- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
TokenScale studies training-free resolution expansion for pretrained DiT-based flow models. Its main methodological choices are to interpolate whole patch-token vectors from a completed low-resolution sample and to correct selected regions against a fixed reference during a short initial denoising window. The selection rule uses smoothed prediction–reference distances in the input-projected token space, followed by quantile thresholding and connected-component filtering. The corrected clean prediction is incorporated into the current latent state while preserving its implicit residual, after which the velocity is re-evaluated. The paper reports improved perceptual quality on FLUX.1[dev], with qualitative extensions to Qwen-Image and UltraImage.
Critical strengths
Whole-patch expansion is a concrete and implementable design choice.
The complete pipeline shows promising practical results.
Critical weaknesses
-
The independent contribution of whole-token expansion is not established. The tokens being interpolated are obtained immediately after an affine input projection. As the paper's own equivalence shows, the projection commutes with spatial interpolation, so expansion can be implemented entirely by resampling patchified VAE latents. The methodological distinction is therefore the spatial grouping used during interpolation. This could be useful, but it does not by itself establish the claimed preservation of semantic information. The quantitative ablation mainly contrasts the proposed initialization with a collapsed configuration, while the matched comparison with ordinary latent-grid interpolation is limited to a qualitative example. It remains unclear how much of the gain comes from preserving patch coordinates and how much comes from inheriting any reasonable low-resolution initialization. A benchmark comparison of ordinary latent interpolation, pixel-upsample-and-re-encode initialization, and patch-grid expansion, using the same base sample, noise, restart schedule, and extrapolation toolkit, is needed to establish this first contribution.
-
The selective fusion rule has not been shown to identify the regions where correction is beneficial. The mask selects relatively large, spatially coherent deviations from a fixed low-resolution-derived reference. Both structural drift and legitimate new high-resolution detail can produce such deviations, and a quantile threshold continues to select a roughly fixed fraction even when the absolute discrepancy is small. Smoothing and connected-component filtering make the mask coherent, but coherence alone does not demonstrate that those regions should be pulled toward the reference. The current ablation measures the effect of adding the complete fusion procedure; it does not separate the value of the projected-token distance, the spatial mask, and the early reference correction itself. A comparison with uniform early fusion and matched-area control masks, with correction strength and network-evaluation budget accounted for, would show whether spatial selection adds value. Comparing projected-token distance with raw patch distance would further test whether the token-space metric is an essential part of the method.
-
The contribution of the combined sampling strategy is insufficiently distinguished from existing early-guidance cascades. DiffuseHigh already confines structural guidance to an early stage, and HiFlow reduces its guidance strength over time. The temporal release of reference constraints therefore has a direct precedent. TokenScale needs to establish the added value of coupling its patch initialization with spatial selection. The reported comparisons use the competing methods' official settings, while TokenScale also uses positional and attention-balancing techniques adopted from prior work. They do not include a simple, matched FLUX cascade with ordinary initialization and tuned early global fusion. The parameter examples show that excessive guidance can hurt, but do not establish that the proposed combination outperforms a well-tuned simpler strategy. The 4K UltraImage combination disables fusion, so that result supports expansion compatibility rather than the added value of the complete two-module design. A matched comparison that separates initialization, spatial selection, and guidance duration is necessary to determine what the overall method contributes beyond these existing ingredients.
Questions for authors
-
How does patch-grid expansion compare with ordinary latent-grid interpolation and pixel upsampling followed by VAE re-encoding when the low-resolution sample, added noise, restart schedule, positional/attention settings, and sampling budget are identical? Please report this comparison over a shared evaluation set rather than selected examples.
-
With the same initialization and early window, does the proposed mask outperform uniform fusion and matched-area control masks? Please account for the amount of reference correction and the extra velocity evaluations. How much is gained by the projected-token distance over raw patch distance, and by smoothing/component filtering over quantile selection alone?
-
How much of the final improvement remains over a simple FLUX cascade with tuned early global guidance, or an appropriately tuned/early-stopped HiFlow? Can initialization, spatial selection, and guidance duration be varied separately to show which combination is necessary?
-
Do the components retain their contributions on Qwen-Image and when paired with UltraImage? In particular, can the full combination be compared with expansion alone under matched quality and total inference cost?
4 comments
Part 2 (W2 & Q2): Ablation Study of Different Mask Strategies and Distance-Metric Diagnostics
We compared all-token fusion, an area-matched random mask, quantile thresholding without smoothing or component filtering, and the full structural mask. The runs used the same patch-grid initialization, early fusion window, blend weight per selected token, and re-evaluation protocol, one extra velocity evaluation per fusion step, so all four conditions incur the same number of network evaluations. The structural and quantile-only masks each covered about 40% of the tokens, the random control matched this area, and all-token fusion covered the full map. The mask changes only where the correction is applied, not the evaluation count.
| Metric | All-token | Random | Quantile only | Structural |
|---|---|---|---|---|
| FID ↓ | 60.51 | 59.92 | 59.24 | 59.15 |
| FGResQ ↑ | 0.6011 | 0.5941 | 0.6003 | 0.6024 |
| KID ↓ | 0.007665 | 0.007737 | 0.007432 | 0.007200 |
| CLIP Score ↑ | 34.43 | 34.24 | 34.29 | 34.31 |
| CLIP-IQA ↑ | 0.7266 | 0.7166 | 0.7299 | 0.7350 |
The results show that the structural mask performs best on most metrics. It corrects only the spatially coherent regions with the largest deviations, which stabilizes the structure while leaving the remaining regions free to synthesize new detail. New detail can also produce large deviations, so we use the deviation map only as a heuristic for candidate regions, requiring coherence on top of magnitude.
