ModelScope Text-to-Video Technical Report
This work addresses video generation from text, a key challenge in AI for content creation, but it is incremental as it builds on existing text-to-image models.
The paper tackles text-to-video synthesis by evolving Stable Diffusion into ModelScopeT2V, which uses spatio-temporal blocks for consistent frames and smooth transitions, achieving superior performance over state-of-the-art methods across three evaluation metrics.
This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and smooth movement transitions. The model could adapt to varying frame numbers during training and inference, rendering it suitable for both image-text and video-text datasets. ModelScopeT2V brings together three components (i.e., VQGAN, a text encoder, and a denoising UNet), totally comprising 1.7 billion parameters, in which 0.5 billion parameters are dedicated to temporal capabilities. The model demonstrates superior performance over state-of-the-art methods across three evaluation metrics. The code and an online demo are available at \url{https://modelscope.cn/models/damo/text-to-video-synthesis/summary}.