How to use this with Diffusers?

#1
by jmportilla - opened

Apologies for my ignorance, but how can we use this model with diffusers library?

Owner

Hi, no problem, I still haven't published or changed the docs on how to use it because it's not finished yet. If you want to use this model you'll need to install image_gen_aux which is something we're planning to use instead of the outdated library we currently use.

To use it with diffusers you just need to install it from main like this

 pip install git+https://github.com/asomoza/image_gen_aux.git

To use it, you can do this:

from image_gen_aux import LineArtPreprocessor
from image_gen_aux.utils import load_image

input_image = load_image(
    "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/simple_upscale/hippowaffle.png"
)

lineart_preprocessor = LineArtPreprocessor.from_pretrained("OzzyGT/lineart").to("cuda")
image = lineart_preprocessor(input_image)

Thank you so much for the info! image_gen_aux looks like an amazingly useful library, thanks for sharing, excited to use it. Also thank you for your outpainting articles, I have found them super useful and informative, appreciate the quick reply and all your work for the community!

jmportilla changed discussion status to closed

Sign up or log in to comment