mayhair@discuss.tchncs.de to AI Generated Images@sh.itjust.worksEnglish · 3 months agoSome fun pics of my OC/online avatar (Cleo) (view body for more)discuss.tchncs.deexternal-linkmessage-square11fedilinkarrow-up141arrow-down114file-text
arrow-up127arrow-down1external-linkSome fun pics of my OC/online avatar (Cleo) (view body for more)discuss.tchncs.demayhair@discuss.tchncs.de to AI Generated Images@sh.itjust.worksEnglish · 3 months agomessage-square11fedilinkfile-text
Here come the silly ones… And finally something we should all agree on… (edited via GIMP) I used: Stable Diffusion WebUI Forge Pony Diffusion V6 XL Shane Glines Style LoRA
minus-squaredavidgro@lemmy.worldlinkfedilinkEnglisharrow-up6·3 months agoI’m really surprised at the consistency. I haven’t kept up, so I don’t know how anything works now, but I’m used to all the little details changing each time (instead of only a couple at most like here)
minus-squaretal@lemmy.todaylinkfedilinkEnglisharrow-up5·edit-23 months agoDitto, though the LoRA might explain it. The base model, Pony Diffusion, doesn’t normally act like that in my experience. Maybe if you generated an enormous number of images and culled them. The simplicity of the style might also help – less to change.
minus-squaremayhair@discuss.tchncs.deOPlinkfedilinkEnglisharrow-up4·3 months agoIt’s definitely the LoRA :)
I’m really surprised at the consistency. I haven’t kept up, so I don’t know how anything works now, but I’m used to all the little details changing each time (instead of only a couple at most like here)
Ditto, though the LoRA might explain it.
The base model, Pony Diffusion, doesn’t normally act like that in my experience. Maybe if you generated an enormous number of images and culled them.
The simplicity of the style might also help – less to change.
It’s definitely the LoRA :)