Make A Video

What is Make A Video?

Make-A-Video is a system from Meta AI that generates videos from simple text descriptions and still images. It builds on text-to-image technology, but instead of producing a single picture, it generates actual video. The goal is to let anyone create videos with just a few words.

With Make-A-Video you can:

• Text to Video: Create videos directly from text prompts.
• Animate Still Images: Add motion to a single picture.
• Video Variations: Generate different versions of an original video.
• Image-to-Image Motion: Fill in the motion between two images.

Example outputs described by Meta include hyper-realistic scenes like a spaceship landing on Mars or a dog in a superhero outfit flying through the sky, as well as more whimsical ones like a teddy bear painting, a robot dancing in Times Square, or a baby sloth figuring out a laptop.

Meta AI emphasizes responsible use: the system follows secure release procedures, works to prevent the creation of harmful or misleading content, and every video generated with Make-A-Video carries a watermark indicating it is AI-generated.

Who created Make A Video?

Make A Video was developed by a team of researchers at Meta AI. Key contributors include Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan (Isabelle) Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. A full list of contributors is available in their official PDF document. Beyond building the text-to-video technology, the team focused on responsible AI use, including preventing harmful content generation.

Who is Make A Video for?

The tool suits artists, content creators, creative professionals, marketers, advertisers, film producers, and brand managers who want to generate video content from text or animate existing images.

How to use Make A Video?

1. Type Your Idea: Enter a few words or a short sentence describing the video you want.
2. Generate: Make-A-Video produces unique, imaginative videos based on your text.
3. Add Movement: Add motion to a single image or create a smooth transition between two images.
4. Experiment with Variations: Generate different versions of a video to explore other possibilities.