Download
1 variant available
What's different about this now??
This version uses a slightly larger dataset, and is trained upon anime final prune (NAI). There is much less keyword wrangling involved and character clothing should appear more accurately with less prompting.
Show more

800 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
4210 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

(This lora is relatively old/outdated)
ありがとう 🍌
READ VERSION DESCRIPTIONS FOR DETAILS...
triggers: johnny joestar, johnnyjojo,
main outfit tags: hat, hoodie, lipstick -optional-
other or unrelated outfits: alternate costume
other notes:
The horse riding images were just depth2img with 3d models. horse usually generates white
Seemingly much more flexible than previous versions

