I have broken up my script into the 8 parts so that I may make workflow easy. This is the storyboard of the first two parts. I have tried to keep the consistency. @Mark Diaz Kindly check the character consistency and background consistency and point out the other elements that needs to improve. Thank you in advance. https://drive.google.com/drive/folders/11iyB4at1q17P4u3j0pFLc16fwt8YEdtu?usp=sharing

Dancing 💣

This took quite a bit of doing. I was pretty happy really with the built in/all-in-one audio of the LTX2.0 video model but the course uses external audio so I was trying to replicate that workflow. Basically I had to hack together the two models to work together and while I am a very nerdy techy, it still gave me headaches! However, while there are still some problems to solve, slightly better lipsyncing ideally and should be going back and getting on with the storyboards now, so this is where I'm up to with LTX2.0 doing the video and Quen3-TTS (an open source Elevenlabs alternative) doing the audio. I was able to manipulate the TTS after many experiments to give pretty good expressive speech. Storyboards next!

Using the Friday class as incentive to meet a self imposed deadline. Feedback welcome.

Will see if Mark has time to dissect this today in class, as well.