Recent progress with conditional image diffusion models has been stunning, and this holds true whether we are speaking about models conditioned on a text description, a scene layout, or a sketch. Unconditional image diffusion models are also improving but lag behind, as do diffusion models which are conditioned on lower-dimensional features like class labels. We propose to close the gap between conditional and unconditional models using a two-stage sampling procedure. In the first stage we sample an embedding describing the semantic content of the image. In the second stage we sample the image conditioned on this embedding and then discard the embedding. Doing so lets us leverage the power of conditional diffusion models on the unconditional generation task, which we show improves FID by 25-50% compared to standard unconditional generation.

翻译：近年来，条件图像扩散模型取得了令人瞩目的进展——无论是依赖于文本描述、场景布局还是草图的条件模型，其表现都十分出色。非条件图像扩散模型虽有改进但仍显不足，同样表现滞后的还有依赖类别标签等低维特征的条件扩散模型。我们提出用两阶段采样流程来弥合条件模型与非条件模型之间的性能差距：第一阶段采样描述图像语义内容的嵌入向量，第二阶段基于该嵌入向量对图像进行条件采样，随后丢弃该嵌入向量。这种方法使我们能够在非条件生成任务中发挥条件扩散模型的能力，实验表明相较于标准非条件生成方法，FID指标可提升25-50%。