通过精准选择目标步数，提升扩散模型生成图像的清晰度与灵活性。
Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance
- 采用精细化目标步数选择策略，提高训练效率
- 支持推理阶段调节指导尺度，生成效果更可控
- 可选非等距采样和x0裁剪，生成更准确
一致性蒸馏方法在加速扩散模型生成任务方面表现优异。然而，以往方法在目标步数选择上采用简单直接的策略，常导致生成图像模糊、细节丢失。为此，我们提出目标驱动蒸馏（TDD），其一，采用精细的目标步数选择策略，提升训练效率；其二，在训练中使用解耦引导机制，使TDD可在推理阶段灵活调整指导尺度；其三，可选非等距采样与x0裁剪，实现更灵活、精确的图像采样。实验表明，TDD在少步生成任务中达到当前最优性能，是一致性蒸馏模型中的更优选择。
原文摘要 · Abstract (English)
Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation methods use simple and straightforward strategies in selecting target timesteps, they usually struggle with blurs and detail losses in generated images. To address these limitations, we introduce Target-Driven Distillation (TDD), which (1) adopts a delicate selection strategy of target timesteps, increasing the training efficiency; (2) utilizes decoupled guidances during training, making TDD open to post-tuning on guidance scale during inference periods; (3) can be optionally equipped with non-equidistant sampling and x0 clipping, enabling a more flexible and accurate way for image sampling. Experiments verify that TDD achieves state-of-the-art performance in few-step generation, offering a better choice among consistency distillation models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。