Hey All, presenting my Velma Dinkley LoRA from Scooby-Doo! Return to Zombie Island.

Scooby-Doo! Return to Zombie Island – Wikipedia

UPDATE

KREA 2 VERSION

This is my second attempt at a Krea 2 LoRA. Due to hardware limitations, most of my testing was done using quantized models. I'm particularly interested in seeing how it performs on larger, higher-quality models, so please do share your generations and reviews!

Trigger Word

velmartzi

Recommended Weight

0.9

Suggested Appearance Description

an animated woman with a brown bob haircut and thick black-rimmed glasses. She wears an orange turtleneck sweater, a red pleated skirt, orange knee-high socks, and red Mary Jane shoes.

You can take a look at my example images. One thing I noticed during testing is that scattering her default appearance across a natural-language prompt, rather than repeating everything in one rigid identity block, might give the model a little more freedom in how it interprets her appearance. Or it could just be my model!

Feel free to experiment with different prompt structures and outfits while retaining her recognisable appearance.

Suggested Generation Settings

My testing was done using:

• LoRA weight: 0.9

• Sampler: er_sde

• Scheduler: Simple

• Steps: 9

• CFG: 1.0

I'd love to see what you create with either version, especially your results with Krea 2 on larger models. Please share your generations and leave a review. Happy generating!

_____________________________________________________________________________________________

ANIMA

Anima 1.0 — Base checkpoint (anima-base-v1.0). Not the Aesthetic or Turbo variants.

Recommended Weight

0.9

Trigger Word

velmartzi

Style

2d animation, cel shading, flat colors

Appearance

short auburn hair, thick rectangular black-framed glasses, black eyes, freckles

Clothes

baggy orange turtleneck sweater, frilled red miniskirt, orange knee socks, red Mary Jane shoes

The appearance and clothing tags can be used separately depending on what you want to generate. The LoRA should also work with different outfits while retaining Velma's identity.

Suggested Generation Settings

My testing was done using:

• LoRA weight: 0.9

• Sampler: Euler a

• Scheduler: Simple

• Steps: 12

• CFG: 2.5

You can refer to my images for more examples. I have tried to tag the training images with accurate metadata and seeds.