Video Lipsyncing

Sync your lips with any video using this model. Similar to methods such as Wav2Lip but with much higher quality.

Note 1: The processing time depends on video resolution and video length but a general rule of thumb is that it takes ~13 seconds to generate a single second of video.

Note 2: To speedup inference times, you can trigger booleans to cut resolution and fps of the output video by half.

Other tips:

• Ensure there are no abrupt scene cuts in the video
• Ensure there is only a single person in the video
• Ensure the person is facing the camera
• Ensure the person is not wearing any accessories that cover the mouth (e.g. mask, scarf, etc.)
• Ensure the person is not moving their head too much
• Ensure the person is at at most arms length from the camera