Santa in my house with ChatGPT or any AI: the photo prompt and the video prompt

Add Santa Claus to my photo without changing anything else in it: same room, same furniture, same tree, same light, same angle. He is a real, warm elderly man with a full white beard, in a classic red velvet suit with white fur trim, a black belt and black boots, a red sack over his shoulder. He stands in the front of the room near the camera, seen from the knees up, bending to set a wrapped present on the floor, and glances at the camera with a finger to his lips. Make it look like a slightly soft, grainy frame from a home security camera at night. No text, no timestamp, no other people.

Footage from a small indoor home security camera fixed on a shelf in this room, recording on Christmas Eve, exactly 10 seconds. @Image1 is the FIRST FRAME and the camera's fixed view. It is a locked-off shot from one mounted camera: the frame never moves, never pans, never tilts, never pushes in, never zooms and never cuts. The four edges of the frame and everything in the room, the walls, the floor, the furniture, the tree and every decoration, stay at exactly the same place in the picture from the first frame to the last, with the same light. Only Santa moves; lights that are on may twinkle and a fire, if there is one, flickers. Plain home-camera image, slightly soft and noisy, no cinematic grading. WHO: one man, Santa Claus, a real, warm elderly man with a full white beard and white hair, rosy cheeks and a kind face, in a classic red velvet suit with white fur trim, a wide black belt with a plain gold buckle, black boots and a red hat with a white pom-pom. He carries a red cloth sack over one shoulder. He is the only person in the video; nobody else appears. HOW BIG: Santa is close to the camera, in the front of the room. He walks in from the RIGHT edge of the frame right in front of the camera, and from his first step he is big in the picture: seen from the knees up, his hat near the top of the frame, filling about two thirds of the frame height, his face large and easy to read. He stays in this front part of the room for the whole video. The camera never moves to make him bigger: he is big because he is close. ACTION, one continuous shot from the fixed camera: [00:00-01.0] the room is still and empty, exactly as in @Image1. [01.0-03.0] Santa tiptoes in from the right edge, close to the camera, sack on his shoulder, glancing into the room. [03.0-05.5] he bends down, takes one wrapped present with a red ribbon out of the sack and sets it on the floor in front of him. [05.5-07.5] he straightens up, takes a cookie, from a plate if the room has one, else from his coat pocket, and takes a happy bite. [07.5-10.0] he notices the camera, turns to face it with a surprised smile, chewing, and raises one finger in front of his lips to say shh, his face and beard large and clearly visible. Avoid: camera movement, a moving frame, pan, tilt, dolly, push-in, zoom, handheld shake, following the subject, cuts, Santa small or far away, Santa at the back of the room, a second person, children, pets, elves, reindeer, a different room, furniture moving or disappearing, new decorations appearing, glasses, sunglasses, a fake or costume-shop beard, a mask, logos, brand names, readable text, captions, watermarks, a timestamp, extra arms, extra fingers, distorted hands, morphing face. Sound: the quiet room at night: soft footsteps on the floor, a faint jingle of bells as he moves, the rustle of the sack, a small crunch of the cookie, a fire crackling if there is one. No music, no speech.