Model trained on shojo manga artists.
Currently not on civitai because this is very much a beta. If you use this model, please provide me with feedback! I'm Mira!#1697 on Discord.
See the images for examples.
I think it performs best with the
aid28 and/or badv5
negative embeddings, but this is a bit subjective. Aid28 is more authentically retro, but badv5 is probably more like what most people want.
I use
ClearVAE
, but any VAE should be fine.
I recommend R-ESRGAN 4x+ Anime 6B for upscaling, but other upscalers
are fine
.
The sketchier gens use Latent (Nearest).
See
artists.txt
for names to add to your prompts. How well it replicates each style varies, but each produces a different result.
Example on recommended settings: