No special tags needed, just prompt normally while the LoRA is enabled. "Hires fix" is highly recommended for best results.
If you're interested in sharing your results or getting involved in male-focused Stable Diffusion projects, join us in the #men-only channel on the Unstable Diffusion Discord.
470 images
Tagged with wd14-swinv2-v2
Tagged image repeats:
33 1x repeat "monochrome, lineart"
17 1x repeat "normal quality"
8 1x repeat "sketch"
101 2x repeats "high quality"
311 2x repeats "masterpiece, best quality"
x768 base resolution with aspect ratio bucketing
25 epochs, batch size 5
1e-3 cosine with restarts LR (matching U-Net and text encoder)
25 cycles
256 dim
Clip level 2
[redacted] base model
[redacted] .vae enabled during training
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.