>>2813618I broke this down just to see how much work this would be. There are 38 frames but I counted 20 unique frames.
This frame was done using txt2img with controlnet lineart + canny. I didn't apply the character loras.
The best way to tackle this would be of course to apply the loras and go manually frame by frame to ensure consistency.
Also note that more detail = less consistency or more time spent making it consistent.
It can be done but it's a tall order.
