import gradio as gr
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def generate_caption(image):
    inputs = processor(images=image, return_tensors="pt")
    out = model.generate(**inputs)
    caption = processor.decode(out[0], skip_special_tokens=True)
    return caption

gr.Interface(fn=generate_caption,
             inputs=gr.Image(type="pil"),
             outputs="text",
             title="画像キャプション生成",
             description="アップロードされた画像に対してキャプションを自動生成します"
             ).launch()