- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper describes a training-free faster diffusion and flow-matching models sampling method, which uses Hermite spline to avoid velocity evaluation at every timestep, but instead predicts the estimated intermediate velocities. By conducting experiments on various base models, the novel sampling method achieves the state-of-the-art efficiency, while preserving the generated image quality under different metrics.
Critical strengths
Here are some major strengths of the paper:
- The theoretical foundation of the method is clear and thorough, with explicit motivation and rigorous Hermite spline derivations.
- Experiments inside of the paper are comprehensive, across different models, different baselines, different tasks, and different metrics.
Critical weaknesses
Here are some weaknesses:
- The Bn experiments (for example B10), although their configurations are able to be inferred from the paper context, should be defined more explicitly.
- The anchor optimization part is a bit suspicious; see the questions below.
Questions for authors
The paper looks sound in general, but I have one major concern, which can be split into the following detailed questions
- The exact-budget anchor optimization is described inside of Section 5; however they seem to be costly, since whenever the NFE budget and the size of the generated image changes, they need to be re-optimized by minimizing the loss (13). Can you give an analysis of the budget/wallclock time needed for the exact-budget anchor optimization?
- Should the anchor optimization NFE budget be also included in the comparison, since they're highly configuration-dependent? For example inside of Table 1, would it be a more fair comparison if the B10 and B17 are counted as using 10/17 NFEs+optimization NFEs, instead of purely 10/17 NFEs?
- Does the actual optimization development prompt–seed pairs used in the anchor optimization procedure matter? More precisely, if we happen to choose some different/bad samples used during the optimization, will the final anchor positions change drastically and therefore affect the final results?
I will raise my score to 3 or 4 if the anchor optimization related questions are addressed. Edit: I raised my score to 3.
5 comments
Response to Reviewer sUux — Part 2/3
Q2. Should optimization evaluations be included in the inference comparison?
We propose reporting offline preparation and per-image inference as separate, complementary costs. Table S1 makes the optimization cost explicit, while B17 describes the 17 guided evaluations performed for each generated sample using the frozen schedule. If preparing a schedule costs guided evaluations and it is reused for generations, the total is , and the average per generation is . This accounts for preparation once and makes its contribution explicit for any deployment volume.
Once obtained, the same mask is reused across prompts and can also transfer across the tested resolution settings, as Table S2 demonstrates. The relevant parallel with a pretrained or distilled checkpoint is that both produce reusable artifacts: a user can download the prepared checkpoint or anchor schedule and apply it directly to subsequent generations. BoundaryDelta keeps the pretrained weights fixed and optimizes only the evaluation locations. We therefore report schedule preparation alongside the inference comparison, while retaining the exact per-sample B10/B17/B25 counts. The preparation cost is amortized as the number of generated samples grows.
Response to Reviewer sUux — Part 3/3
Q3. Does changing the development prompt–seed panel alter the schedule and final performance?
Using a different ten-prompt search panel, the complete development pipeline selected a B17 schedule differing from our deployed schedule at only one evaluation location. Their archived terminal losses on the same original search panel differ by just 0.48%, with the new schedule slightly lower. On all 200 DrawBench prompts, it also improves all five fidelity means over the deployed schedule, including 2.52% lower MSE and 2.69% lower LPIPS.
A different development split. We re-split the development pool so that the ten search prompts were disjoint from the original ones. At B17 we ran the complete pipeline: Q200 search with optimizer seeds 0/1, selection on 15 prompts × two generation seeds, and confirmation on 25 prompts × five seeds, all separate from DrawBench. Both searches used CFG4 and generation seed 42.
We then froze the alternate-split selected B17 mask and evaluated it on all 200 DrawBench prompts at generation seed 42.
Table S3. Held-out test of the alternate-split selected mask, B17. All 200 DrawBench prompts, seed 42. Lower MSE/L1/LPIPS and higher SSIM/PSNR are better; bold/underline mark the best/second-best displayed means.
| Method / schedule | MSE ↓ | L1 ↓ | LPIPS ↓ | SSIM ↑ | PSNR ↑ |
|---|---|---|---|---|---|
| BoundaryDelta, alternate-split selected mask | 0.00598 | 0.0409 | 0.0583 | 0.9456 | 29.40 |
| BoundaryDelta, original deployed mask | |||||
| Released MeanCache | 0.00835 | 0.0542 | 0.0809 | 0.9287 | 27.36 |
The alternate-split mask preserves BoundaryDelta's advantage (MSE/L1/LPIPS −28.4%/−24.5%/−28.0% versus released MeanCache) and slightly improves on the deployed mask (MSE −2.5%, LPIPS −2.7%). The two BoundaryDelta masks have nearly identical automated quality means: HPSv2.1 0.29967/0.29966, VQAScore 0.8574/0.8575, CLIP-G 33.47/33.46 and ImageReward 1.211/1.213, respectively. Selection and confirmation average over two and five generation seeds per prompt, respectively, providing development evidence across noise draws.
