Please support the artist and do not use this model for monetary gain!
I'd appreciate it if you could upload pictures here if you use this model, I'm curious to see what others will do with it, and if I like it, I will tip buzz! Thank you!
Anima LoRA
This is not a strictly furry LoRA as the dataset does not have a lot of furry species variety, so it usually falls back on the base model way of drawing especially the heads, but the art style is still applied pretty well.
I uploaded two separate runs, the base one is epoch 10 of 10 epoch run, the alternative one is epoch 14 of 30 epoch run.
Alternative version: Style is a little stronger and overfit a bit, but it is slightly better for furry stuff in my opinion.
I trained this without tag dropout, so you might need to be a bit more descriptive when prompting.
I hope you like it! Trained using both Danbooru tags and descriptive captioning.
Usage Guide
Trigger Word: @ngmanhho
Optional (VERY recommended!) tags:
crosshatching, sketch, lineart, brush strokeOptional (good to have) tags:
anime coloring, anime screenshot, traditional mediaRecommended Weight: 0.7 ~ 1.0
Preview Image Parameters
Checkpoint: Indigo Furry Mix Anima v1.0
Sampler: ER SDE
Scheduler: SGM Uniform
Steps: 30
CFG Scale: 4.0
Hires.fix:
Upscaler:
4x_foolhardy_Remacri(1.5x scale)Denoising Strength: 0.3
Steps: 15
*These settings are by no means the best, just what I personally use, but if something looks off on your generation, you can maybe give these a try!
**I did some inpaints on preview images, so if you are trying to replicate through txt2img only, it might not look 100% the same!

