lost if you press enter out of habit. I had the same frustration until I realized what happened which turned that into anger :)
Maybe I'm just too old for tech demos.
Re:Nvidia releases Paint me Picture – A web app for GauGAN2
by johnsolo1701 on Thursday November 25, 2021 @02:45AM
(#29339116)
Nah, the UI is not very intuitive, so there's plenty of blame to go around :-)
Alright, I've uttered the incantation for it to do the thing. I still don't get it. [0] https://imgur.com/4zbaiH0
I also tried another example prompt, which bared a striking similarity to the previous result. I don't know if it's persisting the result (It shouldn't - I didn't click the re-use image button), but the strange life-raft looking artifact is very persistent. [1] https://imgur.com/KTCM4xH