Studio Ghibli Style LoRA - offset
Highlighted images
Recommended Prompts
ghibli style
ghibli style, 1girl, looking at viewer, solo, upper body
Recommended Negative Prompts
(painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, cropped, watermark, worst quality, jpeg artifacts, low quality, normal quality, signature, username, artist name, (worst quality, bad anatomy, low quality:1.4)
Recommended Parameters
samplers
steps
cfg
resolution
Recommended Hires (High-Resolution) Parameters
upscaler
upscale
steps
denoising strength
Tips
Use a weight of around 1 for the offset version and 0.65 for the old version for best results.
This is a style model, so to create specific Ghibli characters combine with character TI/LoRA models to avoid overfitting on style.
To use LoRA with auto1111, update your webui with git pull or redownload, copy the file to stable-diffusion-webui/models/lora, select your LoRA in the interface, and adjust the weight (default is :1).
Creator Sponsors
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Studio Ghibli style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
I know there are already various Ghibli models, but with LoRA being a thing now it's time to bring this style into 2023. This is good around 1 weight for the offset version and 0.65 for the old one, on Anything v4.5 for a more authentic style, but it's also good on AbyssOrangeMix2. Triggers with ghibli style and, as you can see, it should work with any character LoRA or TI that didn't overfit on style too. Keep in mind, this is a style model not a "Ghibli characters" model, so movie characters in the examples are made using careful prompting, meaning it can reproduce similar characters, but it won't make them perfectly (unless you also use other TI/LoRA's).
4th pic by Karkaz using also his own character LoRA.
Last pic by LottaLewds.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight if needed (by default it's
:1)
Contributor
Model Details
Model type
Base model
Model version
Model hash
Trained words
Creator
Discussion
Please log in to leave a comment.