Separately, the original frozen schedules retain all five fidelity point-estimate improvements over released MeanCache on the same 50-prompt panel at generation seeds 42, 43 and 44, across B10/B17/B25. This complementary deployment-noise test is also reported in our response to Reviewer 8DyQ (Table R4); we repeat the three-seed averages below to keep this answer self-contained.
Table S4. Three-generation-seed averages, original frozen systems. Each seed uses the same 50 prompts. Metric directions and within-budget highlighting follow Table S2; CLIP-G is 100×cosine.
| Budget | Method | MSE ↓ | L1 ↓ | LPIPS ↓ | SSIM ↑ | PSNR ↑ | CLIP-G ↑ | ImageReward ↑ | HPSv2.1 ↑ |
|---|---|---|---|---|---|---|---|---|---|
| B10 | BoundaryDelta | 0.0276 | 0.1074 | 0.1921 | 0.8347 | 21.75 | 31.80 | 1.092 | 0.2885 |
| Released MeanCache | |||||||||
| B17 | BoundaryDelta | 0.0062 | 0.0425 | 0.0622 | 0.9448 | 28.99 | 32.00 | 1.101 | 0.2927 |
| Released MeanCache | |||||||||
| B25 | BoundaryDelta | 0.0024 | 0.0238 | 0.0282 | 0.9741 | 33.90 | 31.84 | 1.095 | 0.2931 |
| Released MeanCache |
In short, schedule search is a one-time, measured cost per call budget. Once found, a schedule is reused across prompts and transferred to the tested new resolution. The alternate development pipeline selected a closely related B17 schedule with nearly identical archived search loss and improved held-out fidelity.
Response to Reviewer sUux — Part 1/3
Thank you for recognizing the rigorous derivation and the breadth of our evaluation. Your questions concern the practical cost and reliability of anchor scheduling. We address them with measured optimization costs, a frozen-schedule resolution-transfer test, and an additional search on different development prompts.
Budget definition. B10, B17 and B25 mean exactly 10, 17 and 25 guided transformer evaluations per generated sample, including the startup anchors, on the unchanged 50-transition solver grid. The remaining transitions use cached updates; FULL-50 evaluates the model at every transition.
Q1. What does anchor optimization cost, and must a configuration change require another search?
Measured offline cost. Our fresh Qwen-Image CFG4 searches use ten development prompts and two optimizer seeds. Q200 means that each search run evaluates 200 distinct candidate anchor schedules: eight starting schedules followed by 192 additional candidates. Each candidate is scored by its average terminal-latent MSE over the ten development prompts. Each search runs on four AMD MI210 GPUs and took approximately 8.3 hours at B17 and 12.0 hours at B25. Table S1 reports the combined cost of both optimizer seeds, together with the subsequent candidate-selection and validation stages.
Table S1. Measured BoundaryDelta offline preparation, both optimizer seeds combined. Calibration includes search, candidate collection, selection and validation.
Each reported call budget uses its own separately prepared schedule, with the one-time per-budget cost listed above. A new resolution did not require another search in our test: the B17 masks transferred unchanged from 1664×928 to 1328×1328 (Table S2).
Schedule reuse across resolutions. We transferred both methods' original B17 masks unchanged from 1664×928 to 1328×1328, keeping guidance at CFG4. Table S2 uses the same 50 DrawBench prompts and generation seed 42, with a resolution-matched FULL-50 reference.
Table S2. Frozen-mask resolution transfer, B17. Same 50 prompts, seed 42, resolution-matched FULL-50 and fixed CFG4; no re-search. Lower MSE/L1/LPIPS and higher SSIM/PSNR are better. Bold/underline mark the better/second mean within each setting.
At the new resolution, BoundaryDelta reduces MSE/L1/LPIPS by 29.93%/28.54%/30.76% versus released MeanCache, with higher SSIM and PSNR. The searched masks therefore transfer between these resolution settings while preserving BoundaryDelta's fidelity advantage over released MeanCache.