I Just Woke Up From a Fuzzy Dream: Do the Skeur Dance From One Photo

Use the reference image as the sole character identity reference and the reference video as the motion reference. Animate exactly one adult dancer, in the place from the reference image. Preserve the person's recognizable face, hairstyle, skin tone, body proportions, outfit, shoes, and accessories throughout the video. Follow the reference dancer's movement order and timing, including the relaxed standing bounce, the drop into a deep wide squat with the knees pointing out, the steady low bounce on the beat, the arm winds at chest height, both hands on top of the head, the fast knee shake with the fists at the chest, and the one arm thrown straight up. Do not invent additional moves. Keep the entire body visible from head to shoes, with enough space around both hands and feet. Follow the reference framing and camera movement: one fixed camera, one continuous shot. Maintain natural balance, believable weight in the squat, stable ground contact, and consistent shadows. Keep the face recognizable, calm and cool during the whole dance. No extra dancers, duplicate bodies, extra limbs, fused fingers, outfit changes, new camera cuts, text, or watermark. Use a vertical 9:16 reference and output when supported. No white T-shirt, no light grey track pants and no white sneakers unless the reference image shows them.

Recreate the reference video [Video 1] shot for shot: the same bright college lounge with the light wood floor, the grey sofas, the round grey seats and the warm ceiling lights, the same fixed phone camera, framing, timing and dance moves, one continuous shot. The ONLY change: the woman in front on the right, with long dark hair, a dark grey graphic T-shirt and light grey shorts, is now the person in [Image 1], and the woman behind her on the left, with dark curly hair, a beige crop top and black trousers, is now the person in [Image 2]. Dancer 1 = 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 dark grey graphic T-shirt, no printed lettering and no light grey shorts unless [Image 1] shows them. Dancer 2 = 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 beige crop top, no black trousers and no curly 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 low in the squat. 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: 0-3.5 s: both stand side by side facing the camera, feet apart, with small loose bounces and swaying shoulders. 3.5-5 s: both drop into a deep wide squat, knees pointing out, and bounce low on the beat. 5-6.5 s: still low, they work their arms at chest height; dancer 2 rises for a moment with both arms spread wide. 6.5-9 s: both bounce low in the squat again, knees opening and closing, until the end. 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; the lounge behind them stays empty. Natural balance, believable weight in the squat, stable ground contact. No dialogue. No background music. No extra dancers, duplicate bodies, extra limbs, fused fingers, text, logos or watermark.

Recreate the reference video [Video 1] shot for shot: the same sunny concrete yard with the grey mat on the ground, the blue see-through roof on thin metal poles, the grey block wall and the big round blue water tank, the same fixed phone camera, framing, timing and dance moves, one continuous shot. The ONLY change: the man in the white T-shirt and light grey track pants who dances is now the pet in [Image 1], a real animal, not a person. The dancer = the pet in [Image 1], whole body, in every frame: 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. It stands upright on its hind legs like a person the whole time, at the natural size of that animal, in the place where the man dances. Its own fur from head to toe, with a collar only if [Image 1] shows one: NO white T-shirt, NO grey track pants, NO sneakers, NO human body, NO human face and NO human hands. If [Image 1] shows a dog, a cat or another animal, that animal dances in the same place with the same moves. The dance, matching the reference second by second, on the beat: 0-0.5 s: the pet bends its hind legs into a deep wide squat, knees pointing out. 0.5-3.5 s: it bounces low on the beat, both front paws winding in circles at chest height. 3.5-6 s: both front paws rest on top of its head while it keeps bouncing low, knees opening and closing. 6-7.5 s: front paws together in front of the chest, the hind legs shake fast. 7.5-10 s: one front leg shoots straight up, then both front legs spread wide, still low and bouncing until the end. Anatomy rules: one head only, one tail. Two hind legs on the ground and two front legs, no extra legs or paws, no human hands. Natural balance, stable ground contact. Photorealistic, real fur. No dialogue. No background music. No people, no extra animals, no text, no logos, no watermark.