How to use text to image models from hugging face?

Sorry I am very new to ML and bumblebee but i wonder how to get this model to work with it?

By following the docs (Stable Diffusion — Bumblebee v0.3.0) I have issues to figure out how to set tokenizer, clip, unet, vae variables?

Or am I on the wrong track?

I would be very thankful for any help.

Hey @Bumbus, Bumblebee doesn’t support StableDiffusion XL just yet, but we definitely want to support it and optimise its performance.

1 Like

Hi @jonatanklosko thanks for your reply.
As the noob on this field am I, I did not know that there is a difference :smiley:
Thanks a lot for clarification