Instructions to use kandinskylab/Kandinsky-5.0-I2I-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinskylab/Kandinsky-5.0-I2I-Lite 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-I2I-Lite", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Improve model card: Add metadata, links, and image-to-image usage for Kandinsky 5.0 Image Editing
#1
by nielsr HF Staff - opened
This PR enhances the model card for the Kandinsky 5.0 Image Editing model by:
- Adding
pipeline_tag: image-to-imageto improve discoverability for relevant tasks on the Hugging Face Hub. - Specifying
library_name: diffusersto enable an automated, predefined code snippet for users, as indicated by compatibility with the Diffusers library. - Including explicit links to the academic paper and the project page.
- Presenting a clear Python code snippet for image-to-image inference, extracted directly from the GitHub repository, to facilitate quick adoption.
makovka2000 changed pull request status to merged