Photo 1 = person (portrait). Photo 2 = scene (landscape, room, event). Output = the person plausibly placed in the scene.
Required fields are highlighted. 1 credit per output image.
This second photo combines with the first one — e.g. person from photo 1 inserted into scene of photo 2.
AI composite. The person was NOT actually at that location — this is a composition. Disclose AI editing where it could mislead viewers.
Generation runs in the background — you'll be redirected in a moment.