Aug 2026· International Conference on Multimedia Analysis and Pattern Recognition· pp. 580-585· 0 citations· 46 references
Abstract
Stable Diffusion models deliver photorealistic image synthesis but face computational bottlenecks that hinder deployment in resource-constrained environments. However, most existing distillation methods for diffusion models rely on point-wise feature matching, which often fails to preserve global semantic structure, or require additional and costly teacher finetuning. To address these limitations, we propose StableKOT — a novel knowledge distillation framework that leverages Optimal Transport (OT) theory. Still, direct OT alignment of high-dimensional feature maps is computationally prohibitive and sensitive to spatial noise. To overcome this issues, we transform teacher-student knowledge transfer into a distribution matching problem, applying OT to max-pooled features augmented with positional embeddings across U-Net layers. This captures geometric relationships in latent space while reducing computational overhead. Empirically, our method reduces parameters by 32.6% and accelerates inference 1.5×, while maintaining generative fidelity.
Few-step distillation reduces the inference cost of image-to-video generation, but directly reusing LoRA adapters trained for long denoising trajectories can weaken their intended effects and degrade video quality. We observe that adapters with similar measured static parameter geometry can behave differently under the...
Shi-Hong Li, Jun-Tao Xu, Cao Jin et al.· 0 citations
High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient methods mainly distill pretrained models into few-step samplers, a challenging process that depends heavily on teacher-model quality. In this pape...
Jin-Xiu Liu, Xuan Liu, Kang-Fu Mei et al.· 0 citations
Image morphing aims to produce a smooth and semantically consistent transition between two input images. Existing diffusion-based morphing methods either require expensive per-pair optimization or rely on implicit spatial alignment, which easily fails under large layout discrepancies. To address these limitations, we p...
Wu-Yi Liu, Xu Han, Yu-Ren Chen et al.· 0 citations
Structural Parameter-free Affinity Regularization (SPARE), a regularizer that matches the pairwise affinities of intermediate tokens to those of the clean latents across images, is proposed, a regularizer that attains the lowest FID among parameter-free regularizers in every tested setting.
Zong-Wei Hong, Jinglun Li, Shen Zhang et al.· 1 citation
LinCa decomposes cached features into sub-components with distinct continuity properties via a lightweight invertible network and applies differentiated prediction orders matched to each component, forming a unified Decompose-Predict-Reconstruct pipeline.
Jin-Shan Liu, Hao-Ran Qin, Xiao-Bing Tu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
