- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses an interesting and practical problem at inference time: how to generate a batch of images that maintains high visual diversity while ensuring the worst image in the batch still meets a certain reward threshold. To solve this, they propose SatisDive, a training-free latent optimization method. The technique cleverly uses per-image reward floors and batch diversity constraints, applying batch-relative cutoffs for penalties and replacing consistently poor candidates in the late stages of generation. The results on Pick-a-Pic and HPDv2 are convincing, showing clear improvements over FK steering in worst-case reward at matched diversity levels.
Critical strengths
1.Clear formulation. By decoupling per-image reward requirements from batch-level diversity, the paper makes the intended trade-off highly intuitive. Furthermore, the theoretical analysis offers a solid interpretation of the method's behavior, clearly scoped within its stated assumptions.
2.The proposed method of boosting the reward of weaker candidates while diversifying the stronger ones works well in practice. The empirical Pareto curves convincingly show that it achieves a better worst-candidate reward than FK steering at matched diversity.
Critical weaknesses
-
While pairwise cosine distances of pooled backbone features serve as a reasonable proxy for diversity, they risk overlooking nuanced semantic variations. More critically, computing pairwise distances across all images in a group incurs a computational overhead that scales quadratically with group size, making it increasingly prohibitive for larger groups.
-
Higher computational overhead. As shown in Table 14, it takes 60.8 seconds per prompt compared to 37.7 seconds for FK steering, alongside higher GPU memory consumption. These timings are averaged over only three prompts at a small batch size (K=4), which means this method may not generalize well to larger batch sizes under acceptable time and gpu costs.
Questions for authors
-
How sensitive are the results to diversity and reward cutoffs? Do these hyperparameter settings generalize to other baseline models without extensive retuning? Additionally, what is the recommended strategy for selecting appropriate cutoff values in practice?
-
What is the rationale behind choosing cosine distance for measuring diversity? Have you evaluated the model's performance using alternative diversity measures?
3 comments
Thank you for the response. But my concerns about the computation overload and generalizability of the proposed method remain unresolved.
We thank the reviewer for the follow-up. We further clarify our response.
Computational costs. Although SatisDive is more computationally expensive than FK steering, it achieves higher worst-candidate reward at matched diversity on FLUX/HPSv3 and SANA/ImageReward (Figure 3), as the reviewer notes. The additional computation comes from forward and backward evaluations through the generator to calculate the reward and diversity updates used to guide each candidate. The reported runtime comparison therefore does not establish that FK steering achieves the same reward–diversity outcome at lower cost.
Furthermore, although the number of pairwise cosine comparisons grows quadratically with batch size, we cache and reuse the pooled feature vectors obtained during each candidate’s forward pass. Each additional comparison therefore requires only inexpensive vector calculations, without another forward or backward evaluation through the generator. The costly generator evaluations grow with the number of candidates rather than the number of pairs, which explains the approximately linear total runtime observed on SD1.5: 29.73, 58.69 and 118.84 seconds per prompt for 4, 8 and 16 candidates, respectively. Sampled GPU memory increases from 12.33 to 22.58 GiB between four and sixteen candidates, as shown in Appendix D.15.
Appendix D.1 also reports output quality for SD1.5/ImageReward at : SatisDive achieves DreamSim of 0.77 versus FK steering’s 0.45, with average worst-candidate reward of 0.41 versus 0.69. Thus, SatisDive’s diversity benefit extends to this larger batch size, with a corresponding reduction in worst-candidate reward.
Transfer across backbones without retuning. Regarding generalizability of across base models, our ImageReward experiments (Tables 3, 12 and 13) use the same across FLUX, SANA, and SD1.5, without backbone-specific retuning of . At this setting, SatisDive achieves higher DreamSim than FK steering on all three backbones, with comparable satisfaction rate to FK steering on FLUX and higher satisfaction rate than FK steering on SANA and SD1.5.
