Instructions to use CabalResearch/Mugen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CabalResearch/Mugen with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CabalResearch/Mugen", 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
Comfyui error
#3
by win10 - opened
RuntimeError: Given groups=1, weight of size [320, 32, 3, 3], expected input[2, 9, 152, 104] to have 32 channels, but got 9 channels instead
win10 changed discussion status to closed
Hello @win10 , did you solve this error?
I'm on latest comfyUI nightly release, and I'm getting the same error.
I saw the workflow and assumed that it didn't need any custom nodes so I should be okay, but this patches the model.
It works now! Thanks!