Phenaki

About Phenaki

Phenaki is an advanced AI model designed to generate high-quality videos directly from text inputs. This powerful tool is capable of producing videos that can be several minutes long, and can even generate videos from still images and prompts. The model utilizes a cutting-edge video encoder-decoder that outperforms all per-frame baselines currently used in the literature in terms of spatio-temporal quality and number of tokens per video. To generate video tokens from text, Phenaki employs a bidirectional masked transformer that is conditioned on pre-computed text tokens. The generated video tokens are then de-tokenized to create the final video output. With its advanced capabilities and impressive performance, Phenaki is a valuable tool for anyone looking to generate high-quality videos from text inputs.