Phenaki

Phenaki is a new technology that can generate realistic videos from text descriptions. It was developed by Google Research and uses a combination of machine learning models to compress videos into tokens, translate text into tokens, and de-tokenize tokens into videos. Phenaki can create videos of variable length and quality, based on a sequence of textual prompts that can change over time. For example, Phenaki can generate a video of a teddy bear swimming in the ocean, going underwater, and meeting a panda bear, just by using these sentences as prompts.

Phenaki is a breakthrough in video synthesis, as it can handle open-domain and time-variable prompts, unlike previous methods that were limited by data availability and computational cost. Phenaki can also generate videos from a still image and a prompt, such as zooming into the eye of a cat or making it yawn. Phenaki has many potential applications, such as entertainment, education, storytelling, and art.

To learn more about Phenaki, you can read the paper published by Google Research or watch some example videos generated by Phenaki on their website or YouTube channel.