- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper focuses on accelerating text-to-image generation through few-step diffusion distillation. The authors observe that linear shortcuts poorly approximate curved teacher trajectories, which can reduce image quality and diversity in few-step generation. They therefore propose ArcFlow, which models nonlinear trajectories using continuous momentum mixtures, integrates them analytically, and learns them through lightweight adapters. To validate the method, they conduct several experiments, including benchmark comparisons on Qwen-Image and FLUX, trajectory analyses, convergence comparisons, and component ablations. The results show that ArcFlow enables two-step generation, preserves diversity, and achieves faster convergence.
Critical strengths
-
This paper proposes ArcFlow, which constructs a closed-form nonlinear flow trajectory to approximate the teacher trajectory.
-
To simplify training, the authors propose an analytic trajectory solver for ArcFlow.
-
The paper conducts a range of experiments to demonstrate ArcFlow's advantages across different backbones.
Critical weaknesses
-
Section 1 claims that ArcFlow is "the first distillation framework to explicitly construct a closed-form non-linear flow trajectory to approximate the teacher trajectory." However, "Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory" (NeurIPS 2025) already evolves states in closed form, , within a learned latent space. These trajectories are not straight lines. HKD is trained on PF-ODE trajectories from a pretrained EDM teacher (Alg. 1; Eq. (6)). ArcFlow's interval trajectory is likewise a superposition of exponential modes, yet the paper does not discuss this work. The priority claim therefore needs qualification.
-
The Abstract claims generation "without significant quality degradation" at 2 NFEs. However, Table 1 reports that the FLUX text score drops from 0.556 to 0.368. This substantial decline does not support such a broad preservation claim.
-
The claimed 40× inference speedup lacks a measured comparison with the teacher. The main text reports no latency results, and NFE counts alone do not establish the claimed wall-clock speedup.
-
The 2-NFE baselines in Tables 1 and 2 are not fully specified. Section 4.2 notes that official pi-Flow checkpoints support only 4 NFEs, while the official Qwen-Image-Lightning repository releases only 4- and 8-step LoRAs. The paper does not state whether these baselines were retrained at 2 NFEs or simply run below their distilled step counts, nor does it explain how their training budgets compare with ArcFlow's. The reported 2-NFE advantages may therefore partly reflect a mismatch in step count or training budget.
-
The core claim attributes quality degradation to linear shortcuts that cannot follow the teacher's changing tangents. However, a few-step sampler uses only interval endpoints, and a linear step with the correct average velocity can reach any endpoint. ArcFlow's own update, , is likewise a single displacement. Section 4.3 compares velocity changes at adjacent teacher timesteps and intermediate latent states with Qwen-Image-Lightning, which a constant-velocity student cannot match by construction. The linear control in Section 4.3 is trained under matched settings, i.e., to match instantaneous teacher velocities (Eq. (6)), which a constant velocity cannot satisfy. Its performance gap is nonetheless attributed to the "limited expressiveness" of linear modes. No linear student trained on the teacher's interval displacement under the same budget is reported. Thus, the benefit of nonlinear trajectories over a properly trained linear step remains untested.
Questions for authors
-
Could the authors distinguish ArcFlow's momentum-based velocity parameterization from HKD's closed-form latent evolution and trajectory supervision? Please narrow the first-framework claim accordingly.
-
Could the authors qualify the quality-preservation claim and report teacher-student comparisons with uncertainty, especially for text rendering? Please distinguish preserved capabilities from degraded ones.
-
Could the authors report teacher and student latency under identical hardware, precision, batch size, and guidance settings? Please clarify how the 40× factor was obtained.
-
Could the authors specify the checkpoint, native step count, and training budget of each 2-NFE baseline? Please compare pi-Flow and Qwen-Image-Lightning at their native step counts, or after retraining them at 2 NFEs under a matched budget.
-
Could the authors compare ArcFlow with a student trained to regress the teacher's interval displacement using the same teacher-supervision budget per update? Please report results at the final training budget.