V1
Tohru in her dragon form! This model was trained on a mix of SFW and NSFW pictures, with pictures mostly from the anime itself.
It should be able to generate:
With weightage about 0.8 to 1.
Anthro and Feral (Put "Feral" and "Anthro" trigger words accordingly)
SFW and NSFW
Prompts
Trigger Words: Tohru_kobayashi
Additional prompts: dragon, green scales, black wings, horns, tail, claws, female, 1girl, yellow eyes, slit pupils
Optional prompts: yellow sclera
Notes
Model is trained on the base Pony Diffusion model.
Realized that the generations might be a bit slow but not sure if it is this LoRA or whether it's just the site generator acting up.
Decided to generate using two of my more familiar styles to see the contrast of the LoRA (may do more of this in the future). Seems fine for both styles so far (pony realism and diffusion)
Both feral and anthro seem to work quite okay, but of course this model was trained more on feral.
Accuracy wise would be about 80 - 90% to her dragon form in the anime based on initial testing.
I realized if you want her human form hair and outfit, combine with another Tohru mod should work quite well.
For anthro models, use "hands" and "fingers" in prompts for more proper human anatomy (standard 4 finger 1 thumb) or "claws" if you want a slightly more dragon (typically generates 4 fingers)
For feral models, I tend to include these in negatives: "abs, fingers, belly button, hands, pov, human".
Want to support me without Tipping? Here's how:
Liking my posts, collecting my images or collecting my models all generate buzz for me.
Generate more pictures of my models. I get a base commission from anyone who generates using my model, even without the tip.
Leave a like on my model. This helps me with the algorithm in reaching more people
Leave a review. I take all feedback very seriously, good or bad.
Consider using the 'add post' under gallery... if you are posting pictures of just my LoRA. This gives me A LOT of buzz, while you can also complete your daily post quest.
Thank you very much!