[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers

Search:


View post   

>> No.52895655 [View]
File: 1.38 MB, 1280x800, catbox_rtkx94.png [View same] [iqdb] [saucenao] [google]
52895655

>>52893883

>>52858481
AI managed to gen a pizza cone for Noel back there
https://files.catbox.moe/0e6uwv.png
https://files.catbox.moe/xie5w6.png
https://files.catbox.moe/5qap58.png

>>52894952
I see, I don't really do img2img with full prompt unless I'm just up scaling.
I've always thought full prompt + masked only is telling the AI to cram the the full prompt in the inpainted area if it can.
I'll need to play around and see for myself what all this does, only way to learn. Just like most things here like model merging.

Navigation
View posts[+24][+48][+96]