做扩散模型轻量化或模型压缩的团队，终于有了一个在极端压缩下仍能稳定训练的蒸馏方案，值得直接复现实验。
该研究提出了一种名为 LIFT and PLACE 的知识蒸馏框架，用于训练轻量级扩散模型。LIFT 将蒸馏过程分解为粗对齐和细调优两个阶段，先让学生模型学习教师模型的整体分布，再处理细节。PLACE 则通过分组自适应系数处理空间非均匀误差，进一步提升了蒸馏效果。实验表明，该方法在图像/潜空间、U-Net/DiT 骨干网络、条件/无条件生成等场景下均有效，甚至在极端压缩（学生模型仅 1.3M 参数，为教师的 1.6%）时，传统蒸馏方法失效（FID 高达 50-200+），而新方法仍能稳定收敛并达到 FID 15.73。
LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models
We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully mimic. To address this problem, we propose a coarse-to-fine distillation framework with LInear FiTtingbased distillation (LIFT) and Piecewise Local Adaptive Coefficient Estimation (PLACE). First, LIFT decomposes the objective into a "coarse" alignment and a "fine" refinement. The student is then trained on coarse alignment before proceeding to hard refinement. Second, PLACE extends LIFT to address spatially non-uniform errors by partitioning outputs into error-based groups, providing locally adaptive guidance. Our experiments show that LIFT and PLACE is effective across diffusion spaces (image/latent), backbones (U-Net/DiT), tasks (unconditional/conditional), datasets, and even extends to flow-based models such as MMDiT (SD3). Furthermore, under extreme compression with a 1.3M-parameter student (only 1.6% of the teacher), conventional KD fails to provide sufficient guidance for stable training, with FID scores often degrading to 50-200+, but our method remains stably convergent and achieves an FID of 15.73.