Deploy zero shot image classification on sagemaker

Models
1

I deployed a zero shot model on sagemaker and im trying to test it by sending this request

predictor.predict({
  "inputs": "https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png",
    "parameters": {
    "candidate_labels": ['playing music', 'playing sports']
  }
}
)

but the following error is shown :

An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from model with message "{
  "code": 400,
  "type": "InternalServerException",
  "message": "You have to specify pixel_values"
}

can you help me guys.