from fastapi import FastAPI, UploadFile, File
from fastapi.responses import HTMLResponse
from PIL import Image
import io
import torch
from transformers import BlipProcessor, BlipForConditionalGeneration
app = FastAPI()
# Load BLIP model & processor
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
@app.get("/", response_class=HTMLResponse)
async def main():
return """
Smart Image Captioning
🧠 Smart Image Captioning
"""
@app.post("/caption", response_class=HTMLResponse)
async def caption(file: UploadFile = File(...)):
contents = await file.read()
image = Image.open(io.BytesIO(contents)).convert('RGB')
# Generate caption
inputs = processor(images=image, return_tensors="pt")
out = model.generate(**inputs)
caption = processor.decode(out[0], skip_special_tokens=True)
return f"""
Caption Result
"""