- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper does training-free long video generation. It runs a pretrained flow model on overlapping chunks and pulls neighboring chunks together during sampling. There are two pieces: Tweedie matching blends each chunk's prediction with its neighbor's on the overlap. With the linear schedule this is really a crossfade. Stochastic early-phase sampling re-noises with fresh noise, then switches to plain ODE. The whole thing is framed as a DDS-style inverse problem. Experiments use Wan2.1-1.3B and LTX-2 at 30s/60s, with VBench, drift metrics, and a user study. There are also demos on audio-video (LTX-2) and text-to-3DGS (VIST3A).
Critical strengths
It's simple and actually plug-and-play. Nothing in the backbone changes, so it runs on LTX-2 audio+video and VIST3A with no retraining. AR distillation methods really can't do that.
The motion results convinced me. At 60s, the AR baselines distilled from Wan drop to 0.41–0.53 dynamic degree, while FlowLong keeps 0.82. Figs. 7–9 back this up. The authors are also upfront that VBench consistency metrics reward near-static videos, which I appreciate.
Memory doesn't grow with length: 21GB vs. 45–51GB for RIFLEx/UltraViCo. It also works with a 4-step backbone.
Critical weaknesses
-
A.4 doesn't match App. C, and this undercuts the main ablation. In A.4, all chunks share one global buffer and is re-sliced from it. So neighboring chunks have the same noisy latent on the overlap. App. C's argument assumes the opposite (, and noise shrinkage). C's last sentence even admits that with a shared latent, fusing \hat{x}_{0|t} and fusing are the same thing. So where does the Table 3 gap between Ours and matching ( vs. ) actually come from?
-
The novelty is overstated, and close prior work is missing. With the linear ramp , Tweedie matching is just a crossfade of \hat{x}_{0|t} across overlapping windows. The "measurement" is the neighbor's estimate, which itself gets updated, so this is really temporal co-denoising rather than an inverse problem. With , the early phase reduces to "predict , re-noise with fresh ". This is very close to SynCoS, Gen-L-Video and SyncTweedies. SynCoS and Gen-L-Video aren't cited, and SyncTweedies gets one line in App. C. I'd like to see a comparison with at least SynCoS or FIFO-Diffusion.
-
The VBench "Overall" score is mostly Dynamic Degree. Drop that one dimension and average the other six at 60s: Ours , vs. Deep-Forcing and LongLive . In Table 2, FlowLong also trails the strong AR baselines on Visual Stability and Content Retention. The extra motion is a real win, but "outperforming" in the abstract should be "on par, with much more motion".
Questions for authors
- How was matching implemented, given the shared buffer in A.4? Can you confirm that in the ODE-only phase () it's identical to Ours, as the last sentence of App. C implies?
- How does FlowLong differ from SynCoS and Gen-L-Video, both conceptually and in experiments?
- What and did you use for Wan2.1?
- For the user study: how many participants, how many prompts, and how many judgments per pair?
- How sensitive is the method to and ?
- What happens at 2–5 minutes? The constraint is purely local, and Content Retention is already tied for lowest at 60s, so I'd expect identity drift.
3 comments
Response by Authors (2/2)
W3
W3. "The VBench "Overall" score is mostly Dynamic Degree. …"
(1) VBench without Dynamic Degree. The Overall gain comes mainly from Dynamic Degree, and this is by design. The main weakness of autoregressive long-video models is that their motion fades into near-static content as the video gets longer, and FlowLong is designed to solve exactly this. Dynamic Degree is therefore the metric that measures our target problem, not an auxiliary dimension. Following the reviewer’s suggestion, we report the mean of the other six dimensions without Dynamic Degree.
Table R2. VBench mean without Dynamic Degree.
| CausVid | Self-Forcing | Deep-Forcing | ∞-RoPE | LongLive | FlowLong (Ours) | |
|---|---|---|---|---|---|---|
| 6-dim mean(30s) | 0.8296 | 0.8308 | 0.8399 | 0.8434 | 0.8545 | 0.8305 |
| 6-dim mean(60s) | 0.8201 | 0.8060 | 0.8421 | 0.8403 | 0.8528 | 0.8259 |
(2) Long-range drift (Table 2). FlowLong stays within the range of the AR baselines (30s: 0.8305 vs. 0.8296–0.8545; 60s: 0.8259 vs. 0.8060–0.8528). FlowLong roughly doubles Dynamic Degree (0.82 vs. 0.41–0.53 at 60s) while keeping the other dimensions at the same level. We also note that this comparison favors static methods: four of the remaining six dimensions (Subject Consistency, Background Consistency, Motion Smoothness, Temporal Flickering) measure frame-to-frame consistency, which near-static videos maximize. VBench [1,2] notes that static scenes can “cheat” these temporal consistency scores, which is why Dynamic Degree is a separate axis, and Self-Forcing++ [3] attributes the high temporal scores of AR baselines to motion stagnation. Table 2. On long-range drift, FlowLong has the lowest Semantic Drift (0.0003 vs. 0.0009–0.0093), and its Visual Stability (97.2) and Content Retention (0.927) are within a small margin of the strongest AR baselines (97.6–99.2 and 0.927–0.938), which are explicitly designed against drift and produce about half the motion.
