I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary
Your generosity helps me stay motivated to keep improving and to keep trying new things!
At a Glance:
Base model: Illustrated (but you can experiment with other kinds!)
Use a VAE?: Yes (baked or your choice)
Clip skip: 1 or 2 (experiment with both!)
LoRA weight: generally from 1 - 0.7 (adjust as necessary)
Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4
Description:
When I originally made this LoRA, way back in December 2023 (!), there were a few Ghibli LoRAs floating around, but nothing specifically for this movie, which has its own unique art style. Since I waited so long to post it, I'm sure other LoRAs have sprung up in the meantime, but I'll go ahead and add this one to the mix as well!
As you might expect, this LoRA will give you a strong influence in the art style from the movie The Tale of the Princess Kaguya. If you really scrutinize it, I'm sure it's not a perfect recreation of the style, but it's strongly in the ballpark.
Troubleshooting:
As for potential issues you might encounter, the biggest one I noticed is that it likes to give black and white images a bit more frequently than I would like. This is easily solvable through prompting (such as putting "monochrome" in your negative prompt).
Other than that, you'll just run into the standard hand/fingers/anatomy issues that generally plague SD1.5 models. I'd say this model is really not any worse than your average 1.5 model in this area, so just use your regular fixes as necessary.
If you're having any other issues, please see the "At a Glance" section above. Basically, try different base models, try both clip skips, and try different LoRA weights until you find some combos that work well for you!
Outro:
If you make anything awesome, please consider posting them to the gallery! That goes for all of my LoRAs! I really like seeing what kind of stuff you all are able to make!
If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future LoRAs, please don't hesitate to share them with me!
