SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

Yexiong Lin; Jia Shi; Shanshan Ye; Wanyu Wang; Yu Yao; Tongliang Liu

cs.LGApr 14, 2026

SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

Authors: Yexiong Lin, Jia Shi, Shanshan Ye, Wanyu Wang, Yu Yao, Tongliang Liu

Organizations: Sydney AI Centre, The University of Sydney, Sydney, NSW, Australia · School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China · Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia · Department of Information Systems, City University of Hong Kong, Hong Kong, China

Abstract

Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity degradation, concentrating samples on dominant modes while neglecting rare but valid variations of the target distribution. We trace this degradation to averaging distortion: when trained with MSE objectives, class-conditional flows learn a frequency-weighted mean over intra-class sub-modes, causing the model to over-represent high-density modes while systematically neglecting low-density ones. To address this, we propose SubFlow, Sub-mode Conditioned Flow Matching, which eliminates averaging distortion by decomposing each class into fine-grained sub-modes via semantic clustering and conditioning the flow on sub-mode indices. Each conditioned sub-distribution is approximately unimodal, so the learned flow accurately targets individual modes with no averaging distortion, restoring full mode coverage in a single inference step. Crucially, SubFlow is entirely plug-and-play: it integrates seamlessly into existing one-step models such as MeanFlow and Shortcut Models without any architectural modifications. Extensive experiments on ImageNet-256 demonstrate that SubFlow yields substantial gains in generation diversity (Recall) while maintaining competitive image quality (FID), confirming its broad applicability across different one-step generation frameworks. Project page: https://yexionglin.github.io/subflow.

Figures & tables

Panel of Figure 1 — Figure 1. Toy experiment on a 4-peak Gaussian mixture target with imbalanced subclusters (majority weight 0.35, minority weight 0.15 per class). (a) Traditional flow matching (100 inference steps) covers all modes. (b) MeanFlow suffers from severe mode collapse, concentrating only on dominant subclusters and losing diversity. (c) In contrast, our SubFlow successfully restores full mode coverage in a single step by decomposing each class into fine-grained sub-modes and conditioning the flow on sub-mode indices.

Figure 2. Overview of SubFlow. (a) Offline pre-processing : semantic features are extracted from the training images and clustered within each class, yielding sub-mode assignments $\{k_{i}\}$ and empirical priors $p(k\mid c)$ . (b) Training : the vector field $v_{\theta}(x_{t},t,c,k)$ is optimized with the SubFlow objective. For classifier-free guidance, only the class label $c$ is randomly dropped, while the sub-mode index $k$ is always retained. (c) Inference : given a target class $c$ , a sub-mode index $k$ is sampled from $p(k\mid c)$ , and the conditioned vector field generates a sample associated with the selected sub-mode.

Method	Param	Epoch	NFE	FID $\downarrow$	Precision (%)	Recall (%)
GANs
BigGAN ( Brock et al., 2019 ) [ICLR’19]	112M	-	1	7.70	82.17	27.67
StyleGAN-XL ( Sauer et al., 2022 ) [SIGGRAPH’22]	166M	500	1	2.30	71.93	48.71
GigaGAN ( Kang et al., 2023 ) [CVPR’23]	569M	128	1	3.45	75.57	48.36
Multi-step Diffusion/Flows
ADM ( Dhariwal and Nichol, 2021 ) [NeurIPS’21]	554M	400	250	4.59	82	52

Table 1. Class-conditional ImageNet-256 generation results. NFE denotes the number of function evaluations (sampling steps). Results in the Multi-step Diffusion/Flows section are cited from ( Zheng et al., 2026b ) , and all other results are evaluated using officially released checkpoints. SubFlow consistently improves Recall (diversity) when integrated into different one-step baselines, while maintaining competitive FID and Precision.

Figure 3. Qualitative comparison between MeanFlow (left) and MeanFlow with SubFlow (right) on ImageNet-256. Each row shows five samples from the same class. Green boxes highlight samples where SubFlow produces visibly higher image quality with sharper details and fewer artifacts.

Method	NFE	FID $\downarrow$	Precision (%)	Recall (%)
MeanFlow	1	6.17	70.35	43.45
MeanFlow	2	5.46	80.82	38.91
MeanFlow	4	5.54	82.86	37.59
MeanFlow	8	5.58	83.35	37.62
MeanFlow	16	5.60	83.27	37.83
MeanFlow	32	5.64	83.12	38.16

Table 2. Effect of the number of sampling steps (NFE) on MeanFlow-B/2 with and without SubFlow (

K{=}5

). Multi-step integration could improve FID but Recall slightly decreases, confirming that reduced discretization error amplifies rather than corrects the dominant-mode bias. SubFlow provides consistent Recall gains at all step counts.

