import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("YiYiXu/diff-diff-mellon", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]mellon nodes made with diffusers ModularNode
Instruction
Install Mellon
download this folder insde the custom directory:
install from the latest modular diffusers branch. https://github.com/huggingface/diffusers/pull/11235
pip uninstall diffusers -y
pip install git+https://github.com/huggingface/diffusers.git@modular-refactor
run python main.py and that's it
Components Manager
To use diffusers components manager across different custom nodes, for now, add this in your custom/__init__.py
from diffusers import ComponentsManager
components = ComponentsManager()
and add this code in all your custom nodes module file
from custom import components
e.g.
custom/
├── __init__.py # create your components manager here
├── mellon-modular-diffusers/
│ └── mellon-modular-diffusers.py # use in this
└── diff-diff/
└── diff-diff.py # use in this too
example workflow
find workflow here
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support