Two portraits, one orange booth
Generated here from two separate original portrait references. Each performer keeps their own outfit and position, with natural mouth movements and small gestures. This is one reviewed result; outputs vary.
MiniMax H3 · 768 × 1344
View generation prompt
Vertical 9:16 portrait music-performance video, 4 seconds, one continuous static medium-wide shot. Use the uploaded photos only as identity and outfit references, never as a starting frame or a displayed photo. From the very first frame the performers are already in a flat saturated orange studio with matching orange floor, soft even lighting and one silver microphone hanging centrally between the performers, completely outside both face silhouettes, actively singing and rapping to the beat. Begin the performance immediately and maintain natural mouth movements throughout. The person in @Image1 stands on the left, the person in @Image2 on the right. Preserve each face, hairstyle and outfit separately. In the first half the left performer sings and raps with continuous natural mouth movements and a small hand gesture while the right nods to the beat. In the second half they exchange the singing lead without crossing or merging. No still-photo intro, original photo background, photo collage, fade-in, transformation, transition, furniture, hotel interior, logos, captions, cuts, camera orbit, extra people or distorted hands. Silent visual singing performance; audio will be added separately.

