Request for help, problems with the installation about prompt-to-prompt

[landian60]

I found it work that you can change the diffusers version to make sure it >=0.40.

[uziel313]

añadir
!pip install --upgrade diffusers transformers scipy

y correrá

[cinjon]

@landian60 or @uziel313, How did you get past the other errors that happen after this? In #29 , I pointed at two of them:

1. Setting the offset in ptp_utils.py L163 doesn't work with the newest diffusers.
2. After turning off the offset kwarg above, I get TypeError: forward() got an unexpected keyword argument 'attention_mask'.

[john12458]

Hello, I also encountered a similar problem.
The error occurs because of version inconsistencies between diffusers, transformers, and pretrained weights ("CompVis/stable-diffusion-v1-4").

Here is my solution.

diffusers==0.3.0
transformers==4.24.0

For "CompVis/stable-diffusion-v1-4", we add "revision='249dd2d739844dea6a0bc7fc27b3c1d014720b28'" for the stable version.

ldm_stable = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", use_auth_token=MY_TOKEN, revision="249dd2d739844dea6a0bc7fc27b3c1d014720b28").to(device)