Format image to correctly pass through model.predict()

I created this model for image classification; however, when I try to pass the image path through model.predict(), I receive this error:

ValueError: Error when checking model : the Array of Tensors that you are passing to your model is not the size the the model expected. Expected to see 1 Tensor(s), but instead got 9 Tensors(s).

Is there any way to decrease the number of tensors going through the function, or correctly format the image in tensors to pass through and return a prediction?

I’ve looked everywhere, and other questions similar to this didn’t cover my use case in node.js. Any help or nudge in the right direction is welcome 🙂

Below is my model.json file, the model I created for image classification.
index.js is what I run through node.js to supposedly give a prediction.

model.json

{"modelTopology":{"class_name":"Sequential","config":[{"class_name":"Flatten","config":{"name":"flatten_Flatten1","trainable":true,"batch_input_shape":[null,7,7,256],"dtype":"float32"}},{"class_name":"Dense","config":{"units":100,"activation":"relu","use_bias":true,"kernel_initializer":{"class_name":"VarianceScaling","config":{"scale":1,"mode":null,"distribution":null,"seed":null}},"bias_initializer":{"class_name":"Zeros","config":{}},"kernel_regularizer":null,"bias_regularizer":null,"activity_regularizer":null,"kernel_constraint":null,"bias_constraint":null,"name":"dense_Dense1","trainable":true}},{"class_name":"Dense","config":{"units":3,"activation":"softmax","use_bias":false,"kernel_initializer":{"class_name":"VarianceScaling","config":{"scale":1,"mode":null,"distribution":null,"seed":null}},"bias_initializer":{"class_name":"Zeros","config":{}},"kernel_regularizer":null,"bias_regularizer":null,"activity_regularizer":null,"kernel_constraint":null,"bias_constraint":null,"name":"dense_Dense2","trainable":true}}],"keras_version":"tfjs-layers 0.7.0","backend":"tensor_flow.js"},"weightsManifest":[{"paths":["./ml-classifier-1-2-3.weights.bin"],"weights":[{"name":"dense_Dense1/kernel","shape":[12544,100],"dtype":"float32"},{"name":"dense_Dense1/bias","shape":[100],"dtype":"float32"},{"name":"dense_Dense2/kernel","shape":[100,3],"dtype":"float32"}]}]}

index.js

var tf = require('@tensorflow/tfjs-node');

const image = `./1-1.png`

const main = async () => {
  const model = await tf.loadLayersModel('file:///retake/savedmodels/model.json');
  model.summary();

  const prediction = model.predict(image);
  prediction.print();
}
main()