Looking for a cutting-edge AI model to generate videos from text and still images? Look no further than Phenaki! With Phenaki, you can easily create multiple-minute-long videos straight from text or a still image and a prompt.
Our video encoder-decoder technology is ahead of the curve when compared to per-frame baselines currently used in the literature, boasting superior spatio-temporal quality and the ability to generate more tokens per video. And to generate those tokens from text, we utilize a bidirectional masked transformer that's conditioned on pre-computed text tokens.
The result? Seamless, high-quality videos that are a true testament to the power of AI. So why wait? Sign up for Phenaki today and start generating amazing videos from your text and still images.
