import { AutoProcessor, VitMatteForImageMatting, RawImage,  Tensor, cat  } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.14.2';

env.allowLocalModels = false;

// Load processor and model
const processor = await AutoProcessor.from_pretrained('Xenova/vitmatte-small-composition-1k');
const model = await VitMatteForImageMatting.from_pretrained('Xenova/vitmatte-small-composition-1k');

// Load image and trimap
const image = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_image.png');
const trimap = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_trimap.png');

// Prepare image + trimap for the model
const inputs = await processor(image, trimap);

// Predict alpha matte
const { alphas } = await model(inputs);
// Tensor {
//   dims: [ 1, 1, 640, 960 ],
//   type: 'float32',
//   size: 614400,
//   data: Float32Array(614400) [ 0.9894027709960938, 0.9970508813858032, ... ]
// }

// Visualize predicted alpha matte
const imageTensor = new Tensor(
  'uint8',
  new Uint8Array(image.data),
  [image.height, image.width, image.channels]
).transpose(2, 0, 1);

// Convert float (0-1) alpha matte to uint8 (0-255)
const alphaChannel = alphas
  .squeeze(0)
  .mul_(255)
  .clamp_(0, 255)
  .round_()
  .to('uint8');

// Concatenate original image with predicted alpha
const imageData = cat([imageTensor, alphaChannel], 0);

// Save output image
const outputImage = RawImage.fromTensor(imageData);
outputImage.save('output.png');