- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes RACE, a training-free method using state-guided velocity extrapolation with a refresh-anchored correction mechanism. The authors point out that cache-based velocity reuse will lead to error accumulation as the number of skipped steps increases. They observe an approximately linear relationship between state and velocity changes along local denoising trajectories. Based on the observation, RACE utilizes the state-velocity relationship of historical steps to estimate the velocity of skipped steps and compares the actual velocity and predictions to estimate accumulated errors and make corrections. The paper provides abundant experiments to demonstrate these claims and the improvement.
Critical strengths
- Easy and Useful: The RACE could be utilized in other training-free, cache-based diffusion acceleration methods orthogonally and shows promising improvements (30+dB PSNR results are really impressive), which provides good scalability.
- Clear theory and numerical analysis: The paper discusses the near-linear relationship between state and velocity changes and error accumulation with clear numerical analysis that is easy to understand.
- Innovative: Providing a novel adjustment method to handle the error accumulation problems in cache-based diffusion acceleration, which will inspire more attempts based on these discoveries and techniques.
Critical weaknesses
- Video Quality Evaluation: For 30 dB PSNR configurations, current indicators are powerful enough to demonstrate the closure between the accelerated and original trajectories. However, a VBench result may strengthen the argument for the 20 dB results.
- Generalization of the Near-linear Assumption: It shows that the proposed method still works quite well on backbones that don’t exactly obey the assumption. Additional discussion of the method's generalization ability in non-ideal situations would be helpful.
- Without Indicating the Improvement Directly: Another table showing the improvement of the refresh mechanism compared with previous caching methods such as TeaCache, EasyCache, SenCache, and SeaCache will help strengthen the point.
Questions for authors
- Is there an optimal configuration of this caching and refreshing process for each backbone, or can the optimal configuration be determined by numerical analysis?
- Will it be helpful when utilizing other approximate functions other than linear? If not, what might be the reason?
3 comments
Part2: W3, Q1, Q2
W3: Indicating the Improvement for different cache scheduler Directly.
Compared with TeaCache, EasyCache, SenCache, and SeaCache, RACE focuses on reducing generation errors and modifying the generation trajectory. It is compatible with different cache schedulers. Because RACE changes the sampling trajectory, the actual refresh locations may also change. On FLUX.1-dev, we compared these four schedulers with and without RACE. Adding RACE improves PSNR by 0.479, 2.911, 3.293, and 3.282 dB, respectively, with improvements in the other metrics as well. These results demonstrate RACE’s effectiveness across cache schedulers. We observed that TeaCache still selects reuse in some intervals that deviate from local linearity, partly limiting RACE’s correction gains. Its improvements are therefore consistent but relatively modest.
| Method | TFLOPs | PSNR ↑ | LPIPS ↓ | SSIM ↑ | PSNR gain |
|---|---|---|---|---|---|
| TeaCache | 921.159 | 20.631 | 0.2061 | 0.8085 | — |
| TeaCache + RACE | 930.440 | 21.110 | 0.1938 | 0.8218 | +0.479 |
| EasyCache | 931.011 | 28.394 | 0.0700 | 0.9256 | — |
| EasyCache + RACE | 927.329 | 31.305 | 0.0364 | 0.9541 | +2.911 |
| SenCache | 930.453 | 29.069 | 0.0606 | 0.9309 | — |
| SenCache + RACE | 933.531 | 32.362 | 0.0349 | 0.9552 | +3.293 |
| SeaCache | 930.536 | 29.578 | 0.0546 | 0.9358 | — |
| SeaCache + RACE | 927.412 | 32.860 | 0.0288 | 0.9620 | +3.282 |
Q1: Is there an optimal configuration of this caching and refreshing process for each backbone?
We primarily use the hyperparameter δ to control the cache scheduler’s reuse aggressiveness. We varied δ in SeaCache + RACE on FLUX.1-dev and evaluated computational cost and image quality using 200 DrawBench prompts:
| δ | TFLOPs ↓ | PSNR ↑ | LPIPS ↓ | SSIM ↑ |
|---|---|---|---|---|
| 0.1875 | 1007.270 | 34.69 | 0.0213 | 0.9705 |
| 0.2250 | 930.513 | 32.86 | 0.0288 | 0.9620 |
| 0.2625 | 851.430 | 31.16 | 0.0404 | 0.9491 |
| 0.3000 | 776.999 | 29.87 | 0.0498 | 0.9394 |
| 0.3750 | 670.004 | 26.90 | 0.0846 | 0.9046 |
| 0.5250 | 556.031 | 24.38 | 0.1182 | 0.8745 |
| 0.6000 | 483.926 | 22.34 | 0.1564 | 0.8445 |
Increasing δ makes reuse more aggressive, reducing both computational cost and output fidelity. We further fitted the relationships among δ, computational cost, and PSNR to quantify the quality cost of adjusting δ and guide the choice of computational budget and threshold.
