pocket-diffusion / index.html
ARotting's picture
Publish Interactive classifier-free guided digit diffusion
0213535 verified
Raw
History Blame Contribute Delete
6.84 kB
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<title>Pocket Diffusion</title>
<style>
:root { color-scheme: dark; font-family: Inter, ui-sans-serif, system-ui; }
* { box-sizing: border-box; }
body { margin: 0; min-height: 100vh; background: #060817; color: #edf4ff; }
canvas { position: fixed; inset: 0; width: 100%; height: 100%; opacity: .55; }
main { position: relative; z-index: 1; width: min(1080px, 92vw); margin: auto;
padding: 72px 0 96px; }
.eyebrow { color: #73e6ff; letter-spacing: .18em; text-transform: uppercase;
font-size: .75rem; font-weight: 800; }
h1 { font-size: clamp(3rem, 8vw, 7rem); line-height: .9; margin: 14px 0 24px;
background: linear-gradient(120deg,#fff,#74e7ff 55%,#b48cff);
-webkit-background-clip: text; color: transparent; }
.lead { max-width: 760px; color: #b8c7e6; font-size: 1.2rem; line-height: 1.65; }
.actions { display: flex; flex-wrap: wrap; gap: 12px; margin: 30px 0 48px; }
a { color: inherit; }
.button { padding: 12px 18px; border-radius: 999px; text-decoration: none;
background: #eaf8ff; color: #07101c; font-weight: 800; }
.button.alt { background: #171d38cc; color: #dce8ff; border: 1px solid #415078; }
.grid { display: grid; grid-template-columns: 1.1fr .9fr; gap: 20px; }
.card { border: 1px solid #344269; background: #0c1128dd; border-radius: 24px;
padding: 24px; backdrop-filter: blur(18px); box-shadow: 0 24px 80px #0008; }
h2 { margin-top: 0; }
pre { white-space: pre-wrap; word-break: break-word; color: #a9bddf;
max-height: 520px; overflow: auto; }
ul { max-height: 520px; overflow: auto; padding-left: 1.2rem; color: #a9bddf; }
li { margin: 8px 0; }
input { width: 100%; padding: 12px; border-radius: 12px; border: 1px solid #344269;
background: #070b1a; color: white; margin-bottom: 12px; }
@media (max-width: 780px) { .grid { grid-template-columns: 1fr; } }
</style>
</head>
<body>
<canvas id="field"></canvas>
<main>
<div class="eyebrow">Jacob Garcia · Hugging Face Model Foundry</div>
<h1>Pocket Diffusion</h1>
<p class="lead">Interactive classifier-free guided digit diffusion. This showcase backs up the
trained artifacts, measured evaluation, and complete runnable source.</p>
<div class="actions">
<a class="button" href="https://huggingface.co/spaces/ARotting/pocket-diffusion/tree/main">Explore every file</a>
<a class="button alt" href="https://huggingface.co/ARotting">View the full foundry</a>
</div>
<div class="grid">
<section class="card">
<h2>Verified project card</h2>
<pre># PocketDiffusion
PocketDiffusion is a compact class-conditional denoising diffusion model for 8x8
handwritten digits. It learns to predict Gaussian noise over 50 diffusion steps and
uses classifier-free guidance during sampling.
The same frozen Tiny Vision classifier used for GlyphForge evaluates conditional
recognizability, making the VAE and diffusion results directly comparable under one
judge.
## Reproduce
```powershell
uv run python projects/tiny-vision-foundry/prepare_data.py
uv run python projects/pocket-diffusion/train.py
```
## Verified results
- Parameters: **55,608**
- Diffusion steps: **50**
- Training epochs: **300**
- Generated samples: **1,000**
- Selected classifier-free guidance: **3.0**
- Frozen-judge class fidelity: **96.20%**
Guidance search improved fidelity monotonically from 46.10% at `1.0` to 96.20% at
`3.0`. Per-class fidelity ranged from 83% for digit `8` to 100% for digits `0` and
`6`. Mean within-class pixel variance ranged from 0.0209 to 0.0456, noticeably higher
than the CVAE&#x27;s 0.0066 to 0.0168 range under the same 100-samples-per-class protocol.
