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