Hey everyone! 👋

Presenting my Annie Hughes LoRA from The Iron Giant.

____________________________________________________________________________________________

MOSS-Update

This is my second attempt at training an Annie MOSS LoRA. This time, I let Civitai's autotagger and trainer handle most of the work.

The results are decent, although the automatic captioning wasn't always the best. So, if you get some unexpected or unusual results, you might need to adjust the prompts a little.

Just like the Anima version, this LoRA supports both of Annie's familiar looks:

1. Waitress Look

2. Home Look

I'd really appreciate it if you shared your generations and left a review. Feedback would be very helpful! ❤️

Trigger Word

annieh

Appearance

a woman with wavy brown hair in an updo, green eyes

Default Outfits

Waitress Look

She is wearing a pink waitress uniform, a white apron that ties at the waist, and white loafers.

Home Look

She is wearing a blue long-sleeve shirt with black leggings, a purple apron, and black loafers.

As usual, you don't need to prompt for footwear unless you're going for full-body generations.

My (and Suggested) Generation Settings

I tried a couple of combinations, but Euler didn't give me the best results. Feel free to experiment with different sampler and scheduler combinations.

• Scheduler: er_sde

• Sampler: beta

• CFG: 3.0

• Steps: 50

Model Compatibility

The LoRA was trained on MOSS-Image-Base, but all my example generations were made using the MOSS-Image-SFT INT8 Pruned model.

The LoRA was trained on Anima 1.0 and works particularly well with two of Annie's default looks from the movie:

• Waitress look

• Home look

The LoRA is trained primarily for Annie's character identity, appearance, and these two 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

anniehij

Style

2d animation, flat colors

Appearance - Waitress

auburn hair, updo, green eyes

Default Outfit - Waitress

pink waitress uniform, knee length, white collar, white waist apron, short sleeves

Optional - Full Body Poses

white footwear

Appearance - Home

auburn hair, green eyes, hairband

Default Outfit - Home

blue long sleeve shirt, dark purple apron, black capri leggings

Optional - Full Body Poses

black footwear

Using the Tags

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

For example, you can use the character's appearance tags while changing the outfit completely, or combine the appearance with either of the default outfits.

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

For the 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! ❤️