Florence-2-base

npm i @huggingface/transformers

import {
    Florence2ForConditionalGeneration,
    AutoProcessor,
    load_image,
} from '@huggingface/transformers';

// Load model, processor, and tokenizer
const model_id = 'onnx-community/Florence-2-base';
const model = await Florence2ForConditionalGeneration.from_pretrained(model_id, { dtype: 'fp32' });
const processor = await AutoProcessor.from_pretrained(model_id);

// Load image and prepare vision inputs
const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg';
const image = await load_image(url);

// Specify task and prepare text inputs
const task = '<MORE_DETAILED_CAPTION>';
const prompts = processor.construct_prompts(task);

// Pre-process the image and text inputs
const inputs = await processor(image, prompts);

// Generate text
const generated_ids = await model.generate({
    ...inputs,
    max_new_tokens: 100,
});

// Decode generated text
const generated_text = processor.batch_decode(generated_ids, { skip_special_tokens: false })[0];

// Post-process the generated text
const result = processor.post_process_generation(generated_text, task, image.size);
console.log(result);
// { '<MORE_DETAILED_CAPTION>': 'The image shows a vintage Volkswagen Beetle car parked on a cobblestone street in front of a yellow building with two wooden doors. The car is a light green color with silver rims and appears to be in good condition. The building has a sloping roof and is painted in a combination of yellow and beige colors. The sky is blue and there are trees in the background. The overall mood of the image is peaceful and serene.' }