We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel finetuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. We evaluate our method on a variety of clothing styles and poses, and demonstrate that our method produces state-of-the-art results on fashion video animation. Video results are available on our project page.

翻译：---- 我们提出了一个基于扩散的方法DreamPose，用于从静止的图像生成动画时尚视频。给定一张图像和一个人体姿势序列，我们的方法合成一个包含人体和织物运动的视频。为了实现这一点，我们将预训练的文本到图像模型（Stable Diffusion）转化为一个姿势和图像引导的视频合成模型，使用一种新颖的微调策略，一组架构变化来支持添加的调节信号，以及鼓励时间一致性的技术。我们在UBC时尚数据集的一组时尚视频上进行微调。我们评估了我们的方法在各种服装风格和姿势上的表现，并证明我们的方法在时尚视频动画方面产生了最先进的效果。视频结果可以在我们的项目页面上获得。