Spaces:
Sleeping
Sleeping
File size: 3,844 Bytes
c37e02d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | 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 """
<html>
<head>
<title>Smart Image Captioning</title>
<style>
body {
font-family: 'Segoe UI', sans-serif;
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
min-height: 100vh;
background-color: #f3f4f6;
margin: 0;
}
h2 {
color: #111827;
margin-bottom: 1rem;
}
form {
background: white;
padding: 2rem;
border-radius: 12px;
box-shadow: 0 8px 24px rgba(0,0,0,0.1);
}
input[type="file"] {
margin-bottom: 1rem;
}
input[type="submit"] {
padding: 0.5rem 1.2rem;
font-size: 1rem;
background-color: #2563eb;
color: white;
border: none;
border-radius: 6px;
cursor: pointer;
}
input[type="submit"]:hover {
background-color: #1d4ed8;
}
</style>
</head>
<body>
<h2>🧠 Smart Image Captioning</h2>
<form action="/caption" enctype="multipart/form-data" method="post">
<input name="file" type="file" accept="image/*" required><br>
<input type="submit" value="Generate Caption">
</form>
</body>
</html>
"""
@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"""
<html>
<head>
<title>Caption Result</title>
<style>
body {{
font-family: 'Segoe UI', sans-serif;
background-color: #f9fafb;
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
min-height: 100vh;
padding: 2rem;
}}
.box {{
background: white;
padding: 2rem;
border-radius: 12px;
box-shadow: 0 8px 20px rgba(0,0,0,0.1);
text-align: center;
}}
.caption {{
font-size: 1.25rem;
color: #1f2937;
margin-top: 1rem;
}}
a {{
display: inline-block;
margin-top: 1.5rem;
color: #2563eb;
text-decoration: none;
font-weight: bold;
}}
a:hover {{
text-decoration: underline;
}}
</style>
</head>
<body>
<div class="box">
<h2>🖼️ Image Caption Result</h2>
<p><b>File:</b> {file.filename}</p>
<p class="caption"><b>Caption:</b> {caption}</p>
<a href="/">🔁 Try another image</a>
</div>
</body>
</html>
"""
|