ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation

arXiv:2310.07697v2 Announce Type: replace
Abstract: Recent works have successfully extended large-scale text-to-image models to the video domain, producing promising results but at a high computational cost and requiring a large amount of video data. In this work, we introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text, by leveraging the power of off-the-shelf text-to-image generation methods (e.g., Stable Diffusion). ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our …

abstract arxiv computational cost cs.cv data domain free image replace results scale text text-to-image text-to-video training type video video data video generation work