Phenaki Reviews

Phenaki is an AI model to generate videos that can be multiple minutes long straight from text. You can also generate video from a still image and a prompt.
The proposed video encoder-decoder 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, they are using bidirectional masked transformer conditioned on pre-computed text tokens. The generated video tokens are subsequently de-tokenized to create the actual video.

Phenaki.video has several pros and cons:

Pros:

• Innovative approach to video synthesis.
• Capable of generating long-duration videos.
• Handles changing prompts effectively.
• Produces high-quality video output.
• Useful for a variety of users.

Cons:

• Output Quality needs scaling and refinement.

It's an open-source tool, making it accessible for a wide range of users. However, like any other tool, it has room for improvement, particularly in terms of scaling and refining the output quality. Despite these challenges, it remains a promising tool for video synthesis from text.