菜种 Gardenia Natane
character_pokemon_gardenia
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 Gardenia / Natane from Pokemon.
Example images were picked from pure 512×512 txt2img results and then re-created at 1024×1024 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 512×512 (limitation of the technology) while still giving a realistic impression of what it looks like. Pure 512×512 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_gardenia (with underscores intact) to your positive prompt.
Note: Since Civitai renames files, you will need to rename the downloaded file to “character_pokemon_gardenia_vX.safetensors” (where X is the current version number) if you want to use the example prompts as-is. Otherwise, change “character_pokemon_gardenia_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 multiple variations of Gardenia’s signature look (although very limited and heavily biased towards the classic look because of limited usable training data) so you might need to put combinations of the following tags in your positive or negative prompts to get the desired results:
poncho
cropped shirt
midriff
belt
shorts
boots
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 boots were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.
The shirt might end up with short sleeves a lot of the time. Try adding long sleeves to the positive prompts to be more explicit.
Sometimes, the midriff and belt / shorts can blend together a bit. I don’t know how to fix this yet.
The shorts might come out longer than expected, especially from behind, and are often not torn. Maybe torn shorts in the positive prompts might help with this but I’ve not tried it a lot.
For some tag combinations, the hair might suddenly come out as long. Try adding short hair to the positive prompts for those cases (does not seem to happen often though).
Might sometimes generate a hat instead of just hair. Try things like hat in your negative prompts.
设计人生
