Asymmetric Flow Models

• URL: http://arxiv.org/abs/2605.12964v1
• Date: Wed, 13 May 2026 03:58:01 GMT
• Title: Asymmetric Flow Models
• Abstract summary: We present a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional.<n>AsymFlow analytically recovers the full-dimensional velocity without changing the network architecture or training/sampling procedures.<n>We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation.
• Score: 35.8386911591457
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow-based generation in high-dimensional spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. From this asymmetric prediction, AsymFlow analytically recovers the full-dimensional velocity without changing the network architecture or training/sampling procedures. On ImageNet 256$\times$256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin. AsymFlow also provides the first-ever route for finetuning pretrained latent flow models into pixel-space models: aligning the low-rank pixel subspace to the latent space gives a seamless initialization that preserves the latent model's high-level semantics and structure, so finetuning mainly improves low-level mismatches rather than relearning pixel generation. We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation, beating its latent base on HPSv3, DPG-Bench, and GenEval while qualitatively showing substantially improved visual realism.

Related papers

• XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling [24.78695434475162]
  XYZFlow is a framework that rethinks efficient generation through multidimensional scaling of flow matching.<n>Next Shortcut Prediction delivers superior quality-latency trade-offs over model scaling or step reduction.
  arXiv  Detail & Related papers  (2026-08-12T17:15:42Z)
• MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation [29.57000468788334]
  Masked Image Modeling (MIM) has excelled in representation learning, but its integration into generative pipelines has remained largely modular and disjointed.<n>We propose MIMFlow, a unified end-to-end framework that jointly optimize latent semantics, pixel reconstruction, and generative flow.
  arXiv  Detail & Related papers  (2026-06-24T16:37:10Z)
• SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation [73.51436199324066]
  Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have lagged behind diffusion models for large-scale image generation.<n>We propose SRC-Flow, which introduces a Semantic Representation (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space.<n>SRC-Flow achieves state-of-the-art generation quality among flow methods, with gFID scores of 1.65 and 2.07 under computation-free guidance.
  arXiv  Detail & Related papers  (2026-05-18T12:03:41Z)
• Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows [4.719615308536812]
  Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image.<n>We propose Point-MF, a Mean-Flow-based framework for low-NFE single-image point cloud reconstruction.
  arXiv  Detail & Related papers  (2026-04-27T15:10:47Z)
• One-step Latent-free Image Generation with Pixel Mean Flows [22.294629970410508]
  We propose "pixel MeanFlow" (pMF) to formulate the network output space and the loss space separately.<n>pMF achieves strong results for one-step latent-free generation on ImageNet at 256x256 resolution (2.22 FID) and 512x512 resolution (2.48 FID)
  arXiv  Detail & Related papers  (2026-01-29T18:59:56Z)
• Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling [68.76215229126886]
  We introduce Decoupled MeanFlow, a simple decoding strategy that converts flow models into flow map models without architectural modifications.<n>Our method conditions the final blocks of diffusion transformers on the subsequent timestep, allowing pretrained flow models to be directly repurposed as flow maps.<n>On ImageNet 256x256 and 512x512, our models attain 1-step FID of 2.16 and 2.12, respectively, surpassing prior art by a large margin.
  arXiv  Detail & Related papers  (2025-10-28T14:43:48Z)
• FARMER: Flow AutoRegressive Transformer over Pixels [39.864972164994946]
  We present a novel end-to-end generative framework that unifies Normalizing Flows (NF) and Autoregressive (AR) models.<n> FARMER employs an invertible autoregressive flow to transform images into latent sequences, whose distribution is modeled implicitly by an autoregressive model.<n>We show that FARMER achieves competitive performance compared to existing pixel-based generative models.
  arXiv  Detail & Related papers  (2025-10-27T17:54:08Z)
• STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis [44.2114053357308]
  We present a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis.<n>The core of STARFlow is Transformer Autoregressive Flow (TARFlow), which combines the expressive power of normalizing flows with the structured modeling capabilities of Autoregressive Transformers.
  arXiv  Detail & Related papers  (2025-06-06T17:58:39Z)
• FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems [51.15230303652732]
  FLEX (F Low EXpert) is a backbone architecture for generative modeling of-temporal physical systems.<n>It reduces the variance of the velocity field in the diffusion model, which helps stabilize training.<n>It achieves accurate predictions for super-resolution and forecasting tasks using as few features as two reverse diffusion steps.
  arXiv  Detail & Related papers  (2025-05-23T00:07:59Z)
• Mean Flows for One-step Generative Modeling [64.4997821467102]
  We propose a principled and effective framework for one-step generative modeling.<n>A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training.<n>Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning.
  arXiv  Detail & Related papers  (2025-05-19T17:59:42Z)
• Gaussian Mixture Flow Matching Models [63.092956669059824]
  Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models re parameterize the Gaussian mean as flow velocity.<n>They underperform in few-step sampling due to discretization error and tend to produce over-saturated colors under classifier-free guidance (CFG)<n>We introduce a novel probabilistic guidance scheme that mitigates the over-saturation issues of CFG and improves image generation quality.
  arXiv  Detail & Related papers  (2025-04-07T17:59:42Z)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.