typesafe-image-diffusion
Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes.
Diffusion-style pixel art out of a general classifier (TypeSafe Jev): 256 parallel pixel questions + refinement passes
How it uses Jev
Jev (via TypeSafe System One) is a judgment model. You give it state, ask multiple choice questions, and it picks answers with confidence scores. It classifies things. It does not draw things.
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.



