Instructions to use diffusers-modular/krea2-edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers-modular/krea2-edit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-modular/krea2-edit", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download block.py from diffusers-modular/krea2-edit: direct link, hf CLI and curl.
- Browser
- Download file 602 Bytes
-
https://huggingface.co/diffusers-modular/krea2-edit/resolve/0900a96df47b601279254c353866d146bb3dbd56/block.py
- Command line
-
hf download hf://diffusers-modular/krea2-edit@0900a96df47b601279254c353866d146bb3dbd56/block.py
-
curl -L -o block.py https://huggingface.co/diffusers-modular/krea2-edit/resolve/0900a96df47b601279254c353866d146bb3dbd56/block.py
602 Bytes
| """Entry point for the Krea 2 reference-image edit modular blocks (loaded via `trust_remote_code`). | |
| Importing this module also registers `Krea2Transformer2DModel` into the `diffusers` namespace so that | |
| `ModularPipeline` component loading can resolve the transformer referenced as | |
| `["diffusers", "Krea2Transformer2DModel"]` in the base `krea/Krea-2-Turbo` `model_index.json`. | |
| """ | |
| from .transformer_krea2 import Krea2Transformer2DModel # noqa: F401 (registers into diffusers namespace) | |
| from .modular_blocks_krea2_edit import Krea2EditBlocks | |
| __all__ = ["Krea2EditBlocks", "Krea2Transformer2DModel"] | |