app.py

from __future__ import annotations

import gradio as gr
import PIL.Image
import spaces
import torch
from transformers import AutoProcessor, BlipForConditionalGeneration

DESCRIPTION = "# Image Captioning with BLIP"

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

model_id = "Salesforce/blip-image-captioning-large"
processor = AutoProcessor.from_pretrained(model_id)
model = BlipForConditionalGeneration.from_pretrained(model_id).to(device)

max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}

def predict_caption(image_paths):
    images = []
    for image_path in image_paths:
        image = Image.open(image_path)
        if image.mode != "RGB":
            image = image.convert(mode="RGB")
        images.append(image)

    pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
    pixel_values = pixel_values.to(device)

    output_ids = model.generate(pixel_values, **gen_kwargs)

    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
    return preds