metadata
inference: true
language:
- en
tags:
- stable-diffusion
- text-to-image
license: creativeml-openrail-m
finetuned on dark, moody, "victorian" imagery (ใโใฎโ)ใ*:ใปใโง
v1 was trained on SD 1.4, v2 on SD 1.5. check the pdf for examples with different prompts & settings. comparisons.zip has steps vs cfg scale x/y plots for euler_a and lms.
use the tokens "darkvictorian artstyle" in your prompt to use the style.
random samples:
