Instructions to use cerspense/zeroscope_v2_XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cerspense/zeroscope_v2_XL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_XL", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
RuntimeError: Conv3D is not supported on MPS
#7
by ova1 - opened
Hey guys, any suggestions?
Mac M1
RuntimeError: Conv3D is not supported on MPS
Exception occurred: Conv3D is not supported on MPS
There is a PyTorch PR for this: https://github.com/pytorch/pytorch/pull/99246
You can try PYTORCH_ENABLE_MPS_FALLBACK=1 to fallback to the CPU too.
After I set PYTORCH_ENABLE_MPS_FALLBACK=1, I still got the error RuntimeError: Conv3D is not supported on MPS