Instructions to use kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s", 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
Improve model card for Kandinsky 5.0 I2V Lite 5s: Add pipeline tag, library name, links, and usage example
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for the Kandinsky 5.0 Image-to-Video Lite (5s) model by:
- Adding the
pipeline_tag: image-to-video, making the model discoverable on the Hugging Face Hub under this task. - Specifying the
library_name: diffusers, enabling the automated "how to use" widget for seamless integration. - Including direct links to the academic paper, the project page, and the GitHub repository.
- Providing a practical "How to use" code snippet for image-to-video inference, derived directly from the project's GitHub README, confirming its compatibility and ease of use.
This update aligns the model card with best practices for discoverability and usability on the Hugging Face Hub.
makovka2000 changed pull request status to merged