Quiet on the Creek Dance AI: Do the Shush and the Bounce From One Photo

Track the exact camera movement, framing, facial expressions, and body movements from the reference video. Keep the face, hairstyle, body, clothing, and overall appearance exactly the same as in the reference image, with no changes or distortion. Use the place from the reference image as the background. Keep every move of the dance in time with the beat, the finger-to-lips shush, the head tilt and the bounce, from the first move to the last. Output in 9:16 vertical format. Exactly one adult dancer, the person from the reference image, with natural human anatomy: two arms and two hands with five fingers each, also in the arm flex, the deep squat and the turn. No white tank top, no light blue flared pants, no necklace and no long brown hair unless the reference image shows them. No text, no captions, no watermark.

Recreate the reference video [Video 1] shot for shot: the same empty parking lot at night with the lit city towers far behind, the same fixed phone camera, framing, timing and dance moves, one continuous take with no cuts. 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 on the left = the person in [Image 1], in EVERY frame: copy the exact face from [Image 1]: 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 black tank top, no black or denim shorts and no long straight dark hair unless [Image 1] shows them. Dancer on the right = the person in [Image 2], in EVERY frame: copy the exact face from [Image 2]: 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 black tank top, no black or denim shorts and no long straight dark hair unless [Image 2] shows them. The same real people in every frame, from the first second to the last, so their friends instantly recognize them, also when the hands cover the eyes and the mouth. 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 the dancer on the left, [Image 2] is only the dancer on the right. Both change: no one from the video stays. The dance, both in perfect sync, matching the reference second by second: every move of the dance in time with the beat, the finger-to-lips shush, the head tilt and the bounce, from the first move to the last. 0-0.5 s: both stand side by side facing the camera, arms loose. 0.5-1.5 s: both cover their eyes with both hands. 1.5-2.5 s: both cover their mouths with both hands. 2.5-4 s: the hands drop to the waist and both bounce on the beat, hands out at the hips. 4-4.5 s: one finger to the lips: the shush, eyes on the camera. 4.5-7 s: elbows bent, palms up and open at shoulder height, both sway side to side on the beat. 7-7.5 s: both drop the pose and step toward the camera. Anatomy rules: one head per person, on that person's own shoulders. A face never appears on hands, legs or clothes. Two arms and two hands with five fingers each. Exactly two people. No extra dancers, no text, no logos, no watermark. No dialogue throughout the entire video. No background music.

Recreate the reference video [Video 1] shot for shot: the same sunny forest creek with round wet stones, ferns, tall trees, shallow clear water and a small turtle on a mossy rock, the same warm, soft 3D animated look and golden light, the same camera angles, cuts, timing and moves. The ONLY change: the dog who dances on its hind legs by the creek is now the pet in [Image 1]. The dancer = the pet in [Image 1], in EVERY shot: the same species and breed, head shape, muzzle, eyes, ears, fur colors, fur length, markings and body shape 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 instantly recognizes it, also in the close-up of its face. It is drawn in the reel's soft 3D animated style, but its colors, markings and ear shape come only from [Image 1]. It stands and bounces on its hind legs like a person the whole time. Never drift back to the dog of the original video: not its cream-white coat and not its big pink upright ears, unless [Image 1] shows them. If [Image 1] shows a cat or another animal, that animal dances in the same place with the same moves. Every move of the dance in time with the beat, the head tilt and the bounce, from the first move to the last, matching the reference shot by shot: Shot 1 [0-3.1 s]: wide shot: the pet peeks out from behind a big rock, steps out on its hind legs and bounces with its front paws at its chest. Shot 2 [3.1-3.9 s]: hard cut, close-up of its face: it squints and winks at the camera. Shot 3 [3.9-5.3 s]: hard cut, medium shot: it bounces on its hind legs on the stones, front paws up. Shot 4 [5.3-10.1 s]: hard cut, wide shot, the pet small at the water's edge: it bounces, turns away and wiggles its rear, then, closer again, it bounces in the shallow water with small splashes. Shot 5 [10.1-12.4 s]: hard cut, medium shot in the shallow water: a big open-mouth smile, front paws up, bouncing on the beat. Shot 6 [12.4-14.6 s]: hard cut: it turns side-on and spins to wiggle its rear at the camera, splashing. Shot 7 [14.6-15 s]: hard cut: it faces the camera again with a big smile. Anatomy rules: one head only, one tail. Two hind legs and two front legs with round furry paws, never human hands, no fingers. No people, no extra animals except the small turtle, no text, no logos, no watermark. No dialogue throughout the entire video. No background music.