Not Like Us Halftime Show AI: Headline the Stadium Stage With a Friend

Take the stage at a stadium halftime show, filmed like a real live concert broadcast at night: a huge packed stadium in the dark, thousands of phone lights twinkling in the stands, the field turned into a wide stage with glowing white light lines, bright white spotlights and light haze. Dozens of backup dancers in red, white and navy tracksuits stand in neat rows on the field behind the performers and bounce in sync. Photorealistic, natural skin, real stadium light, gentle broadcast camera moves, not CGI, not a cartoon. Only the two performers change. Medium and medium-wide shots keep both faces large, sharp and lit by the spotlights. The headliner, in the center-left with a black handheld microphone, is the person in [Image 1], in every frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), with the clothes from [Image 1]. The friend, who dances at the headliner's right side, is the person in [Image 2], in every frame: copy the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), with the clothes from [Image 2]. If an image shows an animal, that performer is that animal standing upright on its hind legs, with its own face, fur and markings, not a person. Never blend their faces, never swap their clothes. Each face stays the same from the first frame to the last, so their friends recognize them at once. The shots: 1. 0-3 s: a medium-wide shot from the front: the headliner walks toward the camera down the lit stage, rapping into the microphone with a playful, self-assured look, the rows of dancers bouncing behind. 2. 3-6 s: a medium shot: the friend steps in at the headliner's side and starts a smooth side-to-side two-step with alternating weight shifts, gentle knee bends and rhythmic shoulder bounce, with small, natural arm swings, while the headliner raps to the camera and bounces on the beat. 3. 6-10 s: a medium-wide shot that slowly pushes in: both dance side by side in time with the beat, the headliner points the free hand at the crowd, then both finish in a confident standing pose facing the camera. Audio: none of its own; a live rap song from a stadium show is put on afterwards, so the rapping must be easy to see: the headliner raps into the microphone with clear, confident lip movements on the beat. No dialogue. No background music. Only the two performers in front. No additional people in front, no sudden camera cuts inside a shot, no sliding feet, no distorted hands. No celebrity likeness: every face comes only from the photos. No game-controller-shaped stage, no flags, no stars-and-stripes patterns, no team, league, sponsor or event logos, no scoreboard, no readable text, no subtitles, no watermark.

Take the stage at a stadium halftime show, filmed like a real live concert broadcast at night: a huge packed stadium in the dark, thousands of phone lights twinkling in the stands, the field turned into a wide stage with glowing white light lines, bright white spotlights and light haze. Dozens of backup dancers in red, white and navy tracksuits stand in neat rows on the field behind the performers and bounce in sync. Photorealistic, natural skin, real stadium light, gentle broadcast camera moves, not CGI, not a cartoon. Only the headliner changes. Medium and medium-wide shots keep the face large, sharp and lit by the spotlights. The headliner, in the center with a black handheld microphone, is the person in [Image 1], in every frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles), with the clothes from [Image 1]. The face stays the same from the first frame to the last, so their friends recognize them at once. If [Image 1] shows an animal, the headliner is that animal standing upright on its hind legs, with its own face, fur and markings, not a person. The shots: 1. 0-3 s: a medium-wide shot from the front: the headliner walks toward the camera down the lit stage, rapping into the microphone with a playful, self-assured look, the rows of dancers bouncing behind. 2. 3-7 s: a medium shot: the headliner moves into a smooth side-to-side two-step with alternating weight shifts, gentle knee bends and rhythmic shoulder bounce, with small, natural arm swings, rapping to the camera on the beat. 3. 7-10 s: a medium-wide shot that slowly pushes in: the headliner points the free hand at the crowd, then finishes in a confident standing pose facing the camera as the phone lights wave behind. Audio: none of its own; a live rap song from a stadium show is put on afterwards, so the rapping must be easy to see: the headliner raps into the microphone with clear, confident lip movements on the beat. No dialogue. No background music. Only the headliner in front, with the backup dancers behind. No additional people in front, no sudden camera cuts inside a shot, no sliding feet, no distorted hands. No celebrity likeness: every face comes only from the photos. No game-controller-shaped stage, no flags, no stars-and-stripes patterns, no team, league, sponsor or event logos, no scoreboard, no readable text, no subtitles, no watermark.

