Open paratechnical opened 8 months ago
Had the same issue, never managed to make it work, even installing older versions of diffusers. Were you able to find a workaround?
Had the same issue, never managed to make it work, even installing older versions of diffusers. Were you able to find a workaround?
I managed to solve it by downoading zipped (or clone) commit just before the change happened.
Here is the link https://github.com/huggingface/diffusers/commit/b786fe17588dae93315a69620ccaf8ffd4106823
And the commit hash is b786fe17588dae93315a69620ccaf8ffd4106823
After cloning/downloading and unzipping and installing it by using:
1) cd /content/name_of_your_unzipped_folder 2) pip install .
it worked :)
For me it worked with:
git clone https://github.com/huggingface/diffusers
cd diffusers
git fetch origin 3517fb9
git checkout 3517fb9
pip install .
when I try to run python3 main.py I get the following error
ImportError: cannot import name 'text_encoder_lora_state_dict' from 'diffusers.models.lora' (/usr/local/lib/python3.11/site-packages/diffusers/models/lora.py)
I had to change a couple of things to get to this point I changed to requirements file to this in order to make it work
accelerate==0.24.1 bitsandbytes==0.41.2.post2 datasets==2.15.0 diffusers==0.25.0.dev0
and deleted diffusers.egg==info