(3) Abstract. We have also revised the abstract. Instead of “outperforming both training-free and autoregressive baselines”, it now states that FlowLong achieves “the best Overall VBench score with substantially higher motion, and remains comparable on the other dimensions and on long-range drift metrics.”
Q4. The study has 63 participants and 10 prompts. Each participant made 10 pairwise comparisons, with each of the five baselines appearing twice, and judged every pair on three axes. This gives 126 judgments per baseline and 630 judgments in total for each axis.
Q5. t* trades cross-chunk consistency for detail, and Table 3 shows its two extremes: without a stochastic phase (full ODE) the Quality is 0.6075, and with stochasticity at every step (full SDE) it drops to 0.5298, against 0.6359 for our schedule. Appendix D shows that a stochastic update retains more of the fusion correction than a deterministic one at every measured noise level, so the benefit does not depend on a particular t.
Q6. Generating videos longer than two minutes is a very challenging task for bidirectional models alone. We consider it future work, as noted in the Conclusion.
[1] Huang et al., VBench: Comprehensive Benchmark Suite for Video Generative Models, CVPR 2024.
[2] Huang et al., VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models, 2024.
[3] Cui et al., Self-Forcing++: Towards Minute-Scale High-Quality Video Generation, 2025.
We appreciate your time and constructive feedback throughout the discussion. As the discussion period is ending soon, we would like to kindly follow up on our response. We hope it has addressed your remaining concern about Table 1. If there is anything else we can clarify, we would be happy to answer before the discussion closes.
Response by Authors (1/2)
W1 & Q1, Q3
Thank you for pointing out this inconsistency. Appendix A.4 was incorrectly written, and we have revised it to be consistent with Appendix C. Each chunk keeps its own noisy state, initialized from independent noise. In this setting, fusing clean estimates before the update and fusing noisy latents after the update are not equivalent, and the fusion-space comparison in Table 3 is made under this setting. The x_t matching baseline is given as Algorithm 2 in Appendix G; since the chunks start from independent noise, it is not identical to ours in the ODE-only phase either. For Wan 2.1, we use t* = 0.555 with 30 sampling steps and flow shift 5; each chunk has F = 21 latent frames with an overlap of O = 11 and a stride of S = 10, and λ_j increases linearly over the overlap (Appendix A.1).
W2 & Q2
(1) Inverse problem vs. co-denoising. At each sampling step, the neighboring estimate is held fixed, and the weighted interpolation in Eq. (16) is the closed-form solution of the guidance loss in Eq. (12) for that measurement. The loss has the form 21∥y−Ax∥2, where A selects frames and y is a measurement, and y can be any observation. We additionally apply the same formulation with real measurements that stay fixed throughout sampling: long-video extension, where a real video prefix is the measurement (Fig. 14), and long-video frame interpolation, where observed clips guide the missing intervals (Fig. 13); both are in Appendix E. This extension was not addressed using the existing methods at inference time. The corresponding videos for both tasks are available on the revised anonymous project page. In these tasks, y does not change during sampling, so they are inverse problems in the standard sense. Co-denoising methods average the predictions of overlapping windows and have no measurement term.
(2) Differences from SynCoS, Gen-L-Video, and SyncTweedies. Gen-L-Video fuses the noisy latents of overlapping clips, and SyncTweedies averages Tweedie estimates; both use deterministic sampling throughout, and SyncTweedies is demonstrated on spatial synchronization (panoramas, textures, 3D). SynCoS adds a score-distillation optimization of the latent in the early steps, which requires iterative gradient updates at each of those steps. FlowLong differs in three ways. First, FlowLong is formulated as an inverse problem with a measurement y, so the same sampler extends to real observations: long video interpolation from observed clips (Fig. 13) and long video extension from a given prefix (Fig. 14). The methods above synchronize the predictions of overlapping windows and have no measurement term, so they do not extend to these applications. Second, the update of FlowLong is a closed-form solution of the guidance loss, with no optimization and no additional network evaluations. Third, we show that deterministic synchronization is not sufficient for temporal chunks: a deterministic update retains only 4–7% of each fusion correction, whereas a stochastic update retains 26–33% (Appendix D), which is why FlowLong injects noise in the early phase.
(3) Comparison with FIFO-Diffusion. Following the reviewer’s suggestion, we evaluated FIFO-Diffusion on Wan 2.1-1.3B and added it to Table 1. FIFO-Diffusion reaches a Dynamic Degree comparable to ours (0.8113 / 0.8252 vs. 0.7800 / 0.8200 at 30s / 60s), but with lower aesthetic quality (0.4948 / 0.4887 vs. 0.5777 / 0.5738) and imaging quality (0.5403 / 0.5361 vs. 0.6368 / 0.6391), and FlowLong achieves the higher Overall score at both lengths (0.8233 vs. 0.8032 and 0.8251 vs. 0.8014). SynCoS has no public implementation to our knowledge, so we discuss it in the related work. We have added SynCoS and Gen-L-Video to the related work and expanded the discussion of SyncTweedies there.
Table R1. FIFO-Diffusion vs. FlowLong on Wan 2.1-1.3B (VBench).