The Super Money look is a night-time flex shot: a fan of green banknotes, a phone camera, flash pops, and friends in the background. This page rebuilds it as an original AI clip with fictional prop money, so nothing in the frame is real currency.
Updated October 20, 2026
Each page has its own generated example, still prompt, motion prompt, and model route. Pick the look closest to the clip you want to post.
Use a front-facing photo with even light and no sunglasses. Show your hair, shoulders, and outfit. For a group shot, use one photo with everyone in frame or compose the group first.
The prompt protects the face, skin tone, body proportions, and the number of people. Change the outfit, the scene, or the camera — never the person.
Generate the still first. When the face and outfit look right, send that image to image-to-video for a 9:16 clip of up to 10 seconds.
Keep the prop-money and no-real-currency lines. They are what keeps the clip usable.
Open the generator, upload a clear front-facing photo, and keep the identity and anatomy lines intact. The still prompt is written for an image model; the motion prompt is written for image-to-video.
Use the uploaded photo as the primary reference. Preserve the subject's recognizable face, facial proportions, skin tone, approximate age, body proportions, and natural anatomy. Keep the same number of people as the uploaded photo. Place the subject in a clean streetwear outfit in a night parking lot under warm sodium lights, holding a fan of clearly fictional blank green prop banknotes, with a few friends blurred in the background and a handheld phone camera angle. Photorealistic editorial photography, realistic skin texture and fabric, cinematic practical lighting, shallow depth of field, vertical 9:16 framing. Avoid altered identity, extra limbs, duplicated fingers, distorted anatomy, readable text, logos, watermarks, real currency, and celebrity likenesses.
The still needs an image model that preserves identity; the motion needs a video model that holds a face in a moving scene. Every route below is enabled in the generator.
No. That template swaps a face into a fixed clip. Vidle generates a new still and a new clip from your photo, so the outfit, scene, and camera can change. You can still import the MP4 into CapCut for the trending sound.
No. Every banknote in the example and in the prompt is a blank, clearly fictional prop. The prompt forbids real currency, readable denominations, and logos. Do not use the output to imply real cash, income, or a financial claim.
Yes. Upload one photo with everyone in frame, or compose a group still first with Seedream 4.5 Edit. The prompt keeps the number of people unchanged; it will not invent a crew.
It holds faces well in a handheld night scene with several people and fast hand motion. Veo 3.1 Fast is the faster option when you want a quick draft.
Generate the still first. When the face and outfit look right, send that image to image-to-video for a 9:16 clip of up to 10 seconds.
Independent AI video tool. Not affiliated with, endorsed by, or sponsored by TikTok, CapCut, Drake, OVO, fal, Black Forest Labs, or any artist or label. Use only photos of people who gave you permission and are 18 or older. Do not upload celebrities or public figures. Every banknote in the example videos and prompts is a fictional prop, not real currency.