According to our singer who created the video, it uses the following:
Kling (including lip synch), Vidu, Hailuo and Genmo;
Voice for the vocal stripping,
AI Face Swap for character consistency. The main character uses the face of one of our fans IIRC.
The video was made a year ago so the abilities of the various AI video applications will have moved on since then, and these may not be the best options any more.
The resulting clips were edited together in the full version DaVinci Resolve.
It took a long time to create, much of it was spent learning how to get the best out of the text prompts, and from what I recall very little of the footage generated at the beginning of the process made it through to the final edit. Also had the time been available he could have spent another month or so fine tuning the edits and getting rid of glitches like the additional fingers, but it had to be finished to coincide with the release of the EP which includes this song.