Please read through the entire description (might need to be expanded) and the version change notes as they cover a lot of information about basic use cases and limitations. Thank you!

This is an SD 1.5 LoRA for the character Lillie / Lilie from Pokemon.

Example images were picked from pure 512x512 txt2img results and then re-created at 1024x1024 using txt2img with minimal Hires Fix settings (no upscaler, denoising strength 0.1). This improves faces and other details that are almost impossible to get correctly and consistently at 512x512 (limitation of the technology) while still giving a realistic impression of what it looks like. Pure 512x512 results will have more distorted faces and less detail.

Please see the version change notes for the training and example image generation models as well as the used weights as they might change between versions. Remember that you might need to adjust weights to best suit your use case!

Remember to add the trigger phrase character_pokemon_lillie (with underscores intact) to your positive prompt.

Note: Since Civitai renames files, you will need to rename the downloaded file to "character_pokemon_lillie_vX.safetensors"(where X is the current version number) if you want to use the example prompts as-is. Otherwise, change "character_pokemon_lillie_vX" in the prompts to your local file name. This does not affect the trigger phrase, only the way you reference the LoRA.

The training set contained Lillie's two primary signature looks, the "braids look" from the start of the game and the "ponytail look" from the rest of the game. If you want to focus on one of these looks, you will need to put combinations of the following tags in your positive or negative prompts:

Braids look:

• dress

• duffel bag

• hat

• kneehighs

• slippers

• twin braids

Ponytail look:

• ankle socks

• backpack

• mary janes

• ponytail

• shirt

• skirt

You may also be able to mix these looks but I have not tried it. I might look into separating these into different trigger phrases in the future, not sure yet.

As the training set contained a few images with floating hair, you might need to add floating hair to the negative prompts if not desired.

Known Limitations / Problems:

• The shoes, socks and bags were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.

• Eyes and hair had different colors (blue and green) in the training data, better to specify explicitly. And maybe try adding multicolored eyes in the negative prompts. Still might come out a bit weird, I need to improve the tagging.

• The blue and white parts of the clothing, especially the dress, might get mixed up. No idea how to fix this yet. It might help to put e.g. white dress in the positive prompts.