Hey everyone! 👋

Presenting my Shego LoRA from Kim Possible! This one was particularly challenging due to the nature of her outfits, so I'm really interested in seeing your pictures and feedback!

The LoRA was trained on Anima 1.0 and has 3 outfits baked in:

• Default Outfit

• Miss Go

• Skirt Variant (seen in So the Drama)

The LoRA is trained primarily for Shego's character identity, appearance, and these three outfits, while still allowing you to use different outfits and poses.

Base Model

Anima 1.0 - Base checkpoint

anima-base-v1.0

The LoRA should also work well with other Anima-based checkpoints.

Recommended Weight

0.9

Trigger Word

sgokp

Style

2d animation, flat colors, cel shading

Appearance

green skin, green eyes, long black hair

Default Outfit

two tone green and black bodysuit, green glove, black glove

Default Outfit - Optional Full Body Poses

green footwear, black footwear

Miss Go

For this outfit, the trigger blue headband is necessary as it triggers her slightly different hairstyle.

blue headband, blue turtleneck sweater, light brown blazer, dark brown knee length skirt, light brown belt

Miss Go - Optional Full Body Poses

blue high heeled pumps

Skirt Variant (So the Drama)

This is the weakest of the three outfits and may vary between checkpoints and poses. The asymmetrical skirt may show parts of both legs or cover most of one leg just like the movie

two tone green and black crop top, midriff, two tone green and black asymmetrical skirt, green glove, black glove

Skirt Variant (So the Drama) - Optional Full Body Poses

green footwear, black footwear, high heels

Powers

To show images of Shego using her power, use:

green plasma energy

Using the Tags

The appearance and outfit tags can be used separately depending on what you want to generate.

For example, you can use Shego's appearance tags while changing the outfit completely, or combine the appearance with any of the outfits above.

The LoRA should also work with different outfits and poses while retaining Shego's identity.

For full-body examples, the footwear tags can be added when needed.

Suggested Generation Settings

My testing was done using a Turbo LoRA with the following settings:

• LoRA Weight: 0.9

• Sampler: Euler a

• Scheduler: Simple

• Steps: 12

• CFG: 2.5

These settings worked well for my testing, but other Anima-compatible settings and checkpoints may require some adjustment.

Training / Examples

I tried to tag the training images with accurate metadata, and the example images were generated using recorded seeds to make the results easier to reproduce.

You can refer to the example images for additional generations, outfits, poses, and variations.

Hope you enjoy the LoRA! ❤️