Session 2 · Images · Diffusion, embodied

Human Diffusion Canvas

You are the denoiser. The words arrive, noise sits on the canvas, and step by step you commit what you're sure of — biggest shapes first, details last, a veil of noise thinning between rounds. When you finish, export the GIF and compare your trajectory with the machine's.

Big idea: diffusion iteratively revises a noisy representation under prompt guidance. This activity uses locked, coarse-to-fine rounds to make one trajectory discussable.

1 · The words (the prompt)

The model hears its words at every step. Keep yours in view the whole time.

2 · The step schedule

Noise remaining100%

    3 · Brush — it shrinks every step

    30px

    Coarse steps get fat brushes and fine steps get thin ones. That is this activity's constraint, echoing a common denoising pattern rather than a rule every model follows.

    4 · Round timer (optional)

    No timer — the facilitator calls time.

    5 · Commit

    Undo works inside the current activity step. Locked rounds preserve your trajectory; unlike this activity, later model updates can still revise structure in the current representation.

    6 · Export

    Everything is built on this device — nothing uploads. Share only what you consent to share.

    The canvas · 512 × 512 — the square many diffusion models denoise

    Keyboard: focus the canvas, use arrow keys to move the cursor, hold Shift while moving to draw, press Space or Enter for a dot, and press Home to recenter.

    How a round works

    1. Type the words. The facilitator says them; they're your conditioning.
    2. Draw what you're sure of. Fat brush, biggest shapes. Find them in the noise.
    3. Commit. A veil of noise falls over everything — thinner each time.
    4. Repeat, finer each round. After the last step there's no veil left. Export.

    Setup — facilitator

    Steps:
    Start from:

    The link carries the words, step count, and noise setting — paste it in chat and everyone starts from the same setup. Changing setup restarts the canvas.

    What just happened — the map to real diffusion

    You, drawingA diffusion model
    Starts fromA field of random noiseA field of random noise (in latent space)
    The wordsSaid aloud, held in your head every roundThe prompt, encoded once and applied at every step
    One stepCommit marks so this activity preserves a trajectoryPredict an update to the current noisy representation
    Between stepsA veil — the noise not yet resolvedResidual noise, on a fixed schedule
    Order of workA forced coarse-to-fine drawing sequenceCoarse structure often stabilizes before fine detail
    Knows what it's makingYes — you have the ideaNo — it has statistics about images-with-these-words

    Where the analogy breaks — say this part out loud

    You add. It removes.

    You put marks onto the canvas. A diffusion model updates many values in its current image representation in parallel — often latent values rather than final pixels.

    You mean. It matches.

    You know what a cat is and want to draw one. The model has no idea and no wanting — only learned statistics about which pixel patterns co-occur with the words "a cat".

    Your steps cost a minute. Its steps cost milliseconds.

    You'll take 3–5 steps of a minute each. A model usually follows a longer automated noise schedule; the exact step count and speed vary by model and sampler.

    Classroom run of show

    1. Set up once, share the link. Pick the step count, type the words, press Copy setup link, paste it in chat.
    2. Say the words. Everyone types them. Same words for the whole run — that's the conditioning.
    3. Step 1, about 60 seconds. Fat brush. Biggest shapes only. "Find them in the noise."
    4. Commit together. The veil falls. Point at the noise-remaining meter — it just dropped, on schedule.
    5. Repeat, finer each round. Brushes shrink automatically. The last step gets no veil.
    6. Export GIFs and regroup. Paste them into the Evidence Wall, watch a wall of human denoising trajectories — then open the Diffusion Step-Through Viewer and watch the machine run the same shape of process.

    Field note