Instructions to use Boogu/Boogu-Image-0.1-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Boogu/Boogu-Image-0.1-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Boogu/Boogu-Image-0.1-Base", 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
| # Copyright (C) 2026 Boogu Team. | |
| # This repository is a fork by Boogu Team; modifications have been made. | |
| """ | |
| Compatibility entry point for the released Boogu base pipeline transformer. | |
| The inference code in this repository owns the canonical transformer | |
| implementation. Keeping another full copy here easily causes drift between the | |
| released pipeline package and the active codebase. Diffusers only needs this | |
| module to expose `BooguImageTransformer2DModel` for | |
| `model_index.json`, so this file intentionally re-exports the repository class. | |
| """ | |
| try: | |
| from boogu.models.transformers.transformer_boogu import ( | |
| BooguImageTransformer2DModel, | |
| PromptEmbedding, | |
| ) | |
| except ModuleNotFoundError as exc: | |
| if exc.name != "boogu": | |
| raise | |
| raise ModuleNotFoundError( | |
| "Failed to import the canonical Boogu transformer implementation. " | |
| "Run inference from the Boogu-Image repository root " | |
| "or add that directory to PYTHONPATH before loading the pipeline." | |
| ) from exc | |
| __all__ = [ | |
| "BooguImageTransformer2DModel", | |
| "PromptEmbedding", | |
| ] | |