One little-explored frontier of image generation and editing is the task of interpolating between two input images, a feature missing from all currently deployed image generation pipelines. We argue that such a feature can expand the creative applications of such models, and propose a method for zero-shot interpolation using latent diffusion models. We apply interpolation in the latent space at a sequence of decreasing noise levels, then perform denoising conditioned on interpolated text embeddings derived from textual inversion and (optionally) subject poses. For greater consistency, or to specify additional criteria, we can generate several candidates and use CLIP to select the highest quality image. We obtain convincing interpolations across diverse subject poses, image styles, and image content, and show that standard quantitative metrics such as FID are insufficient to measure the quality of an interpolation. Code and data are available at https://clintonjwang.github.io/interpolation.

翻译：图像生成与编辑领域中一个尚未充分探索的前沿课题是：如何在两张输入图像之间进行插值，这是当前所有已部署的图像生成流程中缺失的功能。我们认为，该功能可以扩展此类模型的创意应用，并提出了一种利用潜在扩散模型实现零样本插值的方法。我们在逐步降低噪声水平的潜在空间中执行插值，随后基于从文本反演（以及可选的物体姿态）中导出的插值文本嵌入进行去噪处理。为提升一致性或满足附加标准，我们可以生成多个候选结果，并利用CLIP选择质量最高的图像。我们获得了涵盖不同物体姿态、图像风格与图像内容的令人信服的插值结果，同时表明，诸如FID等标准定量指标不足以衡量插值的质量。代码与数据可通过https://clintonjwang.github.io/interpolation获取。