- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes CalibCache, an offline calibration method for feature caching in diffusion Transformers. For each deployment configuration it builds one paired full-compute and naive-cache trajectory and uses the discrepancy between their second-order residual-feature differences ("feature acceleration") as supervision. A centered least-squares estimator fits step- and branch-specific scalar maps in closed form. At inference, these frozen scalars correct cached residuals at the first cache step of each interval, combined with corrected writeback and an isolated full-anchor predictor history, adding no extra full-network evaluation and no online optimization.
Critical strengths
-
Very low deployment cost with substantive gains.
-
Requires only one full-compute/naive-cache trajectory pair per deployment configuration.
-
Evaluates FLUX.1-dev, Qwen-Image, and DiT-XL/2, with useful ablations and calibration sensitivity analyses.
Critical weaknesses
-
The experiments cover only 20-step sampling, without validation under other sampling schedules. Although the paper is motivated by the potential unreliability of history-based extrapolation under short sampling schedules, it does not show how this issue and the benefits of calibration vary with the sampling grid. Quality–latency comparisons across different numbers of sampling steps would help establish the method’s applicability and validate its motivation for short sampling schedules.
-
The paper compares only against caching methods and does not report full-compute baselines with fewer sampling steps on FLUX.1-dev or Qwen-Image. Consequently, it remains unclear whether CALIBCACHE provides better generation quality than simply reducing the sampling schedule from 20 steps to 7–9 steps at matched latency.
-
The latency benefits vary substantially across models and fall considerably short of the FLOPs reductions. For example, on DiT-XL/2 at , a 3.31× FLOPs reduction yields only a 1.81× denoising speedup. The paper should further analyze prediction, cache read/write, and other execution overheads to explain these cross-model differences and clarify the operating conditions under which substantial practical gains can be achieved.
-
The authors are encouraged to include a focused analysis of GOC[1] and ERTACache[2] in the related work section. Discussing these representative studies would help trace the development of diffusion feature caching and clarify the technical positioning of this submission.
[1]. Qiu, Junxiang, et al. "Accelerating diffusion transformer via gradient-optimized cache." 2025 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2025.
[2]. Peng, Xurui, et al. "Ertacache: Error rectification and timesteps adjustment for efficient diffusion." International Conference on Learning Representations. Vol. 2026. 2026.
Questions for authors
See the Weaknesses.
5 comments
Response to Reviewer RNbB (2/4): Reduced-Step Full-Compute Baselines
2. Reduced-step full-compute baselines at comparable latency
At comparable denoising latencies, CalibCache-20 improves the mean results on all three fidelity metrics and ImageReward over the reduced-step full-compute baselines on both FLUX.1-dev and Qwen-Image.
We bracket CalibCache's 20-step, N = 5, warmup-3 H800 denoising latency with integer-step Native baselines, using 7/8 steps for FLUX and 8/9 for Qwen. All methods use matched DrawBench-200 prompts and initial noise at 1024×1024, with identical model weights and guidance. Fidelity is measured against each model's Native-20 outputs.
| Model | Method | Time (s)↓ | PSNR↑ | SSIM↑ | LPIPS↓ | CLIP↑ | IR↑ |
|---|---|---|---|---|---|---|---|
| FLUX.1-dev | Native-7 | 2.3482 | 16.1774 | 0.6553 | 0.4595 | 31.3691 | 0.7572 |
| FLUX.1-dev | Native-8 | 2.6819 | 16.5108 | 0.6718 | 0.4298 | 31.4775 | 0.8327 |
| FLUX.1-dev | CalibCache-20 | 2.4644 | 19.1014 | 0.6735 | 0.4292 | 31.9461 | 0.8989 |
| Qwen-Image | Native-8 | 5.3885 | 15.1775 | 0.6327 | 0.4457 | 32.5732 | 0.8433 |
| Qwen-Image | Native-9 | 6.0586 | 15.2832 | 0.6386 | 0.4299 | 32.5348 | 0.8841 |
| Qwen-Image | CalibCache-20 | 5.6295 | 19.2460 | 0.7148 | 0.3041 | 32.4704 | 1.0008 |
On FLUX, all five improvements over Native-7 have paired 95% bootstrap intervals excluding zero. Against Native-8, PSNR improves by 2.5906 dB, also supported by the paired intervals. On Qwen, CalibCache improves all three fidelity metrics and ImageReward over both baselines, reducing LPIPS by 0.14159 versus Native-8 and 0.12578 versus Native-9. The corresponding ImageReward gains are 18.7% and 13.2%, while CLIP decreases by only 0.32% and 0.20%, respectively.
Appendix D.2 provides the complete evaluation and timing protocols, along with paired confidence intervals.
Response to Reviewer RNbB (3/4): FLOPs Reduction and Practical Speedup
3. The gap between FLOPs reduction and denoising speedup
Cache steps retain low-FLOP operations with non-negligible runtime. Differences in backbone workloads and overhead outside forward calls explain the variation in practical speedup across models.
