Distilling large latent diffusion models (LDMs) into ones that are fast to
sample from is attracting growing research interest. However, the majority of
existing methods face a dilemma where they either (i) depend on multiple
individual distilled models for different sampling budgets, or (ii) sacrifice
generation quality with limited (e.g., 2-4) and/or moderate (e.g., 5-8)
sampling steps. To address these, we extend the recent multistep consistency
distillation (MCD) strategy to representative LDMs, establishing the Multistep
Latent Consistency Models (MLCMs) approach for low-cost high-quality image
synthesis. MLCM serves as a unified model for various sampling steps due to the
promise of MCD. We further augment MCD with a progressive training strategy to
strengthen inter-segment consistency to boost the quality of few-step
generations. We take the states from the sampling trajectories of the teacher
model as training data for MLCMs to lift the requirements for high-quality
training datasets and to bridge the gap between the training and inference of
the distilled model. MLCM is compatible with preference learning strategies for
further improvement of visual quality and aesthetic appeal. Empirically, MLCM
can generate high-quality, delightful images with only 2-8 sampling steps. On
the MSCOCO-2017 5K benchmark, MLCM distilled from SDXL gets a CLIP Score of
33.30, Aesthetic Score of 6.19, and Image Reward of 1.20 with only 4 steps,
substantially surpassing 4-step LCM [23], 8-step SDXL-Lightning [17], and
8-step HyperSD [33]. We also demonstrate the versatility of MLCMs in
applications including controllable generation, image style transfer, and
Chinese-to-image generation.

将大型潜在扩散模型（LDMs）提炼为快速采样模型是一个备受关注的研究领域，本文通过扩展最新的多步一致性提炼（MCD）策略，建立了用于低成本高质量图像合成的多步潜在一致性模型（MLCM）。MLCM 通过与强调联合段一致性的渐进训练策略相结合，能够提高少步骤生成的质量。实验结果表明，MLCM 仅需 2-8 个采样步骤即可产生高质量、令人愉悦的图像，比 4 步骤的 LCM、8 步骤的 SDXL-Lightning 和 8 步骤的 HyperSD 显著优越；此外，MLCM 还在可控生成、图像风格转移和中文到图像生成等方面展示了其多功能性。