字生 / In your browser

A character, from noise.

Pick a character. Watch the model work from fresh noise.

Your browser needs canvas support to show the generated character.Your next character
starts here.
永 · everlasting48 × 48

New seed on every Generate, unless locked. The model and inference engine load once, on your device.

Ready when you are

Generate a new sample, or inspect a recorded model run.

What’s running?

The original 880,385-parameter conditional U-Net and the repository’s 1,000-step DDPM update, with fresh Gaussian noise at each reverse step. The timeline records 101 actual states, including the starting noise. The first steps can still look noisy; recognizable structure often arrives later.

The faster DDIM options use the same weights but take a different, deterministic sampling path. Browser and PyTorch random-number generators differ, so the same numeric seed does not produce identical pixels across implementations.

These are synthetic printed-glyph samples from a 12-character pilot, not handwriting or pen-stroke paths. Recognition accuracy and unseen-font performance have not been measured.

Project source ↗ · Model provenance ↗