Diffusion Model

Tap it: the noise clears, step by step, into a rubber duck.

A diffusion model makes pictures out of noise. It is trained by taking real pictures, adding random noise to them a little at a time until only specks are left, and learning to undo each step. To make a new picture, it starts from pure noise and takes a little away at each of many steps, until a clear picture appears.

Tap it: a cloud of random specks clears in ten steps into a rubber duck while the STEP counter runs down from 50 to 0, then the noise washes back over it. Pick the poster or a 3D model in the Splash tab.

The About text describes the broad idea of learning to reverse a noise process. The splash morphs a fixed noise cloud into a known duck in ten stages; its 50-to-0 counter is a visual scale, not 50 calculated denoising steps.

1. Correct

   Diffusion generation uses a learned reverse noise process.¹

   The About text gives an introductory description of adding noise for training and reversing it to generate a picture.

2. Simplified

   The splash has ten visual stages while the counter goes from 50 to 0.¹

   The stage helper selects ten morph values and the actual display reports 50 minus five times the stage.

3. Simplified

   The clearing duck is a prepared illustration of generation.¹

   The morph blends fixed particle positions toward a known duck. No model predicts the noise to remove.

1. Denoising Diffusion Probabilistic Models, Ho, Jain, and Abbeel, 2020

Simplified

The duck is supplied in advance and there is no denoising network, training objective, or sampled reverse process. Ten visual stages decrease the counter by five each time.

Made in Splashery. Its code is MIT.

This link opens it in the Playground. To put it on your own page, add the element and one script tag. Every option.

https://splashery.app/play/?toy=diffusion-model

<script type="module" src="https://splashery.app/play/src/element.js"></script>
<splashery-toy toy="diffusion-model"></splashery-toy>