How do I pass the text prompt and the image parameters to the predictor?

#3
by tocsa - opened

The SgaeMaker deploy card shows this invocation:

predictor.predict({
    "inputs": "Can you please let us know more details about your ",
})

But this is an image+text multi modal model. How do I pass in both the text prompt and the image?

I got fed up and used replicate.com: https://stackoverflow.com/a/77364236/292502

Sign up or log in to comment