Instructions to use rooroo79/music-spectrogram-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rooroo79/music-spectrogram-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rooroo79/music-spectrogram-diffusion", 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
| """Shim for this checkpoint's model_index.json. | |
| The Google weights name the note/context encoders as library | |
| `spectrogram_diffusion`. Diffusers' from_pretrained() does: | |
| library = importlib.import_module("spectrogram_diffusion") | |
| class_obj = getattr(library, "SpectrogramContEncoder") | |
| class_candidates = {name: getattr(library, name, None) for name in LOADABLE_CLASSES} | |
| so this module must export both the encoder classes *and* ModelMixin | |
| (otherwise loading raises: no from_pretrained on the component). | |
| """ | |
| from __future__ import annotations | |
| from diffusers import ModelMixin | |
| try: | |
| from diffusers.pipelines.deprecated.spectrogram_diffusion.continuous_encoder import ( | |
| SpectrogramContEncoder, | |
| ) | |
| from diffusers.pipelines.deprecated.spectrogram_diffusion.notes_encoder import ( | |
| SpectrogramNotesEncoder, | |
| ) | |
| except ImportError: # older Diffusers still used the non-deprecated path | |
| from diffusers.pipelines.spectrogram_diffusion.continuous_encoder import ( # type: ignore | |
| SpectrogramContEncoder, | |
| ) | |
| from diffusers.pipelines.spectrogram_diffusion.notes_encoder import ( # type: ignore | |
| SpectrogramNotesEncoder, | |
| ) | |
| __all__ = ["ModelMixin", "SpectrogramContEncoder", "SpectrogramNotesEncoder"] | |