Unifying Distributional Training for One-Step Visual Generation
A common gradient-flow view of distributional training. Gaussian mixtures capture multimodal feature distributions with a compact, adjustable representation.
W-Flow uses empirical measures and Sinkhorn divergence; Gaussian-kernel Drifting uses kernel-smoothed densities. MGFlow-W2 uses paired Gaussian transport costs, and MGFlow-KL uses paired component score fields.
Match the components, not just their local scores.
A more expressive density model alone does not ensure stable matching. Soft assignments can lose components, while global mixture scores can miss incorrect mass allocation between separated modes.
MGFlow constrains each component's batch mass with a linear program, updates its statistics, and matches corresponding reference and generated components. This pairing is used for both Gaussian transport and KL-based updates.
Component assignment and the choice of score field both matter. The toy experiment compares soft-assigned global, LP-assigned global, and LP-paired updates.
FDr6 averages normalized Fréchet distances across six encoders; FDr3 uses three held-out encoders. † Full-CFG NFE upper bound for interval CFG. Bold marks the best value within each backbone among the methods shown.
The one-step initialization is evaluated before MGFlow post-training. Joint matching uses image and SigLIP2 text features. PickScore uses 499 Pick-a-Pic prompts. Published baseline values follow AMFD, Table 3; — denotes an unreported value.
On ImageBench, MGFlow (4B) achieves an Overall score of 52.8 at 0.8 seconds per image with one-step generation. It lies on the observed quality–latency Pareto frontier among both all 81 published runs and the 42 locally evaluated models.
Hover or focus a model for details · click to view its evaluation
A run is on the frontier if no other visible run has lower or equal latency and higher or equal Overall, with at least one strict improvement. The dashed line connects observed frontier points.
Overall combines capability and estimated aesthetic preference equally. Latency is reported by ImageBench; local and API runs use different execution paths. Source leaderboard ↗ · Snapshot: 2026-10-28.
View the plotted data 81 entries
Model / evaluation route
Overall ↑
Capability ↑
EPS ↑
Latency ↓
Could not load the ImageBench data. Please reload the page.
04 / Models & data
Build on MGFlow.
Six ImageNet backbones, two objectives. Two text-to-image variants, training data, and references.
ImageNet
Post-trained JiT and pMF models at B, L, and H scales. MGFlow-W2 uses K = 1 + 4; MGFlow-KL uses K = 1 + 4 + 16.