🤗🖼️HuggingPics

Fine-tune Vision Transformers for anything using images found on the web.

Check out the video below for a walkthrough of this project! ⤵️

Usage

Click on the link below to try it out:

How does it work?

1. You define your search terms

2. We download ~150 images for each and use them to fine-tune a ViT

3. You push your model to HuggingFace's Hub to share your results with the world

Your auto-generated model repo will look something like this. Pretty cool, eh? 😎

Examples

💡 If you need some inspiration, take a look at the examples below:

You can see a full list of model repos created using this tool by clicking here