(a) Retained cache-step costs
For DiT-XL/2 at 20 steps, N = 5, warmup-3, full evaluations decrease from 20 to six, yielding approximately 3.31× FLOPs reduction. The remaining 14 cache steps retain modulation, gating, residual updates, and cache operations. Matched-schedule measurements over 18 paired inputs on H800 at batch size 1 give the following cumulative costs:
| Component | Time (ms/image) | Share |
|---|---|---|
| Direct-reuse cost | 31.89 | 61.25% |
| CalibCache increment | 20.18 | 38.75% |
Even without correction, retained operations incur substantial latency after the main attention/MLP recomputation is skipped. CalibCache adds execution costs from prediction, history maintenance, and corrected-feature writeback.
In the same DiT setting, FORA uses four full evaluations without extra warmup, versus six for TaylorSeer, HiCache, and CalibCache. This smaller full-compute budget contributes to its speed advantage, while its generation quality is lower in this comparison. Its 4.96× FLOPs reduction yields 2.53× denoising speedup, consistent with the costs retained even by direct reuse.
(b) Cross-model runtime composition
The following shares use each configuration's total CalibCache denoising time as the denominator.
| Model | Resolution | Full forward | Cache forward | Outside forward |
|---|---|---|---|---|
| FLUX.1-dev | 1024×1024 | 89.39% | 10.59% | 0.02% |
| Qwen-Image | 1024×1024 | 66.52% | 11.65% | 21.83% |
| DiT-XL/2 | 256×256 | 48.46% | 38.02% | 13.52% |
DiT's 256×256 setting has fewer image tokens and smaller attention/MLP workloads than the 1024×1024 FLUX/Qwen settings, whereas AdaLN modulation-parameter projections do not shrink proportionally with token count. Retained operations therefore occupy a larger runtime share. Qwen also incurs substantial costs outside forward calls, including guidance computation, coordination between conditional/unconditional passes, and sampler updates.
The reported CalibCache speedups are 2.86×, 2.27×, and 1.81× on FLUX, Qwen, and DiT. Caching generally provides greater practical gains when attention/MLP recomputation dominates full-compute runtime and retained operations and outside-forward costs are relatively small. Appendix D.3 provides the complete protocols and breakdowns from diagnostics conducted separately from the original latency measurements.
Response to Reviewer RNbB (1/4): Sampling Grids and Calibration Benefits
We thank the reviewer for recognizing our method's low deployment cost, single-trajectory calibration design, and multi-model evaluation. We address the comments with sampling-grid diagnostics, comparable-latency baselines, runtime measurements, and a clarified comparison with prior work.
1. Sampling grids, extrapolation reliability, and quality–latency trade-offs
CalibCache remains effective at 30–50 steps, while the tested 20-step configurations show greater local extrapolation error and larger PSNR, LPIPS, and ImageReward gains over TaylorSeer than the 50-step configurations.
(a) Local extrapolation across sampling grids
Both models exhibit higher local prediction error at 20 than at 50 steps, even when predictions do not feed back into sampling.
We evaluate the same 32 DrawBench prompt–seed pairs at 20, 30, 40, and 50 steps. TaylorSeer receives features from a full-compute trajectory only at the anchors prescribed by N = 5, warmup-3, and predicts each interval's first cache step with maximum order two. Predictions never advance sampling. Errors are normalized by each sample's teacher-feature energy before averaging.
On both models, the paired 95% bootstrap confidence intervals for the 20-minus-50-step error difference lie entirely above zero. Appendix D.1 details the diagnostic and statistical procedures.
(b) Effectiveness under longer schedules
At 50 steps on FLUX.1-dev, CalibCache achieves the best means on all five quality/fidelity metrics among the compared caching methods and is faster than TaylorSeer and HiCache, with a 3.54× denoising speedup.
We evaluate 30, 40, and 50 steps on both models using DrawBench-200 at 1024×1024 with matched prompt–seed pairs, retaining one calibration trajectory pair per model–schedule configuration. The FLUX 50-step results follow. All caching methods use N = 5, with warmup-3 for TaylorSeer, HiCache, and CalibCache. Fidelity uses the matched Native-50 outputs.
Complete results and protocols for both models at 30–50 steps appear in Appendix C, Tables 16–21.
(c) More pronounced calibration gains under shorter schedules
CalibCache improves all five metrics over TaylorSeer in every listed setting. PSNR, SSIM, LPIPS, and ImageReward gains are larger at 20 than at 50 steps on both models.
The table reports CalibCache minus TaylorSeer, with the LPIPS sign reversed so that every positive value indicates improvement. Fidelity uses each grid's corresponding full-compute reference.
Together, the local extrapolation diagnostic and generation results support our motivation for calibration under short schedules. Complete longer-schedule baseline and latency results are provided in Appendix C.