Quick question about inference

#1
by andrew-cartwheel - opened

Benjamin!

Your LoRAs are awesome. I'm trying to run them in a diffusers pipeline, but can't seem to get the keys to line up. What is your preferred method for inference?

Andrew!

You caught me just as I was moving things around and adding examples. If you install diffusers from source it will now successfully load the LoRA format hosted here. Now that the 1.3B and 14B are separate repositories, you can also do .load_lora_weights("benjamin-paine/steamboat-willie-1.3b")to automatically download and load - check the model card for example code!

It works like a charm! Cheers and great work again

benjamin-paine changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment