Bunny Mint (XL2-V3-NS)

The model is a very predictable result. Therefore, I recommend using seed with increasing the number of steeps when satisfied with the “draft” with a small number of steps. But predictability and forecasting have the other side of the coin: uniformity of results.

Introduction

BunnyMint is a Pony model based on two finetunes. The first finetune was trained on 8k randomly selected artist images with score:>99 from danbooru for 10 epochs to improve overall aesthetic.

Training

(8k random artist images score:>99) * 10 Epochs

(20k NAIv3 dataset) * 20 Epochs

Total steps: ~480k

Usage

Sample prompt

score_9, score_8_up, score_7_up, source_anime,
1girl, BREAK

joyful, black skirt, white pantyhose, crop top, double v,inside submarine, legs apart, pleated skirt, jumpsuit,
masterpiece,best quality

Negative prompt:

nsfw,censor,extra_fingers,logo,score_4,score_5,score_6,lowres,(bad),text,error,bad hands,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,extra digits,artistic error,username,scan,[abstract]

Settings

Steps: 40 (min 8, low 17)
Sampler: Euler a 
Schedule type: Polyexponential 
CFG scale: 6
Size: 624x912
Hires upscale: 1.5

Since the model is Pony-based, anything Pony related should work here as well.

License

This model is licensed under "Fair-AI public license 1.0-SD", please refer to the original License for more information: https://freedevproject.org/faipl-1.0-sd/

Source

Donate the model author

Finetuning models on personal hardware is pretty costly, so if anyone likes what I do and feels like it, here's my gumroad:

https://lylogummy.gumroad.com/l/avhut

Support

buymeacoffee. Thank you for support!