DreamVideo：用自定主題和動作創作您的夢幻影片

摘要

使用擴散模型進行定制生成在圖像生成方面取得了令人印象深刻的進展，但在具有挑戰性的視頻生成任務中仍然不夠滿意，因為它需要對主題和動作的可控性。為此，我們提出了DreamVideo，這是一種從幾張所需主題的靜態圖像和幾個目標運動的視頻生成個性化視頻的新方法。DreamVideo將這一任務分解為兩個階段，即主題學習和運動學習，通過利用預訓練的視頻擴散模型。主題學習旨在從提供的圖像中準確捕捉主題的精細外觀，這是通過結合文本反演和我們精心設計的身份適配器的微調來實現的。在運動學習中，我們設計了一個運動適配器並在給定的視頻上進行微調，以有效地建模目標運動模式。結合這兩個輕量級和高效的適配器，可以靈活定制任何主題和任何運動。大量的實驗結果證明了我們的DreamVideo在定制視頻生成方面優於當前最先進的方法。我們的項目頁面位於https://dreamvideo-t2v.github.io。

English

Customized generation using diffusion models has made impressive progress in image generation, but remains unsatisfactory in the challenging video generation task, as it requires the controllability of both subjects and motions. To that end, we present DreamVideo, a novel approach to generating personalized videos from a few static images of the desired subject and a few videos of target motion. DreamVideo decouples this task into two stages, subject learning and motion learning, by leveraging a pre-trained video diffusion model. The subject learning aims to accurately capture the fine appearance of the subject from provided images, which is achieved by combining textual inversion and fine-tuning of our carefully designed identity adapter. In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern. Combining these two lightweight and efficient adapters allows for flexible customization of any subject with any motion. Extensive experimental results demonstrate the superior performance of our DreamVideo over the state-of-the-art methods for customized video generation. Our project page is at https://dreamvideo-t2v.github.io.

DreamVideo：用自定主題和動作創作您的夢幻影片

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

摘要

Support