AnisoFlow learns an anisotropic, learnable prediction target for flow-based generative models, improving FID and image quality without altering the architecture or sampler.
Flow-based generative models are trained on a hand-chosen prediction target, such as the velocity, the noise, or the clean data. This choice strongly affects training and sample quality. We introduce Anisotropic Flow Models (AnisoFlow), which replaces a fixed prediction target with a fully learnable one. AnisoFlow learns to scale the noise component of the target anisotropically, assigning a separate nonnegative weight to each direction in a jointly learned basis. A closed-form map recovers the velocity from the network's prediction, leaving the architecture, flow-matching loss, and sampler unchanged. Since recovery is exact, training optimizes the target purely to make it easier for the…
flow-based generative modelsprediction targetvelocitynoise componentclean dataAnisotropic Flow ModelsAnisoFlowlearnable prediction targetanisotropic scalingnonnegative weight
- Upvotes
- 5
- Authors
- 4
- Published
- Nov 13, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.