NOTE: I don't really do StableDiffusion stuff anymore, so this model won't get any more updates from here on out. If anyone else would like to take the reins, though, please feel free to! Pretty much all of the art I sourced for this LoRA was obtained through free-access sources such as Kemono, so I'm confident you'll be able to reconstruct or make it even better.
Just a quick and dirty model based on roughly about 145 321 pictures of Doodledox's works. Mostly weighed toward women and anthro bird girls, though it's also trained on a few male characters so you could possibly have some luck if that's what you're going for.
V1 and V2 trained on AutismMix, V3 trained on default Pony. You can input specific character tags; the model has a hard time generating content with Bailey and Verity, but generates Dee and Aza extraordinarily well:
Aza:
aza (doodledox), avian, pink skin, pink feathers, red beak, yellow eyes, big eyebrows, big hands, short hair, ponytail, medium breasts (alternatively, large breasts), thighs, thick thighs, pink tailDee:
dee (doodledox), avian, yellow skin, yellow feathers, pink beak, green eyes, big hands, short hair, hair antenna, large breasts, thighs, thick thighs, yellow tailWill add more example tags for other characters later, these are just the main two that work the best.
Description
Initial release. Trained on 145 images.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.