Mmh, ime you need to discard the session/rewrite the failing prompt instead of continuing and correcting on failures. Once errors occur you've basically introduced a poison pill which will continuously make things to haywire. Spelling out what it did wrong is the most destructive thing you can do - at least in my experience

Almost no image/video models can do "upside-down" either.

to the point where you can say, raise the left arm and then raise the right arm and get the same image with the same arm raised.