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. The description is always focused on the latest version. Thank you!
This is an SD 1.5 LoRA for the character Gardenia / Natane from Pokemon. It works for models based on SD 1.x only, it will not work for models based on SD 2.x or SDXL!
Example images were picked from pure 512x512 txt2img results and then re-created at 1024x1024 using txt2img with moderate Hi-res Fix settings (upscaler Lanczos, denoising strength 0.4). 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 tag gardenia \(pokemon\) (with backslashes intact) to your positive prompt.
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.
Loves to generate black legwear under the shorts for some reason (not part of any training image). Try adding black legwear to the negative prompts. Might still show up a lot though.
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).
Shots from behind are very inconsistent due to extremely limited training data. Might for instance generate the poncho pattern, not apply poses correctly etc. Not much I can do without a bit more training data.
Description
There are detailed changes below the next paragraph, you might need to expand this version changes box!
I learned a few new things about creating LoRAs and wanted to see how far I can push my existing LoRAs without changes to their datasets. So there's still no support for alternate outfits, colors etc. for now, sorry! There are other LoRAs if you want those things. Not sure if I'll improve the LoRAs more than that in the future or make new ones but who knows.
LoRA Changes:
Now uses the standard "gardenia \(pokemon\)" instead of a custom trigger word to make things easier for everyone (please note though that the LoRA itself is still named "character_pokemon_gardenia_vX" as before!)
Switch to 32 dims (now trained directly instead of resizing from 128)
Switch to target weight 1 (increased from 0.7)
Changed a lot of training settings (too many to list, check LoRA metadata if you are interested) and updated to much newer scripts version (~3 months worth of changes)
Example image changes:
Use CLIP skip 2 instead of 1 as I accidentally did before
Change settings for hir-res fix: Switch upscaler from None to Lanczos and increase denoise from 0.1 to 0.4 to get better results while still not changing TOO much
Use a negative embedding for the majority of negative prompting
Recommended weight: 1
Training model: Anything V3
Example image generation model: AbyssOrangeMix2 - Hardcore