This is a clip-interrogator starter template from Banana.dev that allows on-demand serverless GPU inference.
You can fork this repository and deploy it on Banana as is, or customize it based on your own needs.
- Fork this repository to your own Github account.
- Connect your Github account on Banana.
- Create a new model on Banana from the forked Github repository.
- Wait for the model to build after creating it.
- Make an API request using one of the provided snippets in your Banana dashboard. However, instead of sending a prompt as provided in the snippet, send the base64 string of the image where you want to apply CLIP to in the following structure:
inputs = {
"image": "image_base64_string",
}
For more info, check out the Banana.dev docs.