I updated the workflow for 2.5 . Made a few changes to make lipsync more reliable , including switching to convrot gemma text encoder.

This workflow is for people who want long videos of someone talking/singing.

Final demo (not allowed by civit and some edits with Davinci)

I suggest updating to 2.5 if you use LIP SYNC frequently

Please note this workflow requires my custom nodes : "TK Handy Nodes"