- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a training-free video DiT caching method ALIGNVACE: utilizing streaming SVD and continuous-time dynamical operators to predict CFG residuals within a low-rank subspace, combined with closed-loop error calibration dynamic stepping, achieving leading acceleration ratios and PSNR/LPIPS in multi-round video editing and generation tasks.
Critical strengths
The proposed solution is interesting: Formulating diffusion residual caching as dynamical prediction within a low-rank subspace, combined with closed-loop error calibration for step-skipping, offers an interesting perspective while keeping the cache memory footprint low.
Critical weaknesses
-
Lack of Comprehensive Comparison:
a. The prediction-based methods under "Forecasting rather than reusing" (Section 2), such as TaylorSeer, are not included in the baselines;
b. The paper chooses a video model (Wan2.1 1.3B) for Text-to-Image comparison instead of dedicated T2I models like FLUX or Hunyuan-Image.
-
Limited Acceleration Gains and Insufficient Qualitative Comparison:
The speedup improvement over the strongest baseline (EasyCache) is relatively small (mostly ~1.8×–1.9× vs. ~1.6×–1.8×), and qualitative comparisons are only conducted on the Wan backbone, lacking visual results on other tasks and models (e.g., LTX-Video and T2I).
-
The method may be over-engineered, and the actual effectiveness of each module is difficult to determine:
In Table 3, "Without adaptive rank" achieves better quality and lower memory than the "Full" method, "Without cross-round transfer" is faster than "Full", and "Without predictive increment" has a slightly higher PSNR than "Full".
Questions for authors
-
How does ALIGNVACE compare against prediction-based caching methods such as TaylorSeer under the same settings?
-
Can the authors provide Text-to-Image evaluations on dedicated T2I models (e.g., FLUX or Hunyuan-Image)?
-
Can the authors provide qualitative visual comparisons on LTX-Video and T2I tasks, as well as results under higher acceleration ratios (e.g., >2.5×)?
-
Given that removing individual modules in Table 3 improves either quality, memory, or speed over the "Full" model, how do the authors justify the necessity and complexity of each proposed module?