Edit [Video 1]: replace the singing dog with the subject of [Image 1], which can be a pet, a person, a toy, a character or an object. Recreate [Video 1] exactly: one continuous take, a fixed camera at the subject's eye level, the same close chest-up framing, timing, head moves and mouth moves. The ONLY changes: the singing dog is now the subject of [Image 1], in the same place and at about the same size in the frame, and the flat green screen behind it becomes the real place from [Image 1] (its room, yard or street, its light). With no clear place in [Image 1], a cozy living room. No green screen and no green background anywhere. [Image 1] is the only reference for the subject and the place; [Video 1] is only for the moves, the mouth, the timing and the framing.
Use the photo as the subject and keep it exactly as photographed: same breed, fur colour and markings, eyes, ears and size, in a vertical 9:16 close portrait framing.
An animal keeps its own face, muzzle and fur length and its natural body proportions: never flattened, stretched or merged with anything. NOT the short brown coat, the big round bulging eyes or the huge ears of the dog in [Video 1] unless [Image 1] shows them. Real animal anatomy, paws only, no human hands.
A person keeps 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), the hair and the clothes, at full adult size, with no fur, no dog ears and no snout.
Anything else keeps its own whole shape, colors, material and style, with a mouth that opens to sing, and no human body parts it does not have.
It stays the same in every frame, so its owner instantly recognizes it. Never morph, never drift back to the dog in [Video 1].
The subject sits upright facing the camera, looking straight into the lens, and sings a funny viral chant with total seriousness, its mouth shaping every word: "oh my carne asada... one love", in a long, dramatic, howl-like singing voice. Its eyes widen on the high notes, an animal's ears flop, and it gives a few short comedic head tilts between phrases.
[0-5s]: the long opening note "aaaah": the head tips far back, the eyes close and the mouth opens wide upward.
[5-6s]: the head comes down to the camera, lips pulled back in a toothy grin.
[6-8.5s]: "oh my carne asada": the eyes wide open and bulging, staring into the lens, the mouth opening wide on every word, teeth showing.
[8.5-11.5s]: "one love": the eyes squeeze shut and the head tilts to one side, the mouth stretched in a toothy wail.
[11.5-12.6s]: it looks back into the lens with wide eyes and ends on a small, sly, toothy grin.
Only replace the dog and the green screen; keep everything else the same.
No dialogue throughout the entire video. No background music.
One head only. Exactly one subject. No text, no captions, no letters or words anywhere in frame, no logos, no watermark.
2977 characters