ReszkaMixes / README.md
reszka's picture
Update README.md
b80d386
|
raw
history blame
1 kB
metadata
license: creativeml-openrail-m
language:
  - en
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - waifu-diffusion

Model Card for Model ID

Anime models mix for stable diffusion

Model Details

Model Description

This model is 50% weighted mix of: https://huggingface.co/andite/yohan-diffusion/blob/main/Cocoa.ckpt and https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/AbyssOrangeMix2/AbyssOrangeMix2_nsfw.safetensors

  • Developed by: Reszka
  • Model type: Anime/NSFW
  • License: CreativeML OpenRAIL-M license

Uses

Sampler: “DPM++ SDE Karras” is good Steps: forTest: 12~ ,illustration: 20~ Clipskip: 1 or 2 Upscaler : Latenet (nearest-exact) CFG Scale : 5 or 6 (4~8) Denoise strength: 0.5 (0.45~0.6) If you use 0.7~, the picture will change too much. If below 0.45, Block noise occurs.

Recommendations

Use bad_prompt_version2, bad-hands5 and bad-artist for better results

Click to expand