Home/ Tool index/ Human Diffusion Canvas
Launch ready Session 2 · Images Whole-class activity

Human Diffusion Canvas

Everyone becomes the denoiser. The facilitator says the words, noise sits on every canvas, and the class draws in timed steps — biggest shapes first, details last, a veil of noise thinning between rounds on a fixed schedule. Each drawing exports as a PNG and as a step-by-step trajectory GIF.

tools/human-diffusion-canvas/
noise → shapes → forms → details one color per step · the veil thins on schedule · no undo across steps

Live preview · launch for the interactive version

§ A · What it makes visible

the denoising schedule
Fig. 01

Coarse before fine

The brush shrinks every step, forcing a coarse-to-fine drawing trajectory. That echoes a common denoising pattern without claiming every model follows this exact order.

Fig. 02

The schedule

A noise-remaining meter drops by the same fraction at every commit. Between steps, a veil of noise falls — thick early, thin late, gone after the last step.

Fig. 03

Commitment

Undo works only inside the current activity step so the trajectory stays visible. A sampler moves forward through timesteps, while later updates can still revise structure in its current representation.

§ B · How to run it

one prompt, whole class
01 · Share the setup

One link, same start

Pick step count and noise, type the words, press Copy setup link, paste it in chat. Everyone opens the same conditioning.

"a cat asleep on a red chair" · 4 steps · from noise
02 · Draw in steps

Timed, coarse to fine

About a minute per step. Step 1 is big shapes only — "find them in the noise." Commit together and watch the veil fall.

step 1: fat brush · step 4: 5px accents
03 · Export trajectories

PNG + GIF, on-device

Each participant exports the finished image and the animated trajectory. Nothing uploads; sharing is a consent decision.

human-diffusion-a-cat-asleep.gif
04 · Compare with the machine

Compare analogous trajectories

Tile the GIFs on the Evidence Wall, then open the Diffusion Step-Through Viewer. The human drawing and machine denoising make different kinds of iterative change visible.

your steps: minutes · its steps: milliseconds

§ C · Debrief questions

after the drawing
What did you commit to in step 1 that you could never take back?
Where did the words decide, and where did you decide?
Everyone heard the same words — why does the wall show different images?
You knew what you were drawing. What does the model have instead of knowing?