Instructions to use Eddy12253/imagine-instruct-pix2pix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Eddy12253/imagine-instruct-pix2pix 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("Eddy12253/imagine-instruct-pix2pix", 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
Imagine InstructPix2Pix endpoint
Custom Hugging Face Inference Endpoint handler for instruction-based image
editing with timbrooks/instruct-pix2pix.
The handler accepts a text edit instruction in inputs, a base64 source image
in image, and generation controls in parameters.
The upstream model is distributed under the MIT license. The application using this endpoint remains responsible for its own acceptable-use controls.
- Downloads last month
- -