kandinskylab

/

Kandinsky-5.0-I2I-Lite-pretrain

like 2

Follow

Kandinsky Lab 202

This PR significantly enhances the model card for the Kandinsky 5.0 Image Editing model.

It adds:

• The pipeline_tag: image-to-image to correctly categorize the model's primary function.
• The library_name: diffusers to enable the automated "how to use" widget on the Hub, as evidenced by the integration examples in the GitHub repository.
• Links to the paper (Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation), the project page (https://kandinskylab.ai/), and the GitHub repository (https://github.com/kandinskylab/kandinsky-5).
• A descriptive overview of the model's capabilities and visual examples of its output.
• A practical Python code snippet for image-to-image inference, directly sourced from the project's GitHub README, to guide users on its usage.
• The citation information and acknowledgements for proper attribution.

This update makes the model more discoverable, informative, and user-friendly on the Hugging Face Hub.