pschaldenbrand / Text2Video

A fast approach for translating a series of text prompts into a video. The 2022 NeurIPS Workshop on Machine Learning for Creativity and Design

Towards Real-Time Text2Video via CLIP-Guided, Pixel-Level Optimization

Peter Schaldenbrand, Zhixuan Liu, and Jean Oh. The Robotics Institute, Carnegie Mellon University

Read our paper on ArXiv

An approach to generating videos based on a series of given language descriptions of the video. We currently only have a Colab implementation which is linked above.

Please message Peter at pschalde at andrew dot cmu dot edu with any questions or make a GitHub issue. Thanks!