cs.CVNov 13, 2026

Learning Anisotropic Prediction Targets for Flow Models

Authors: Rayhan Zirvi, Hansheng Chen, Gordon Wetzstein, Leonidas Guibas

Organizations: Stanford University · California Institute of Technology

Abstract

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 network to predict. We theoretically analyze the resulting prediction error and predict that the preferred noise weight in each direction scales near-linearly with data variance, in agreement with the weights learned empirically in pixel space. AnisoFlow improves FID from 1.90 to 1.55 over the JiT baseline on ImageNet 256×\times256, by learning only the prediction target, without representation alignment or architectural changes. In pixel-space text-to-image generation, AnisoFlow improves image quality and, through better-conditioned velocity recovery, largely removes patch-seam artifacts under reduced-precision inference.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Asymmetric Flow Models

    May 13, 2026Hansheng Chen, Jan Ackermann, Minseo Kim +2Flow MatchingT2I Generation

  2. Dino Forcing Flow Models: Do not denoise what you can predict

    Oct 8, 2026Arijit Ghosh, Lucas Degeorge, Paul Couairon +3Self-ConditioningFlow-Based Generative Modeling

  3. Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models

    Jul 13, 2026Xu Han, Jiajing Hu, Li-Ping LiuRectified FlowImage Generation