Character LoRAs - Want more character variety? Then check This List!
Description

Image imported from Derpibooru.
Original: https://derpibooru.org/images/2958317
Metadata at the time of import:
Field Data
Favorites 33
Upvotes 66
Downvotes 8
Score 58
Comments 10
Uploader Hazy Skies
Original description below this line

25.5 cute mares all generated via Pony Diffusion (Pony fine-tuned Stable Diffusion)
Prompt: Anon Filly smiling, Vivid green pony with jet black hair, fluffy, countershading, cute, vibrant cinematic lighting, trending on artstation, professional pony portrait by franz xaver winterhalter sophie anderson

safe14399 ai generated41100 automatically imported33036 derpibooru import33211 generator:stable diffusion21283 oc4665 oc only4019 oc:filly anon103 pony20332 chest fluff2230 collage316 cute4506 ear fluff2387 female38712 filly1229 high res3431 looking at you15900 mare13115 multiple angles1 smiling13713 solo31062

Comments

Syntax quick reference: **bold** *italic* ||hide text|| `code` __underline__ ~~strike~~ ^sup^ ~sub~

Detailed syntax guide

Background Pony #695A
Speaking of tags, I’m not all that certain if solo should apply. Each portrait is solo, but because it’s a collage then there isn’t just one pone and thus not solo?
There’s no doubt in my mind that making AI art is real art.
I spent about 1.5 hours tweaking things to produce these visuals!!1
I spent about 30 minutes generating to get all these, which wouldn’t have gotten as good results if it weren’t for modifying a prompt a fellow user was using which allowed for this level of quality with V1.
It seems that specifying specific styles (eg. Vivid cinematic), art platforms (eg. Deviantart, artstation) and artists (eg. Artgerm) seem quite important for achieving the best results, even if the only change is lighting, colour palettes and texture.
I’ve also been using AI for months, so perhaps the increase in speed is just experience with prompting, or maybe I was just lucky with these xD

Imported from Derpibooru - Posted by Hazy Skies