- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Rotational Quality Tuning (RoQT), a framework designed to improve the quality tuning of pretrained rectified-flow image generation models. The method is motivated by two observations: correcting velocity directions at higher noise levels can improve reconstruction quality, and samples at similar noise levels exhibit different angular prediction errors. Based on these observations, RoQT introduces three components: (1) a macro-level noise curriculum that progressively shifts training from high-noise regions toward the reference timestep distribution, (2) a micro-level angular weighting scheme that emphasizes samples with larger relative directional errors, and (3) an additional direction correction term derived from the rotational component of the flow-matching MSE. The authors evaluate RoQT on SD3.5-Medium and Z-Image using approximately 50K curated image-text pairs. The method improves overall GenEval and Qwen-Image-Bench scores compared with standard supervised fine-tuning (SFT), and the authors provide component ablations and training dynamics to support its effectiveness. While the proposed framework is computationally straightforward and demonstrates encouraging empirical improvements, I have several concerns regarding its methodological novelty, the justification of its core design choices, and the completeness of the experimental evaluation.
Critical strengths
- The paper addresses the challenge of efficiently adapting pretrained rectified-flow models to limited high-quality datasets while mitigating performance degradation during prolonged fine-tuning. This is a relevant problem for modern generative-model training pipelines.
- RoQT does not require modifications to the backbone architecture, flow-matching trajectory, or inference procedure. The method can be integrated into existing LoRA fine-tuning pipelines with a single trainable-model forward pass.
- The decomposition of the flow-matching MSE into magnitude and rotational components provides an intuitive mathematical interpretation of the additional direction correction. The scale-calibrated angular objective also makes the intended directional gradient explicit.
- The experiments demonstrate improvements in overall GenEval and Qwen-Image-Bench scores on both SD3.5-Medium and Z-Image. The component and curriculum ablations provide preliminary evidence supporting the effectiveness of the combined framework.
Critical weaknesses
-
The three components of RoQT largely resemble established training strategies, including timestep curriculum learning, difficulty-based sample reweighting, and angular regularization. In particular, the proposed direction correction is derived directly from the standard flow-matching MSE decomposition and essentially increases the relative strength of directional gradients already present in the original objective. The paper does not sufficiently demonstrate why this particular formulation is preferable to simpler alternatives, such as timestep-weighted flow matching, direct cosine-based regularization, or conventional hard-example weighting. Without comparisons against these alternatives, it is difficult to determine whether the improvement comes from the proposed rotational perspective or from more general loss-reweighting effects.
-
The direction-correction experiment in Figure 1 is used to motivate emphasizing high-noise supervision. However, applying corrections from higher noise levels also affects more ODE integration steps. Consequently, the observed reconstruction improvements cannot be attributed solely to the greater importance of high-noise directional errors. Furthermore, the experiment relies on oracle reference velocities computed using ground-truth clean latents. Equation (5) establishes a relationship between timestep and one-step reconstruction error, but this does not directly establish the optimal supervision allocation along a complete generative trajectory. Additionally, Figure 2(a) shows elevated angular errors near both noise endpoints, which does not immediately explain why training should initially concentrate so heavily on high-noise samples.
-
The micro-level weighting scheme assumes that larger prediction-target angular errors correspond to samples requiring stronger supervision. However, in conditional flow matching, the optimal velocity predictor represents a conditional expectation, and the target velocity may remain ambiguous given the noisy input and conditioning information. As a result, a larger angular error does not necessarily indicate a correctable model deficiency. This issue may be particularly relevant near the noise endpoints, where the available information for predicting an individual sample's target velocity can be limited. The paper does not investigate whether angular difficulty weighting primarily emphasizes learnable prediction errors or potentially amplifies supervision on intrinsically ambiguous samples.
-
The experimental evaluation lacks widely adopted perceptual preference metrics such as PickScore, HPSv2, and ImageReward, relying primarily on GenEval and Qwen-Image-Bench. More importantly, despite approximately 17.2% of the curated fine-tuning dataset belonging to the Text category, the paper does not report dedicated OCR or text-rendering accuracy metrics. This omission is particularly concerning because the proposed curriculum strongly emphasizes high-noise supervision, potentially affecting the balance between global visual aesthetics and fine-grained textual fidelity. Improvements in aesthetics do not necessarily imply improvements in text-rendering accuracy, and the current evaluation cannot rule out potential trade-offs. Moreover, the improvements are not uniform across quality dimensions. On SD3.5-Medium, the Qwen-Image-Bench Quality score slightly decreases from 47.86 to 47.83, despite an improvement in Aesthetics. On Z-Image, Real-world Fidelity decreases from 43.00 to 42.13. The overall Qwen-Image-Bench improvement on SD3.5-Medium is also relatively modest, increasing from 43.53 to 44.04. Given that the primary objective is quality tuning, broader perceptual preference evaluation, dedicated OCR benchmarks, and human preference comparisons would provide substantially stronger evidence for the claimed improvements.
Questions for authors
-
Can the authors provide a controlled experiment separating the effect of high-noise direction correction from the effect of correcting more ODE integration steps? How does this observation directly justify the proposed noise curriculum?
-
How does RoQT compare against simpler alternatives under matched training budgets, including timestep-weighted flow matching, direct cosine regularization, and conventional difficulty-based loss weighting?
-
Can the authors include PickScore, HPSv2, ImageReward, and dedicated OCR/text-rendering evaluations? In particular, does the improvement in aesthetics introduce any trade-off in text-rendering accuracy or other fine-grained generation capabilities?
We thank the reviewer for highlighting the relevance of quality tuning, RoQT's single-pass design, and its empirical gains.
Q1. Technical Novelty and Coordinated Formulation
RoQT's contribution is a lightweight, single-pass framework that coordinates noise allocation (Macro), regional angular-difficulty reweighting (Micro), and scale-calibrated direction correction. The comparisons in Table R2 of our General Response show that generic loss reweighting and standard cosine regularization do not match its performance, supporting the practical value of this coordination.
Q2. Component Contributions and Complementary Gains
Table R1 in our General Response provides the component ablations. Adding Micro to Macro increases GenEval from 0.6711 to 0.6822 and improves all three preference metrics. Removing Macro lowers performance relative to full RoQT, which achieves the highest scores across all five metrics. These comparisons support complementary gains from the components.
Q3. Perceptual Preference, Human Evaluation, and Robustness
We conducted a double-blind human preference evaluation on SD3.5-M using 500 prompts randomly sampled from Qwen-Image-Bench and GenEval. Image pairs used matched training steps; each pair was assessed by at least 5 of 10 raters under a forced-choice protocol (no ties). Across all pairwise evaluations, RoQT achieved 89.0% wins over Base and 71.4% over standard SFT, supporting the preference gains in Table R1. Generation-seed stability is reported in Table R6 (response to Vuzr, Q6).
Q4. Implementation Details and Reproducibility
We will include the following settings in the final version: