Algomancer / Minimal-Drifting-ModelsView on GitHub
A minimal implementation of Drifting Models for 2D toy data. Unlike diffusion/flow models that iterate at inference, drifting models evolve the pushforward distribution during training and generate in a single forward pass (1-NFE). The drifting field V governs sample movement: V -> 0 as generated matches data.
63Feb 13, 2026Updated 2 weeks ago

Alternatives and similar repositories for Minimal-Drifting-Models

Users that are interested in Minimal-Drifting-Models are comparing it to the libraries listed below

Sorting:

Are these results useful?