Instructions to use not-pegasus/IMAGE_MODAL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use not-pegasus/IMAGE_MODAL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("not-pegasus/IMAGE_MODAL", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
| from typing import ClassVar | |
| from fsspec import AbstractFileSystem | |
| __all__ = ("ChainedFileSystem",) | |
| class ChainedFileSystem(AbstractFileSystem): | |
| """Chained filesystem base class. | |
| A chained filesystem is designed to be layered over another FS. | |
| This is useful to implement things like caching. | |
| This base class does very little on its own, but is used as a marker | |
| that the class is designed for chaining. | |
| Right now this is only used in `url_to_fs` to provide the path argument | |
| (`fo`) to the chained filesystem from the underlying filesystem. | |
| Additional functionality may be added in the future. | |
| """ | |
| protocol: ClassVar[str] = "chained" | |