A newer version of the Gradio SDK is available:
5.15.0
PaliGemma Image Captioning Gradio App
Deployment Instructions
- Create a new Hugging Face Space
- Choose Python as the SDK
- Select 16GB CPU hardware
- Upload the following files:
app.py
requirements.txt
HuggingFace Access Token
- Go to HuggingFace settings
- Create a new access token with "Read" permissions
- Add the token as a secret named
HF_TOKEN
in your Space settings
Features
- Multi-language image captioning
- Upload custom images
- Example images included
- Supports English, Spanish, French, German captions
Model Details
- Model: google/paligemma-3b-mix-224
- Task: Multilingual Image Captioning