Gives base Pony Diffusion V6 model more defined characters and backgrounds and can improve character/style LoRA accuracy. Comparisons at end of gallery.
Recommended positive prompt: score_9, score_8_up, score_7_up, source_anime
For western style replace source_anime
with source_cartoon
If using a character or style LoRA and its style is not preserved remove source_anime
I recommend leaving negative prompt blank. You may put source_anime
, source_cartoon
, or 3d
in the negative to tune the style but try without a negative first.
To use artist tags shown in the examples use art by
followed by the artist name.
This is an extract of version 2 of Anime Confetti Comrade Mix. Generally I recommend using the base model instead of this LoRA. However using this LoRA with the base Pony Diffusion model gives you the flexibility to tune how strong you want its effect to be.