Sensitivity to reward tolerance. We additionally illustrate how affects the results with an example. Consider a candidate whose reward is 0.6 less than the batch's highest. If , this candidate falls below the reward cutoff (since 0.6 > 0.3) and incurs a larger reward penalty. In contrast, if , that same candidate is above the cutoff and is weighted more in the diversity penalty. The tradeoff is visible on SANA in Table 3, in which increasing from 0.3 to 0.75 improves DreamSim from 0.591 to 0.658, while average worst-candidate reward falls from 1.29 to 1.13.
For practical selection of , we compute the difference between the highest and lowest rewards in each base-model batch and use about 75% of the median of these differences as a starting value.
Automatic diversity-cutoff selection. The diversity cutoff is designed to not require a separate tuning search. As specified in Appendix C, is computed automatically from the median pairwise feature distance among candidates at the first gradient update step. For a given batch, changing scales the diversity gradient magnitude without changing its direction. We normalize the reward and diversity gradients separately so that differences in their numerical scales do not make one dominate the latent update. Since changing only changes the diversity gradient’s magnitude, this normalization also means that changing does not alter a given candidate’s diversity update. A separate search over would therefore add tuning work without changing these updates. Thus, we can instead adjust to choose the reward–diversity tradeoff.
Alternative diversity guidance. Our original response explained the choice of cosine distance. We now additionally test LPIPS during guidance, rather than only using perceptual metrics to evaluate the final images. We compared both settings on the same 100 Pick-a-Pic prompts using SD1.5/ImageReward, and .
| Diversity guidance | Mean worst-candidate ImageReward ↑ | Mean pairwise DreamSim ↑ |
|---|---|---|
| Pooled-feature cosine distance | 0.335 | 0.743 |
| LPIPS | 0.330 | 0.756 |
Both guidance choices produce similar observed reward–diversity results in this setting, providing a tested alternative to cosine-based guidance.
We hope these explanations and additional results clarify SatisDive’s computational costs and generalizability. We would be happy to address any further questions.
We thank the reviewer for recognizing the clear formulation and the improvements in worst-candidate reward at matched diversity.
Response: (a) Cost as batch size grows. Although the number of pairwise distances grows quadratically, our SD1.5 measurements show that doubling the batch size approximately doubles the total runtime of both SatisDive and FK steering over K=4,8,16. We measured runtime and GPU memory on 50 prompts, using the same RTX A6000 GPU, prompts and starting seeds.
Time is mean ± standard deviation; memory is the largest sampled GPU memory usage. The full profiling protocol is in Appendix D.15.
(b) Expanded FLUX timing. We have replaced the three-prompt estimate with measurements on 50 prompts, using the same two A100 80 GB GPUs for both methods:
SatisDive achieves higher worst-candidate reward at matched diversity (Figure 3), with 1.87× FK steering's runtime in the FLUX timing study.
Response: (a) Cutoff sensitivity. Δ controls the allowed reward gap from the batch maximum. Figure 3 shows how varying Δ changes the reward–diversity tradeoff: smaller values favor higher worst-candidate reward, while larger values permit greater diversity. Changing the diversity cutoff δ does not make the diversity step larger or smaller, because we normalize each nonzero diversity gradient as described in Appendix C.
(b) Cutoff selection and transfer. For each prompt, we subtract the lowest reward from the highest reward in the base model's batch. We use about 75% of the median of these differences as a starting value for Δ. We initialize δ from the median pairwise feature distance at the first update. We use the same selection rules across FLUX, SANA and SD1.5, including FLUX/HPSv3 on both Pick-a-Pic and HPDv2. We compute the cutoffs for each setting rather than reuse the same numerical values.
Response: Cosine distance compares feature directions without treating larger feature norms as greater diversity, and it is differentiable for latent guidance. Cosine similarity is also used by NegToMe to match diffusion features and by CNO in its contrastive objective on denoised latent predictions.
Although pooled-feature cosine distance may miss some semantic differences, we evaluate the final images separately with the standard perceptual metrics DreamSim and LPIPS. NegToMe also evaluates diversity with DreamSim, while DAS uses LPIPS. Both metrics show greater diversity than FK steering in the FLUX/HPSv3 comparison (Table 1):
Thus the measured diversity improvement is not specific to the internal cosine distance used for guidance.