- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SharpEuler, a training-free timestep scheduler for pretrained flow matching models. The method estimates trajectory acceleration from offline velocity differences and converts the smoothed profile into a fixed Euler grid. The analysis motivates a square-root allocation, , through an Euler local-error objective. Experiments on synthetic distributions, FLUX.1-dev, and Pyramid Flow report improved low-budget sampling and closer agreement with high-step references.
Critical strengths
- The method is simple and practically attractive. A single offline calibration profile supports different sampling budgets without retraining or additional inference evaluations.
- The Euler-error analysis provides a clear motivation for acceleration-based allocation. The FLUX results show substantial improvements in reference agreement, supported by the additional 1,000-prompt evaluation.
Critical weaknesses
- The comparison with closely related scheduling methods remains limited. FLUX is evaluated only against the default and static shifted schedules, while OSS-ave appears only on synthetic datasets. Since OSS [1] already studies calibrated schedules for FLUX, a comparison at matched NFE, together with calibration costs, is important to establish the practical advantage.
- The statistical guarantee does not directly cover the full implementation. Theorem 2 assumes an idealized interval allocation. Errors from finite differences and inverse-CDF interpolation are not explicitly bounded, especially when inference uses far fewer steps than calibration.
- The FLUX results use an additional final-step correction without a separate ablation. Its contribution to the gains is therefore unclear. Calibration also uses a shifted grid, while the algorithms assume uniform spacing. The handling of interval widths and endpoints needs clarification.
[1] Optimal Stepsize for Diffusion Sampling, Pei et al., arXiv 2025
Questions for authors
- How does Theorem 2 account for finite-difference and inverse-CDF discretization errors when the inference budget is much smaller than the calibration grid?
- For FLUX, how are nonuniform calibration intervals and the final-step replacement handled? Are results available without the tail-alignment correction?
3 comments
Tail-alignment ablation (W3, Q2). We conducted a separate ablation to isolate the contribution of the FLUX tail-alignment correction. We use the same 1,000 COCO evaluation captions, original calibration profile, generation seeds, and inference budgets, changing only whether the final step is aligned with the native FLUX pipeline.
| Method | B=8 RMSE | CLIP | FID | B=12 RMSE | CLIP | FID |
|---|---|---|---|---|---|---|
| Native FLUX | 53.69 | 0.308 | 42.89 | 49.63 | 0.307 | 37.02 |
| SharpEuler (with tail alignment) | 32.58 | 0.307 | 33.07 | 33.01 | 0.307 | 25.31 |
| SharpEuler (without tail alignment) | 33.82 | 0.307 | 33.68 | 33.07 | 0.307 | 25.36 |
Reference FID is computed against the fixed set of 1,000 images generated with the 50-step FLUX pipeline.
SharpEuler retains substantial improvements over native FLUX even without tail alignment. At , removing the correction changes the reference FID only from 33.07 to 33.68, compared with 42.89 for native FLUX. At , reference FID changes from 25.31 to 25.36, compared with 37.02 for native FLUX.
These results show that the principal gains arise from the calibrated timestep allocation rather than the final-step correction. Tail alignment provides a modest additional improvement and was introduced primarily to preserve perceived sharpness and fine visual details near the low-noise endpoint as noted in Appendix D.4. We will include this ablation and paired visual examples in the appendix.
Nonuniform calibration intervals and endpoint handling (W3, Q2). SharpEuler's construction in Section 2 is defined for a general descending calibration grid,
rather than requiring uniformly spaced timesteps. In particular, Eq. (4) divides consecutive velocity differences by the local interval width, defined as the average of the two adjacent calibration intervals. The estimate therefore accounts for nonuniform spacing rather than assuming a constant timestep. For FLUX, calibration uses the default 50-step pipeline described in Appendix D.4, retaining its shifted time coordinates. The sharpness estimates are assigned to their corresponding time midpoints before constructing the interpolated cumulative profile.
As specified in Appendix D.4, tail alignment replaces the final SharpEuler step with the corresponding native FLUX pipeline step, preserving the pipeline's low-noise tail, where the calibrated finite-difference profile is empirically noisier. The initial and terminal endpoints remain fixed, and the correction introduces no additional model evaluations. The sampler therefore continues to use exactly network evaluations. We will make these implementation details and the new experimental ablations explicit in the revised manuscript.
Follow-up
We would like to thank the reviewer again for their time and constructive feedback. We believe our responses and additional experiments address the main points raised in the review. We would be happy to clarify any remaining questions during the discussion period.
We thank the reviewer for the careful review and constructive comments.
Comparison with OSS-ave and KTS on FLUX (W1). We have extended the FLUX experiments to include OSS-ave and KTS at matched inference budgets, with offline calibration costs reported separately. We evaluate all methods on the same 1,000 COCO captions, using identical evaluation prompts, generation seeds, and 50-step reference images. All experiments use FLUX.1-dev at 1024×1024 resolution, with inference budgets of B=8 and B=12 model evaluations. For methods requiring offline calibration, we use 64 calibration prompts and 50 profiling or teacher steps. KTS uses the balanced hyperparameter setting reported in its paper.
Reference FID is computed against the fixed set of 1,000 images generated using the 50-step FLUX pipeline.
SharpEuler achieves the lowest RMSE and reference FID at both budgets. Compared with OSS-ave, at B=8, RMSE decreases from 38.73 to 32.58 and reference FID from 37.73 to 33.07. At B=12, RMSE decreases from 33.65 to 33.01 and reference FID from 25.92 to 25.31. CLIP scores remain close across methods.
Offline calibration cost. SharpEuler estimates a single continuous sharpness profile that can be reused across inference budgets, whereas our OSS-ave implementation performs a separate schedule search for each budget.
All calibration and search computations were performed on NVIDIA A100 GPUs. SharpEuler requires 9$\times$ fewer offline model evaluations than OSS-ave at B=8 and 13$\times$ fewer at B=12. Furthermore, the same SharpEuler profile supports both inference budgets, whereas OSS-ave requires a separate search. These offline evaluations are not included in the matched inference NFE. We will include these comparisons and implementation details in the appendix.
Statistical guarantee and practical discretization (W2, Q1). We agree that Theorem 2 abstracts from some implementation details. It explicitly absorbs finite-difference and calibration-grid biases into the residual term C2, while the inverse-CDF construction is the deterministic realization of the calibrated density: each interval carries mass 1/B, so the practical grid implements the same allocation principle analyzed theoretically. When B≪N, the calibration profile is still estimated on the fine grid N, while the smaller B simply makes the resulting Euler approximation coarser, as reflected by the O(1/B) term; the theorem is therefore a stability guarantee rather than a tight few-step error bound. Note that a theorem covering every implementation detail would necessarily depend on model- and task-specific choices such as time parameterization, interpolation, endpoint handling, and multistage sampling, so we intentionally isolate the model-independent calibration error and treat these deterministic approximations separately. We will clarify this scope in the revision.