Figure 4. Diverse generation from the same noise $x_{0}$ . First column: MeanFlow output. Columns 2–6: MeanFlow+SubFlow with different sub-mode indices $k$ .

Panel of Figure 5 — Figure 5. Sensitivity analysis for the number of sub-modes $K$ . Dashed lines indicate the baseline without SubFlow. Recall improves steadily with moderate $K$ , while Precision remains stable and FID stays competitive across a broad range.

Strategy	FID $\downarrow$	Prec.(%)	Recall(%)
Baseline (no SubFlow)	18.70	55.23	43.51
Random sub-mode assignment	18.80	55.45	43.92
Uniform sampling	20.00	52.86	48.22
SubFlow	18.49	54.21	46.54

Table 3. Ablation on sub-mode clustering and sampling strategy (MeanFlow, DiT-B/4, 80 epochs,

K{=}5

). SubFlow (

K

-Means clustering and prior-based sampling

p(k\mid c)

) achieves a better quality–diversity trade-off than random sub-mode assignment and uniform sampling.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Clustering Algorithm	FID $\downarrow$	Prec.(%)	Recall(%)
Baseline (no SubFlow)	18.70	55.23	43.51
DBSCAN	19.49	54.65	44.67
$K$ -Means (SubFlow)	18.49	54.21	46.54

Appendix

Table 4. Comparison of clustering algorithms for sub-mode discovery (MeanFlow, DiT-B/4, 80 epochs).

K

-Means yields better FID and comparable Recall, suggesting that evenly partitioned sub-modes are more effective for flow matching conditioning.

Strategy	FID $\downarrow$	Prec.(%)	Recall(%)
Baseline (no SubFlow)	18.70	55.23	43.51
SubFlow (drop both $c$ and $k$ )	18.59	54.79	46.25
SubFlow (drop $c$ only)	18.49	54.21	46.54

Appendix

Table 5. Effect of dropping the sub-mode index

k

during CFG training (MeanFlow, DiT-B/4, 80 epochs,

K{=}5

). Both

c

and

k

are dropped independently with the same probability. Dropping

c

only (our default) achieves the best overall trade-off.

Panel of Figure 6 — Figure 6. t-SNE visualization of DINOv3 features for ImageNet classes at opposite ends of the HDBSCAN clustering spectrum. Classes in (a) are well served by standard class conditioning, while classes in (b) suffer from averaging distortion that SubFlow’s sub-mode conditioning resolves.

Explore similar work

Frequency-Aware Flow Matching for High-Quality Image Generation
Apr 16, 2026Sucheng Ren, Qihang Yu, Ju He +3Flow Matching Conditional Image Generation
Johns Hopkins University · ByteDance
Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
Oct 2, 2026Divya Jyoti Bajpai, Arun Verma, Manjesh Kumar HanawalEfficient Inference Flow Matching
Department of IEOR IIT Bombay, Mumbai, India · SMART Centre Singapore
Perceptual Flow Matching for Few-Step Generative Modeling
Jul 3, 2026Chuyang Zhao, Yifei Song, Hongfa Wang +7Flow Matching Perceptual Loss
1Joy Future Academy · 2Fudan University · 3Tsinghua University +1

Apr 16, 2026J/K move · Enter open · S save

Frequency-Aware Flow Matching for High-Quality Image Generation

Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen+2

Johns Hopkins University · ByteDance

Flow Matching Conditional Image Generation Image Generation Flow-Based Generative Modeling

Open paper AskPDF arXiv

Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However, because noise is injected in the latent domain, its impact on different frequency components is non-uniform. As a result, during inference, flow matching models tend to generate low-frequency components (global structure) in the early stages, while high-frequency components (fine details) emerge only later in the reverse process. Building on this insight, we propose Frequency-Aware Flow Matching (FreqFlow), a novel approach that explicitly incorporates frequency-aware conditioning into the flow matching framework via time-dependent adaptive weighting. We introduce a two-branch architecture: (1) a frequency branch that separately processes low- and high-frequency components to capture global structure and refine textures and edges, and (2) a spatial branch that synthesizes images in the latent domain, guided by the frequency branch's output. By explicitly integrating frequency information into the generation process, FreqFlow ensures that both large-scale coherence and fine-grained details are effectively modeled low-frequency conditioning reinforces global structure, while high-frequency conditioning enhances texture fidelity and detail sharpness. On the class-conditional ImageNet-256 generation benchmark, our method achieves state-of-the-art performance with an FID of 1.38, surpassing the prior diffusion model DiT and flow matching model SiT by 0.79 and 0.58 FID, respectively. Code is available at https://github.com/OliverRensu/FreqFlow.

Abstract

Explore similar work

Frequency-Aware Flow Matching for High-Quality Image Generation

Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation

Perceptual Flow Matching for Few-Step Generative Modeling