Instructions to use Kr1sJ/iMontage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Kr1sJ/iMontage 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("Kr1sJ/iMontage", 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
Improve model card with metadata, links, features, and sample usage
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for iMontage by adding comprehensive information and metadata.
Key updates include:
- Adding the
pipeline_tag: image-to-imagefor better discoverability on the Hub, as the model is an all-in-one image generator. - Specifying
library_name: diffusersdue to the model's compatibility and usage ofdiffusion_pytorch_model.safetensorsas seen in the installation instructions. This enables the automated "how to use" widget. - Including a link to the paper: iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation.
- Linking to the official project page: https://kr1sjfu.github.io/iMontage-web/.
- Providing a link to the GitHub repository: https://github.com/Kr1sJFU/iMontage.
- Incorporating a "Features" section and a "Sample Usage" section with a Python code snippet extracted directly from the GitHub README, demonstrating basic image generation.
- Adding a table illustrating various inference tasks with example inputs and outputs, sourced from the GitHub README.
- Including the "Acknowledgment" and "Citation" sections.
Please review and merge this PR if everything looks good.
Kr1sJ changed pull request status to merged