Small decisions. Interesting possibilities.Submit contentSubmit

How it uses Jev

A prompt and selected representation/grid settings are converted in the browser into batched Jev questions about palette, HSL, RGB, or silhouette values. The browser combines returned probabilities and samples them into a rendered painting; a local Python helper forwards API requests because the endpoint does not allow browser CORS.

What Jev decides

Illustrative Jev requestExample answers · not a recorded Jev response · Source ↗
Question 1 · x0 y0
YOUR APP
INSTRUCTION

Is pixel (x=0, y=0) inside the foreground silhouette described in state?

STATE

Image description, grid size, pixel (0,0) and silhouette task.

JEV · NOUL
YesNo

App workflow

  1. Set up a canvas request

    The user enters a prompt, chooses a representation and grid size, and starts a painting in the browser.

  2. Ask in batches

    Browser code constructs and batches the representation-specific questions and sends them through the loopback helper to Jev.

  3. Transform probabilities

    The browser combines channel probabilities where needed and uses spatially correlated sampling, mean color, and entropy to derive pigments and relief.

  4. Render and retain

    A module worker computes the image and adds it to the in-memory carousel; reloading clears paintings.

Why it is interesting

It treats Jev probability distributions as generative material: spatial sampling, entropy, contours, and lighting turn typed pixel-level outputs into textured artwork rather than a conventional answer display.