[Character] Indiana (Azur Lane)

v2.0 - Pony
DrA_263
about 1 year ago

Character model based on what few images (11 in total) I could scrape together, namely the official splash arts, a few official artworks, some screenshots from the music video, and the small handful of fan arts.

Usage

Basic

Works well anywhere between a strength of 0.7 to 1.0.

Base trigger is indiana
Specifying dark skin shouldn't be necessary, but may help in some cases.

The facial scar is tagged separately in case you don't want to include it, but is not very consistent as you will see in the previews (likely due to the lack of data).

Higher strengths (0.9-1.0) will more accurately capture the facial scar but will lead to the base outfits bleeding into most output (especially the coat).

Outfits

Outfit components are tagged separately so you can choose what to include.

  • Base skin:
    long coat, necktie between breasts, harness, cleavage, midriff, black chaps, high-waisted thong, black boots

  • 'High Noon Arrest' skin:
    cowboy hat, blue cape, tassels, black bra, cleavage, under boob, belt, hotpants, cutoffs, chaps, crotchless legwear, brown boots, fingerless gloves

Extra

In the interest of openness and community-helping, I have uploaded the dataset along with the model, this includes: images, captions, and the training json (for kohya_ss).

Read more...
Download (53.5 MB) Download available on desktop only

Popularity

120 ~10

Info

Base model: Pony

Version v2.0 - Pony: 2 Files

To download these files, please visit this page from a desktop computer.

About this version: v2.0 - Pony

  • Increased dataset size to 22 images (+11).

  • Changed scar trigger to face scar to avoid conflict with facial.

Scar is a lot more consistent now, and model can be used at higher strengths without bleedthrough of the base outfits, though you may need to add hat to negative if unwanted.

5 Versions

😥 There are no [Character] Indiana (Azur Lane) v2.0 - Pony prompts yet!

Go ahead and upload yours!

No results

Your query returned no results – please try removing some filters or trying a different term.