Type | |
Stats | 1,190 202 |
Reviews | (218) |
Published | Apr 14, 2023 |
Base Model | |
Training | Steps: 3,516 Epochs: 20 |
Trigger Words | double-buns buns-cover |
Hash | AutoV2 CF3CE34A3D |
Please check out my Ko-Fi page if you are interested in supporting me.
LoRA commissions open! -> Fiverr
This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.
Trigger words for V2.20:
<lora:DoubleBunsv220:0.75>(double-buns) or <lora:DoubleBunsvv220:0.75>(buns-cover)
This version is a little better with differentiating between covered and uncovered.
You can try "double-buns" for uncovered buns, "buns-cover" or "white buns-cover" for covered buns (these 2 are mutually exclusive, chose one!), "hair ribbon", "hair ornament".
Notes: It doesn't do very well with the buns color! Its almost always white since that's mostly what the dataset was! You might get different colors, you can try very basic ones. If its failing to generate "buns-cover", prompting for "white buns-cover" increases the chance of it generating the cover variation.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated from Hassaku.
All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.
It was trained on 211 512x512 images scraped from the internet and 13 epochs using animefull_final.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.