Across the seven operating points, the fitted relationship is PSNR = −28.5406δ + 38.9757 (R² = 0.9683). In terms of computational cost F, measured in TFLOPs, the fit is PSNR = 0.023348F + 11.2862 (R² = 0.9975), showing a more pronounced linear relationship. R² is the coefficient of determination which measures how much variation in the observations is explained by the fitted model; values closer to 1 indicate a better fit. Thus, δ can control computational cost and fidelity, while the fitted slopes quantify the magnitude of this trade-off.
Overall, choosing δ involves a clear compute–fidelity trade-off, and no single δ is optimal for all budgets.
Q2: Will it be helpful when utilizing other approximate functions other than linear?
We examined nonlinear approximations in two ways: (1) incorporating older refresh points into polynomial fitting for SGVE; and (2) using higher powers of β to weight the per-step error estimates in RAIC.
For SGVE, we compared history windows containing 2, 3, and 4 refresh points, fitting a nonlinear polynomial in each window for per-step velocity prediction. We evaluated these settings on FLUX.1-dev using DrawBench prompts:
| Number of historical points | TFLOPs ↓ | PSNR ↑ | LPIPS ↓ | SSIM ↑ |
|---|---|---|---|---|
| 2 | 938.142 | 32.9389 | 0.0285 | 0.9623 |
| 3 | 937.584 | 31.6772 | 0.0306 | 0.9606 |
| 4 | 937.584 | 30.8036 | 0.0315 | 0.9610 |
Increasing the history from 2 to 3 or 4 points reduces PSNR by approximately 1.262 and 2.135 dB, without improving LPIPS or SSIM. This indicates that extending the history does not yield more accurate predictions of the current velocity. SGVE relies on the local state–velocity relationship, while older refresh points may come from trajectory segments whose dynamics have already changed. The two most recent refresh points therefore better reflect current local changes.
For RAIC, we replaced the linear weight β with β^1.5、β² and β³ to evaluate nonlinear weighting. These experiments also used FLUX.1-dev and 200 DrawBench prompts, with each variant’s threshold set according to the computational budget:
| RAIC weight | TFLOPs ↓ | PSNR ↑ | LPIPS ↓ | SSIM ↑ |
|---|---|---|---|---|
| β | 938.142 | 32.9389 | 0.0285 | 0.9623 |
| 937.956 | 32.6654 | 0.0292 | 0.9613 | |
| β² | 937.956 | 32.3271 | 0.0305 | 0.9599 |
| β³ | 937.77 | 31.9871 | 0.0320 | 0.9581 |
Increasing the exponent of β from 1 to 1.5, 2, and 3 progressively reduces PSNR and worsens both LPIPS and SSIM.
Overall, neither quadratic fitting nor correction weights with higher powers improved fidelity. For SGVE, older history may shift the fit away from current local changes. For RAIC, higher powers of β reduce compensation at intermediate steps, whereas the error diagnostics in Fig. 4(a) indicates growth closer to linear. We therefore retain two-point SGVE and linear RAIC.
Thanks for your rebuttal. My concerns are well addressed.
Part1: W1, W2
Thank you for your valuable assessment and suggestions.
W1: Video Quality Evaluation.
We additionally report VBench Quality, Semantic, and Total scores for Original, reduced-step sampling, and the caching methods on Wan2.1, HunyuanVideo, and MiniMax-H3. These complement the reference-fidelity evaluation using PSNR, LPIPS, and SSIM.
RACE achieves the highest Total scores among the listed caching methods at both computational budgets on all three models. Compared with SeaCache, RACE improves Total by 0.511 and 0.674 on Wan2.1, 0.239 and 0.098 on HunyuanVideo, and 0.156 and 0.128 on MiniMax-H3, at the high and low computational budgets, respectively. These results show that RACE maintains overall video quality while improving reference fidelity.
W2: Generalization of the Near-linear Assumption.
The method does not require the entire sampling trajectory to be globally linear; it relies primarily on local approximations within short reuse intervals. SGVE models the local state–velocity relationship using the two most recent full-computation refresh points and determines the extrapolation coefficient by projecting the current state onto the latest displacement direction. Each refresh updates the local secant, allowing predictions to adapt as the sampling trajectory evolves. In Appendix E, the second and third principal components exhibit more pronounced curvature, yet SGVE still tracks the local trajectories well. This indicates that the mechanism also applies when the linear relationship is imperfect.