ME!ME!ME!版本me!me!me!-PonyXL (ID: 342556)

I present to you the legendary Meme-chan

LoRA is designed for use with ponyDiffusionV6XL or mix, for example AutismMix SDXL

I couldn't create a version for Animagine in normal quality. Most likely I won't be able to release it.

Model: ponyDiffusionV6XL_v6.safetensors

Dataset size: 95

Clip skip: 1

dim32, alpha16

lr=0.0003, constant, 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

描述:

训练词语: me!me!me!