Type | |
Stats | 213 3,182 |
Reviews | (38) |
Published | Mar 4, 2024 |
Base Model | |
Training | Steps: 2,520 Epochs: 4 |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Trigger Words | robo-fortune miss-fortune score_9, miss-fortune, 1girl, solo, yellow eyes, crop top, underboob, cat ears, scar, bell, short hair, dark skin, white hair, dark-skinned female, bob cut, shorts, fang, gloves score_9, robo-fortune, 1girl, solo, blue eyes, no humans, robot joints, humanoid robot, colored skin, bell, bob cut, short hair, white hair, cat ears, claws, belt pouch |
Hash | AutoV2 2E8ACC2440 |
Two characters Ms. Fortune and Robo-Fortune from Skullgirls (2D fighting game)
Dataset did not include detached limbs or gore that is sometimes associated with this character so don't expect that
LoRA is designed for use with ponyDiffusionV6XL or mix, for example AutismMix SDXL
Model: ponyDiffusionV6XL_v6.safetensors
Dataset size: 105
Clip skip: 1
dim32, alpha16
lr=0.0003, constant_with_warmup, adafactor
Optimizer extra arguments: scale_parameter=False relative_step=False warmup_init=False
My tips for generating on SDXL for AUTOMATIC1111
Resolution:
1024 x 1024
1152 x 896 or 896 x 1152
1216 x 832 or 832 x 1216
Don't use Hires. fix. Send the picture to img2img, set CFG 0.15-0.25, then select “SD upscale” in the script, you also need to select 4x-AnimeSharp (find out how to install it) or what you like best from upscale. All other settings are default. Click generate.
For me 12gb VRAM is enough for this using --xformers