- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a personalization method for few-step diffusion models to learn user-specified attributes. The authors argue that prior work, which relies on indirect supervision from a teacher model, lacks sufficient signals for image quality. To address this limitation, the authors introduce SRA, which incorporates rewards using DINOv3 and TOPIQ during personalization, applies them at each timestep, and adjusts their weights according to the sampling schedule. The method is evaluated on Z-Image-Turbo and FLUX.2-klein. Further ablation studies examine the effects of individual components of the proposed method.
Critical strengths
The paper is well-organized, and both the writing and figures are easy to follow. The experiments aim to examine the individual components of the proposed method in detail. The authors show that explicitly introducing rewards leads to better image quality metrics than learning generation quality indirectly through the teacher model in D-OPSD.
Critical weaknesses
The authors argue that the designed rewards, based on DINOv3 and TOPIQ, improve the personalization of few-step diffusion models. However, while the method improves image quality metrics, the text-image alignment score (CLIP-S) is lower than that of D-OPSD. Table 4 also reports only image metrics such as DINO and Quality-S. These results make it difficult to assess whether the proposed method improves key aspects of personalization, including prompt alignment.
The experimental setting differs from that of D-OPSD, the main baseline used in this paper. The original D-OPSD paper evaluates 30 subjects and 10 styles in its personalization experiments, while SRA uses 10 subjects and 10 styles in Table 1. This difference also makes the results more difficult to interpret. Since the proposed method extends D-OPSD by introducing additional rewards, the overall evaluation should also include the original D-OPSD setting to establish its improvements.
Questions for authors
The paper presents the proposed method in a logical structure, but further validation is needed to establish its effectiveness. The following questions address the weaknesses discussed above: Can the proposed rewards improve overall personalization performance, including prompt adherence? How does the proposed method perform under the same experimental settings as the other baselines? What are the overall trends across evaluation metrics in Tables 3–6, beyond the selected metrics reported?
5 comments
Response to Reviewer XckW. Part [2/3]
Q3. What are the overall trends across evaluation metrics in Tables 3–6, beyond the selected metrics reported?
Thank you for this suggestion on the overall trends. We have scored every configuration of Tables 3 to 5 on eleven metrics, the paper's seven plus PickScore [2], ImageReward [3], CLIP-I [4] and SigLIP-I [5]. We report them in full in Appendix C.1, Appendix E.2 and Appendix E.4. On the validation and test cases of Tables 3 and 4, the metrics fall into two groups relative to D-OPSD: those that read the reference or image quality (DINO-D, DINOv3 [6], Quality-S, Aesthetic-S, VLM-J, CLIP-I and SigLIP-I) improve with SRA, and the prompt-based metrics (CLIP-S, PickScore and ImageReward) decline, more so as κ grows. LPIPS-D ↓ [7] is 0.7216 to 0.7253 along Table 3 and 0.7736 against 0.7662 for D-OPSD on the test cases. Table 6 shows the same pattern over three seeds for the seven paper metrics, and in Table 5 SRA scores highest on the metric each recipe rewards.
Over the thirty DreamBooth subjects, VLM-J ↑ does not rise on Z-Image-Turbo (1.446 against 1.575, General Response #4). The metrics that Tables 3 and 4 do not show, on Z-Image-Turbo, one training run per configuration:
| Configuration | VLM-J ↑ | CLIP-S ↑ | Aesthetic-S ↑ | PickScore ↑ | ImageReward ↑ | CLIP-I ↑ | SigLIP-I ↑ |
|---|---|---|---|---|---|---|---|
| Table 3, D-OPSD (κ = 0) | 1.453 | 0.3227 | 5.303 | 22.36 | 1.002 | 0.6435 | 0.6958 |
| Table 3, SRA, κ = 0.1 | 1.566 | 0.3210 | 5.618 | 22.20 | 0.948 | 0.6554 | 0.7070 |
| Table 3, SRA, κ = 0.3 | 1.762 | 0.3191 | 5.628 | 21.94 | 0.794 | 0.6645 | 0.7180 |
| Table 3, SRA, κ = 0.6 | 1.922 | 0.3136 | 5.556 | 21.53 | 0.457 | 0.6785 | 0.7300 |
| Table 4, D-OPSD | 1.570 | 0.3099 | 5.315 | 22.29 | 1.015 | 0.6767 | 0.7380 |
| Table 4, SRA | 1.781 | 0.3078 | 5.688 | 21.82 | 0.754 | 0.6967 | 0.7668 |
Response to Reviewer XckW. Part [3/3]
W2. The experimental setting differs from that of D-OPSD, the main baseline used in this paper. The original D-OPSD paper evaluates 30 subjects and 10 styles in its personalization experiments, while SRA uses 10 subjects and 10 styles in Table 1. This difference also makes the results more difficult to interpret. Since the proposed method extends D-OPSD by introducing additional rewards, the overall evaluation should also include the original D-OPSD setting to establish its improvements.
Q2. How does the proposed method perform under the same experimental settings as the other baselines?
Thank you for this suggestion on the original D-OPSD setting. Every method in our tables, D-OPSD included, is retrained by us under one protocol and scored with D-OPSD's four metrics (DINO-D, LPIPS-D, CLIP-S and VLM-J) plus ours, so the comparisons are like for like. D-OPSD's thirty subjects are the public DreamBooth [8] set. The submission used fourteen of them (the ten of Table 1 and four test subjects), and we have now trained all thirty on both base models. Over the thirty subjects SRA has the best mean on all three reward-related metrics on both base models, for example DINO-D ↓ 0.1198 against D-OPSD's 0.1699 on Z-Image-Turbo (General Response #4). We have added these results to Appendix E.2 (New test cases). D-OPSD's ten styles were not released as a set, and its Quality-S and Aesthetic-S come from an internal reward model that is not public, so for styles we use ten public UnlearnCanvas [9] styles.
We thank you again for your valuable comments. If you have any further questions, please let us know, and we will do our best to respond. We hope our responses address your concerns, and we would be grateful if you would take them into account in your final evaluation.
References
[1] D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models.
[2] Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation.
[3] ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation.
[4] Data Filtering Networks.
[5] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.
[6] DINOv3.
[7] The Unreasonable Effectiveness of Deep Features as a Perceptual Metric.
[8] DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation.
[9] UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models.
Response to Reviewer XckW. Part [1/3]
We sincerely thank the reviewer for the time and patience given to this review, and for the constructive questions on prompt alignment and the evaluation setting.
Thank you for raising prompt alignment. Our reward targets reference fidelity and image quality and contains no prompt term, and its cost on CLIP-S grows with the reward strength κ. At κ = 0.1, SRA's CLIP-S ↑ is 0.3210 and 0.3347 against D-OPSD's 0.3227 and 0.3354 on the two base models, while SRA still leads D-OPSD [1] on all three reward-related metrics (General Response #5). The new human study also asks which image better matches the prompt. On this question, participants do not prefer D-OPSD on either base model. SRA's rate is 62.5% on Z-Image-Turbo and 58.1% on FLUX.2-klein-4B, and about half of the judgments are ties. They prefer SRA on reference fidelity, image quality and overall (General Response #3). As suggested, we have added CLIP-S and VLM-J to Tables 3 and 4. On the eight test cases SRA's CLIP-S ↑ is 0.3078 against D-OPSD's 0.3099.