body_swap: subject_definitions: <Subject 1> is an old woman with long silver hair shown on the left of <Picture 1>, <Subject 2> is an old man with white hair and a short white beard shown in the middle of <Picture 1>, and <Subject 3> is an old woman with long grey hair shown on the right of <Picture 1>; their identity, face, head, hair, skin, body shape, proportions and clothing define the three characters in the target video. The guide video provides the scene and the performance: its background, environment, lighting, camera, framing, body pose, hand and arm movement, head rotation, gaze direction, lip movement and facial expression, frame by frame; only the three people are replaced: the woman in the red dress on the left becomes <Subject 1>, the man in the blue plaid shirt in the middle becomes <Subject 2> and the woman in the light blue top on the right becomes <Subject 3>, their face, hair, body and clothing. summary: [video generation + reference] Replace the woman in the red dress with <Subject 1>, the man in the blue plaid shirt with <Subject 2> and the woman in the light blue top with <Subject 3> in the guide video, keeping the scene, camera and the complete motion and performance of the guide video. detailed_description: [Shot 1] <Subject 1> takes the exact place of the woman in the red dress, <Subject 2> takes the exact place of the man in the blue plaid shirt and <Subject 3> takes the exact place of the woman in the light blue top; all three move with the same timing, body pose, gestures, head motion, gaze, speech and facial expressions as the person they replace, while keeping the complete look from <Picture 1>: head, face, skin, hair, body shape and clothing stay stable in every frame, with no trace of the original subjects' faces, hair or clothing. The background, lighting, colors and camera of the guide video are preserved. Prevent identity drift, clothing changes, texture crawling and flicker. The result is a real, photographic video.