Mandem in Disguise prompt for Kling: a copyable prompt without names

Copy this prompt

Image-to-video, 9:16, about 10 seconds.
Reference image 1 is the only person in the video, an adult. Keep their face, eyes, skin tone, hair and body shape in every second, including after the disguise.
Scene: a plain grey brick wall in daylight on a quiet pavement. No readable text or logos.
Camera: one fixed eye-level shot, the person centred, visible head to feet. After the flash the camera slowly pushes in to a medium close-up.
Beat 1 (0 to 1 seconds): the person stands relaxed in the clothes from the photo, smiling warmly at the camera.
Beat 2 (1 to 2 seconds): a camera flash fires and the frame turns bright white for a moment.
Beat 3 (2 to 10 seconds): same position. The person now wears a plain black knit balaclava with only the eyes showing, a black hooded puffer jacket with the hood down and the zipper closed, and black trousers and shoes. Deadpan expression, hands in the jacket pockets, slow calm nods at the camera; near the end one hand slowly pulls the zipper up to the chin. Empty hands, no weapons, no gestures, no emblems or writing on the clothes.
Audio: an instrumental deep dark bass beat with a slow steady kick drum and a soft camera-flash click. No vocals.
Photorealistic, natural colour, no text, no subtitles, no logos, no watermark.

How to use it

• Attach one photo of an adult as image 1.
• Add the trending sound in TikTok afterwards. A text prompt cannot place each beat exactly, so expect to nudge the sound.
• Leave names, sound titles and brands out. Tools can filter them, so the prompt describes the action instead.
• Tools change often, so check the length and aspect ratio your tool supports and adjust the first line.