Take the stage at a stadium halftime show, filmed like a real live concert broadcast at night: a huge packed stadium in the dark, thousands of phone lights twinkling in the stands, the field turned into a wide stage with glowing white light lines, bright white spotlights and light haze. Dozens of backup dancers in red, white and navy tracksuits stand in neat rows on the field behind the performers and bounce in sync. Photorealistic, natural skin, real stadium light, gentle broadcast camera moves, not CGI, not a cartoon. Only the headliner changes, and the headliner is a pet. Medium and medium-wide shots keep the pet large, sharp and lit by the spotlights. The headliner, in the center, is the pet in [Image 1], in every frame: the same species and breed, face, eyes, ears, muzzle, fur colors, fur length and markings as in [Image 1], with the natural body volume and proportions of that animal: never flattened, squashed, stretched or merged with anything, so its owner recognizes it at once. It stands upright on its hind legs like a performer and holds a black handheld microphone in one front paw. It wears no clothes unless [Image 1] shows them. The shots: 1. 0-3 s: a medium-wide shot from the front: the pet walks upright toward the camera down the lit stage, the microphone at its mouth, with a playful, self-assured look, the rows of dancers bouncing behind. 2. 3-7 s: a medium shot: the pet moves into a smooth side-to-side two-step with alternating weight shifts, gentle knee bends and rhythmic shoulder bounce, the free front paw swinging, its mouth opening and closing on the beat. 3. 7-10 s: a medium-wide shot that slowly pushes in: the pet points its free paw at the crowd, then finishes in a confident standing pose facing the camera as the phone lights wave behind. Audio: none of its own; a live rap song from a stadium show is put on afterwards, so the rapping must be easy to see: the pet's mouth opens and closes on the beat. No barking. No dialogue. No background music. Anatomy rules: one head only, on the pet's own body; two hind legs on the stage and two front legs, no human hands. No people in front, only the backup dancers behind. No celebrity likeness: every face comes only from the photos. No game-controller-shaped stage, no flags, no stars-and-stripes patterns, no team, league, sponsor or event logos, no scoreboard, no readable text, no subtitles, no watermark.

Recreate the reference video [Video 1] shot for shot: the same night plaza between tall glass towers, the steel lattice bridge overhead, the city lights, the same fixed phone camera low at hip height looking up, the same framing, timing and dance moves. Follow the reference video's movements, timing, performer positions and camera framing. The ONLY change: the dancer on the left is now the person in [Image 1], and the dancer on the right is now the person in [Image 2]. Dancer 1 (left) = the person in [Image 1], in EVERY frame: copy the exact face from [Image 1] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles) exactly as in the photo. They wear the clothes and shoes from [Image 1]. NO fur jacket, no black crop top and no olive baggy trousers unless [Image 1] shows them. Dancer 2 (right) = the person in [Image 2], in EVERY frame: copy the exact face from [Image 2] (the face shape, eye color and eye shape, eyebrows, nose, mouth, skin tone, age, hair color, hair length and hairstyle, and any beard, moustache, glasses or freckles) exactly as in the photo. They wear the clothes and shoes from [Image 2]. NO fluffy dark fur jacket and no light grey sweatpants unless [Image 2] shows them, and no long dark hair unless [Image 2] shows it. The same real people in every frame, from the first second to the last, so their friends instantly recognize them, also when they bounce, turn and swing their hair. Never morph, never drift back to the original dancers' faces, never add or remove facial hair. Do not mix the two faces: [Image 1] is only dancer 1, [Image 2] is only dancer 2. Both change: no one from the video stays. The dance, matching the reference second by second, on the beat: the two dance side by side in sync, a bouncy hip-hop two-step with knee bends, shoulder bounces, arm swings and side steps, and dancer 2 steps forward toward the camera near the end. Keep identities distinct throughout, with natural joint movement, grounded footwork and clear spacing between performers. Anatomy rules: one head per person, on that person's own shoulders. A face never appears on knees, legs, hands or clothes. Exactly two people. No face blending, role switching, duplicated dancers, extra limbs or added text. No logos, no watermark.