On 100 prompts, the mean Pearson correlations between raw and projected distances were 0.912 before smoothing and 0.937 after smoothing, and the mean final-mask IoU was 0.880, with 39.6% coverage using raw patch distances and 39.7% using projected distances. The two distances are highly correlated, so the choice has a very small impact on generation. For computational efficiency, we compute the distances directly on the patched latents.
Part 3 (W3 & Q3): Simple-Cascade Baseline, Factorized Decomposition, and Early-Stopped HiFlow
DiffuseHigh uses wavelet-based structural guidance early in denoising, and HiFlow gradually reduces its flow-alignment weights. TokenScale combines patch-grid initialization with spatially selective correction toward a fixed reference. To test the added value of this combination, we ran the simple matched cascade you describe, ordinary latent-grid initialization with early all-token fusion:
| Metric | Simple cascade (Latent + All-token) | TokenScale |
|---|---|---|
| FID ↓ | 60.83 | 59.15 |
| FGResQ ↑ | 0.5921 | 0.6024 |
| KID ↓ | 0.007321 | 0.007200 |
| CLIP Score ↑ | 33.21 | 34.31 |
| CLIP-IQA ↑ | 0.6732 | 0.7350 |
The simple cascade is worse on all five metrics under matched settings. We also varied the three components separately around the TokenScale configuration.
Initialization, with structural fusion fixed:
| Metric | Latent + TF | Pixel + TF | TE + TF (ours) |
|---|---|---|---|
| FID ↓ | 59.61 | 59.85 | 59.15 |
| FGResQ ↑ | 0.5841 | 0.5810 | 0.6024 |
| KID ↓ | 0.006659 | 0.007431 | 0.007200 |
| CLIP Score ↑ | 34.20 | 34.22 | 34.31 |
| CLIP-IQA ↑ | 0.6248 | 0.4121 | 0.7350 |
Spatial selection, with patch-grid initialization fixed:
| Metric | All-token | Random | Quantile only | Structural |
|---|---|---|---|---|
| FID ↓ | 60.51 | 59.92 | 59.24 | 59.15 |
| FGResQ ↑ | 0.6011 | 0.5941 | 0.6003 | 0.6024 |
| KID ↓ | 0.007665 | 0.007737 | 0.007432 | 0.007200 |
| CLIP Score ↑ | 34.43 | 34.24 | 34.29 | 34.31 |
| CLIP-IQA ↑ | 0.7266 | 0.7166 | 0.7299 | 0.7350 |
Guidance duration, with initialization and selection fixed, measured on the 200-prompt cohort; columns show the fraction of the post-restart schedule during which fusion is applied:
| Metric | 6.7% | 10% | 13.3% | 26.7% | 40% | 60% | 80% |
|---|---|---|---|---|---|---|---|
| FID ↓ | 171.50 | 166.35 | 171.86 | 168.52 | 168.63 | 172.59 | 171.92 |
| FGResQ ↑ | 0.6021 | 0.6033 | 0.5987 | 0.5904 | 0.5742 | 0.5545 | 0.5623 |
| KID ↓ | 0.007223 | 0.007212 | 0.007998 | 0.007597 | 0.007891 | 0.007876 | 0.007874 |
| CLIP Score ↑ | 34.24 | 34.26 | 34.21 | 34.06 | 34.14 | 34.10 | 34.10 |
| CLIP-IQA ↑ | 0.7209 | 0.7342 | 0.7512 | 0.7136 | 0.6011 | 0.5297 | 0.4958 |
These comparisons estimate separate effects under the tested settings.
A HiFlow variant that stops guidance early while completing the denoising schedule reached, at 4K, KID 0.0086, CLIP Score 34.66, CLIP-IQA 0.602, and FGResQ 0.5934, showing no significant change relative to the official-settings metrics we measured in the main text. Early stopping does not materially improve HiFlow, because its setting resamples after 66% of the schedule, leaving little room for released guidance to benefit the model. FID is omitted since it is a biased estimator at this sample size. Appendix G additionally compares attention spectra using official and restart-matched HiFlow settings.
Part 4(Q4) Component Contributions on Qwen-Image and UltraImage
Qwen-Image. On Qwen-Image, we found during experiments that, because the model is strong, TE alone already generates good images, so TF's contribution there is limited; the paper includes the corresponding clarification.
UltraImage. In the coupling experiment with FLUX as the base model, UltraImage alone cannot generate 4K images; adding TE greatly extends its capability. TE also accelerates generation: instead of 40 steps, the super-resolution stage can restart from step 10 or 20 with the low-resolution upsampled initialization, saving about 25%–50% of the super-resolution time steps. TF's effect is weakened after coupling, and we will report this honestly in the paper.
Part 1 (W1 & Q1): A Matched Benchmark of Alternative Expansion Strategies: Isolating the Effect of Patch-Grid Token Expansion
Thank you for the suggestion. We ran this benchmark on the shared 1,000-prompt 4K evaluation, comparing unpacked latent-grid interpolation, pixel upsampling followed by VAE re-encoding, and packed patch-grid expansion. Within each fusion setting, the runs matched the source sample, injected noise, restart schedule, auxiliary positional and attention settings, and denoiser evaluation budget.
The comparison shows that patch-grid expansion provides an effective initialization. The advantage holds with fusion both enabled and disabled.