A composite without compensation for at least 1) direction of light sources, 2) colour temperature of light sources, and 3) perspective matching will just look "off". Uncanny valleyish. Maybe that's okay or desired for a very limited application. I'm thinking pulp scifi cover artwork, lol.

Humans make these mistakes with naive/low-effort composites. Poorly generated AI images could contain such mistakes also.

OTOH, appropriate training could not only allow AI to avoid the mistake in its own prompt-driven images but also allow it to correct human artist-drawn images. Like local white-balance adjustments or local lens/perspective distortion correction.