Make-A-Video

Make-A-Video is an AI system that generates videos from text. It builds on progress in text-to-image generation and uses images with descriptions to learn what the world looks like and how it is often described. It also uses unlabeled videos to learn how the world moves. With this data, Make-A-Video lets you bring your imagination to life by generating whimsical, one-of-a-kind videos with just a few words or lines of text.

Make-A-Video lets you bring your imagination to life by generating whimsical, one-of-a-kind videos with just a few words or lines of text. It can produce different rendering styles such as surreal, realistic, and stylized representations.

From static to magic, Make-A-Video adds motion to a single image or fills in the in-between motion to two images, enabling creative video generation from limited inputs.

The project discusses inputs like single images, pair of images, input image, input videos, and the resulting Make-A-Video output, emphasizing variations and creative output.

Use cases

• Generate video content from text prompts for exploration
• Create variations of an existing video for creative exploration