超级会员免费看
苹果 宾夕法尼亚
摘要
Diffusion models have demonstrated excellent potential for generating diverse images.
However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as are medy which can reduce the number of inference steps to one or a few, without significant quality degradation.
However, existing distillation methods either require significant amounts of offline computation for generating synthetic training data from the teacher model, or need to perform expensive online learning with the help of real data.
In this work, we present a novel technique called BOOT , that overcomes these limitations with an efficie
However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as are medy which can reduce the number of inference steps to one or a few, without significant quality degradation.
However, existing distillation methods either require significant amounts of offline computation for generating synthetic training data from the teacher model, or need to perform expensive online learning with the help of real data.
In this work, we present a novel technique called BOOT , that overcomes these limitations with an efficie
订阅专栏 解锁全文
787
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
