ClemSummer's picture
UI Enhancements
f66e5e6
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<title>πŸ€– Image πŸ–ΌοΈ Captioning</title>
<meta name="viewport" content="width=device-width, initial-scale=1">
<!-- βœ… Tailwind CDN -->
<script src="https://cdn.tailwindcss.com"></script>
</head>
<body class="bg-gray-100 flex items-center justify-center min-h-screen">
<a href="/" class="absolute top-4 left-4 text-blue-600 hover:text-blue-800 text-sm font-semibold flex items-center">
<!-- back arrow -->
<svg class="w-5 h-5 mr-1" fill="none" stroke="currentColor" stroke-width="2" viewBox="0 0 24 24"
xmlns="http://www.w3.org/2000/svg">
<path stroke-linecap="round" stroke-linejoin="round" d="M15 19l-7-7 7-7"></path>
</svg>
Back to Home
</a>
<div class="bg-white p-8 rounded-xl shadow-md w-full max-w-md text-center">
<h1 class="text-2xl font-bold mb-4 text-gray-800">AI Image Captioning</h1>
<!-- Upload Form -->
<form id="uploadForm" class="space-y-4">
<input
type="file"
id="fileInput"
accept="image/*"
required
class="block w-full text-sm text-gray-700 file:mr-4 file:py-2 file:px-4 file:rounded-full file:border-0 file:text-sm file:font-semibold file:bg-blue-50 file:text-blue-700 hover:file:bg-blue-100"
/>
<!-- Live Image Preview -->
<div id="previewContainer" class="mt-4 hidden">
<img id="previewImage" src="#" alt="Preview" class="mx-auto max-h-64 rounded-md shadow" />
</div>
<button
id="generateButton"
type="submit"
class="w-full bg-blue-600 hover:bg-blue-700 text-white font-semibold py-2 px-4 rounded-lg transition"
>
Generate Captions
</button>
</form>
<!-- Captions -->
<div id="result" class="mt-6 text-left hidden">
<h2 class="text-lg font-semibold mb-2 text-gray-700">Captions:</h2>
<p><strong>Factual πŸ€–:</strong> <span id="greedy" class="text-gray-800"></span></p>
<p><strong>Creative πŸ€ͺ:</strong> <span id="topk" class="text-gray-800"></span></p>
<p><strong>Human like πŸ«€:</strong> <span id="topp" class="text-gray-800"></span></p>
</div>
</div>
<script>
const fileInput = document.getElementById('fileInput');
const previewContainer = document.getElementById('previewContainer');
const previewImage = document.getElementById('previewImage');
const form = document.getElementById('uploadForm');
const result = document.getElementById('result');
const generateButton = document.getElementById('generateButton');
// βœ… Live preview + clear old captions
fileInput.addEventListener('change', () => {
const file = fileInput.files[0];
if (file) {
const reader = new FileReader();
reader.onload = e => {
previewImage.src = e.target.result;
previewContainer.classList.remove('hidden');
};
reader.readAsDataURL(file);
// Clear old captions
document.getElementById('greedy').innerText = "";
document.getElementById('topk').innerText = "";
document.getElementById('topp').innerText = "";
result.classList.add('hidden');
} else {
previewContainer.classList.add('hidden');
}
});
// βœ… Submit form
form.addEventListener('submit', async e => {
e.preventDefault();
// Disable button while generating
generateButton.disabled = true;
generateButton.innerText = "Generating...";
const file = fileInput.files[0];
const formData = new FormData();
formData.append('file', file);
try {
const res = await fetch('/generate', {
method: 'POST',
body: formData
});
const data = await res.json();
document.getElementById('greedy').innerText = data.greedy || "N/A";
document.getElementById('topk').innerText = data.topk || "N/A";
document.getElementById('topp').innerText = data.topp || "N/A";
result.classList.remove('hidden');
} catch (error) {
alert("⚠️ Error generating captions. Please try again.");
} finally {
// Re-enable button with new text
generateButton.disabled = false;
generateButton.innerText = "Generate Captions (can repeat)";
}
});
</script>
<!-- Floating Help Button -->
<button id="helpButton"
class="fixed bottom-4 right-4 bg-blue-600 text-white rounded-full w-12 h-12 text-2xl font-bold shadow-lg hover:bg-blue-700 transition">
?
</button>
<!-- Help Modal -->
<div id="helpModal" class="fixed inset-0 bg-black bg-opacity-50 flex items-center justify-center hidden">
<div class="bg-white rounded-lg p-6 max-w-sm w-full shadow-lg text-left">
<h2 class="text-xl font-semibold mb-4">πŸ€– Image Captioning</h2>
<p class="text-gray-700 mb-4">
Please upload a picture / image and press "Generate Captions", the model will generate captions for it.
The model uses google/vit-base-patch16-224-in21k or openai/clip-vit-base-patch32
as image encoder, trained together with a customer transformer decoder to generate captions.<br>
The available caption styles are: "Factual πŸ€–", "Creative πŸ€ͺ", and "Human like πŸ«€",
which are actually argmax (greedy), top-K and top-P respectively.
</p>
<button id="closeModal"
class="mt-2 bg-blue-600 text-white px-4 py-2 rounded hover:bg-blue-700">
Close
</button>
</div>
</div>
<script>
const helpButton = document.getElementById('helpButton');
const helpModal = document.getElementById('helpModal');
const closeModal = document.getElementById('closeModal');
helpButton.addEventListener('click', () => {
helpModal.classList.remove('hidden');
});
closeModal.addEventListener('click', () => {
helpModal.classList.add('hidden');
});
// Optional: close modal when clicking outside the modal box
helpModal.addEventListener('click', (e) => {
if (e.target === helpModal) {
helpModal.classList.add('hidden');
}
});
</script>
</body>
</html>