How Will Text to Image or Text to Music Become More Expressive?

I'm also curious how kind of like just gestural kind of haptic systems will develop because when I often think about like, you know, text to image or especially text to music. Like a score can never capture the Tamboral world of music. And so systems such as like tambor transfer where you can perform something and then choose what instrument that is is so much more expressive than trying to input a score. So I'm wondering how that will also kind of map over to other, to other medium like painting or,. you know, other kind of more gestural art forms.