When I try to run the FluxPipeline on a Jupyter notebook it gets stuck on the cudart assertion error, but I can’t have a CUDA compatible torch on my M1 Pro mac. Is there a workaround for this?

I had the model loaded already without error.

Code I used:

import torch
from diffusers import FluxPipeline

model_id = "black-forest-labs/FLUX.1-schnell"

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

The snippet I ran:

code

And this is the error:

error