</pre>
<h2>Evaluation snapshot</h2>
<pre>{
&quot;model&quot;: &quot;PocketDiffusion&quot;,
&quot;parameters&quot;: 55608,
&quot;diffusion_steps&quot;: 50,
&quot;epochs&quot;: 300,
&quot;guidance_search&quot;: {
&quot;1.0&quot;: 0.460999995470047,
&quot;1.5&quot;: 0.7149999737739563,
&quot;2.0&quot;: 0.8560000061988831,
&quot;2.5&quot;: 0.9359999895095825,
&quot;3.0&quot;: 0.9620000123977661
},
&quot;generation&quot;: {
&quot;judge_accuracy&quot;: 0.9620000123977661,
&quot;judge_accuracy_by_class&quot;: {
&quot;0&quot;: 1.0,
&quot;1&quot;: 0.9200000166893005,
&quot;2&quot;: 0.9900000095367432,
&quot;3&quot;: 0.9800000190734863,
&quot;4&quot;: 0.9599999785423279,
&quot;5&quot;: 0.9800000190734863,
&quot;6&quot;: 1.0,
&quot;7&quot;: 0.9900000095367432,
&quot;8&quot;: 0.8299999833106995,
&quot;9&quot;: 0.9700000286102295
},
&quot;mean_pixel_variance_by_class&quot;: {
&quot;0&quot;: 0.020940322428941727,
&quot;1&quot;: 0.03187673166394234,
&quot;2&quot;: 0.03836727514863014,
&quot;3&quot;: 0.03142565116286278,
&quot;4&quot;: 0.04158321022987366,
&quot;5&quot;: 0.034002821892499924,
&quot;6&quot;: 0.022990796715021133,
&quot;7&quot;: 0.036991652101278305,
&quot;8&quot;: 0.04558330774307251,
&quot;9&quot;: 0.03457583114504814
},
&quot;samples&quot;: 1000,
&quot;guidance&quot;: 3.0
},
&quot;judge&quot;: &quot;Tiny Vision labels-only student, 98.52% real-image test accuracy&quot;
}</pre>
</section>
<section class="card">
<h2>Backed-up artifact tree</h2>
<input id="filter" placeholder="Filter files…" autocomplete="off">
<ul id="files"><li><code>README.md</code></li>
<li><code>__pycache__/app.cpython-311.pyc</code></li>
<li><code>__pycache__/model.cpython-311.pyc</code></li>
<li><code>app.py</code></li>
<li><code>artifacts/pocket-diffusion/evaluation.json</code></li>
<li><code>artifacts/pocket-diffusion/model.safetensors</code></li>
<li><code>artifacts/pocket-diffusion/samples.png</code></li>
<li><code>model.py</code></li>
<li><code>requirements.txt</code></li>
<li><code>train.py</code></li></ul>
</section>
</div>
</main>
<script>
const canvas=document.querySelector('#field'),ctx=canvas.getContext('2d');
let dots=[];
function resize(){canvas.width=innerWidth;canvas.height=innerHeight;
dots=Array.from({length:90},()=>({x:Math.random()*innerWidth,
y:Math.random()*innerHeight,vx:(Math.random()-.5)*.35,vy:(Math.random()-.5)*.35}));}
function draw(){ctx.clearRect(0,0,canvas.width,canvas.height);
for(const d of dots){d.x=(d.x+d.vx+innerWidth)%innerWidth;
d.y=(d.y+d.vy+innerHeight)%innerHeight;ctx.fillStyle='#65dcff99';
ctx.beginPath();ctx.arc(d.x,d.y,1.4,0,7);ctx.fill();}requestAnimationFrame(draw);}
addEventListener('resize',resize);resize();draw();
document.querySelector('#filter').addEventListener('input',e=>{
const q=e.target.value.toLowerCase();for(const li of document.querySelectorAll('li'))
li.hidden=!li.textContent.toLowerCase().includes(q);});
</script>
</body>
</html>