Abstract
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 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 256times256, 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.
Community
What target should a pixel flow model predict? Data, velocity, or something else? AnisoFlow makes the target fully learnable and interpretable. This improves JiT from 1.90 to 1.55 FID on ImageNet with no REPA, and removes patch artifacts in pixel T2I models.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Rethinking the design space of Vanilla Pixel Diffusion Transformers (2026)
- What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching (2026)
- Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models (2026)
- Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers (2026)
- Just Align $\bm{x}$: Aligning Predictions, Not Representations (2026)
- Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching (2026)
- Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.17767 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper