- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper focuses on guidance control for flow-based text-to-image generation. The authors find that coupling guidance direction and magnitude limits local strength control and allows excessive spatial and temporal variation. They therefore propose CtrlGen, a training-free method that preserves guidance direction while regulating its magnitude using an explicit spectral solution. To validate their method, they conduct several experiments, including comparisons on MS-COCO across three generators, component ablations, and guidance-scale robustness tests.The experimental results demonstrate that CtrlGen improves text alignment and preference scores across the evaluated models.
Critical strengths
-
This paper proposes CtrlGen, which decomposes guidance into direction and magnitude and treats the local magnitude as a control variable.
-
The authors formulate the magnitude update as a convex control problem that admits an explicit spectral solution without iterative optimization.
-
They evaluate the method on three different flow-based text-to-image models, and it introduces negligible computational overhead without requiring retraining.
Critical weaknesses
-
My main concern is that every baseline entry in Table 1 is identical to Table 2 of "CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance" (Wang et al., 2026), which introduced SMC-CFG. The paper does not state whether these values were reused, although Section 4.1 claims shared sampling settings and seeds for all methods. In Figure 3, the baselines' points match these values and show a sharp drop in MPS, whereas their and points approach CtrlGen. Notably, CtrlGen's large gains in Table 1 are concentrated in MPS, the very metric showing this drop. If the baselines come from a different pipeline, the margins reported in Table 1 and Figure 1(c) are not directly comparable.
-
Even within a single pipeline, Table 1 compares all methods at only one guidance scale per backbone, and SMC-CFG and APG are not swept in Figure 3. Moreover, Eq. (9) shrinks the zero-frequency magnitude by , roughly sixfold on FLUX.1-dev and Qwen-Image and twofold on SD3.5L under the default settings in Section 4.1. Equal nominal therefore does not imply equal guidance strength, and the reported margins depend on the chosen operating point.
-
The training-free feedback contribution is not clearly positioned against existing control-based guidance. CFG-Ctrl, cited only as a baseline, already treats CFG in flow models as feedback control with separate gain and direction operators. Section 2 does not clearly distinguish CtrlGen's contribution, namely a spatially varying magnitude with a closed-form solution, from this setting.
-
Section 1 claims that guidance strength is difficult to control without changing the model-predicted correction orientation. However, positive scalar CFG already preserves local correction directions. This motivation therefore does not establish direction preservation as a distinguishing contribution.
-
The title frames CtrlGen as an optimal-control method, yet the optimality applies only to a hand-designed per-step objective with no term tied to generation quality, and Section 3.4 concedes that it is not trajectory-level. Its solution is a fixed spectral filter, so the framing overstates the theoretical contribution.
Questions for authors
-
Could the authors state whether the baseline results in Table 1 were reused from CFG-Ctrl and confirm that all methods share the same prompts, seeds, sampler, step count, and metric implementations? If reused, please rerun the baselines in the same pipeline and explain the drop in Figure 3.
-
Could the authors compare all methods, including SMC-CFG and APG, at their best-tuned or effective-strength-matched guidance scales across all three backbones?
-
Could the authors clarify which aspects of the training-free feedback formulation are new relative to CFG-Ctrl? Please distinguish their objectives, control variables, and solvers.
-
Could the authors revise this motivation and distinguish spatial magnitude regulation from CFG's existing direction preservation? Please specify which compared methods actually alter local correction directions.
-
Could the authors clarify how optimality under Eq. (4) relates to generation quality, or otherwise qualify the optimal-control framing?