The Video Prompt · Pro
scroll to read all ↓
[PERSON_REFERENCE]: @image1
[GAME]: England vs Croatia
[GOAL]: England
[OUTFIT]: England-inspired white jersey
[GOAL_REFERENCES]: @image2, @image3, @image4, @image5, @image6, @image7
Create a realistic viral-style vertical vlog video, 9:16 aspect ratio, 15 seconds long, in bright natural daylight, filmed as one single continuous handheld mobile-camera shot with absolutely no cuts.
Use the person from [PERSON_REFERENCE] as the main character. The person's identity, face, hairstyle, skin tone, body type and overall appearance must remain consistent with the reference image. Do not change their identity. The person should look natural, confident, stylish and like a real stadium visitor at a major international football match.
The setting is inside a completely packed World Cup football stadium. The person is sitting normally in the spectator stands among thousands of fans, in a regular stadium seat. The person is seated in the lower or middle stands, surrounded by excited fans, rows of stadium seats, railings, stairs, crowd movement and the football pitch visible below in front of them. The stadium is completely full, loud, energetic and realistic.
A friend is sitting right beside the person in the next stadium seat, physically next to them, but the friend remains fully offscreen the entire time. The camera is handheld from the friend's seated position, like a real friend casually filming a spontaneous viral moment. The friend's voice is heard offscreen, but the friend's body and face are never shown.
The entire video must feel like one uninterrupted live recording from the friend's handheld camera. The camera never cuts, never switches angle, never inserts another shot, never jumps to the football field, and never becomes separate match footage.
The person has exactly two visible hands and two visible arms. One hand holds a slice of pizza near their mouth and is used only for eating. The other hand rests low on the person's lap / upper thigh. No other hands, no extra fingers, no duplicated hands, no detached hands, no third hand.
The person is relaxed and casually eating the slice of pizza while watching the match. There is no pizza box visible anywhere. Only the pizza slice in one hand is visible.
The person wears exactly one black modern smartwatch on the wrist of the hand resting low on the lap / upper thigh. The smartwatch is small, natural and not a visual focus. The watch display should not be clearly readable. The display is angled away from the camera and appears dark, glossy, reflective, or too small to read clearly. Do not show readable smartwatch text or a readable smartwatch interface.
There is no smartphone visible anywhere in the video. No phone in the hands, no phone on the seat, no phone on the lap, no phone in the frame, and no other visible devices besides the single smartwatch.
The person is wearing [OUTFIT]. The outfit should look natural, stylish and appropriate for someone attending a football match. Do not describe the person as a fan of any specific team. The outfit is simply what they are wearing. The outfit must have no readable text, no names, no numbers, no logos, no crests and no brand marks.
Important game logic:
The match on the field is [GAME]. The team named in [GOAL] is the team that scores. The opposing team is the other team from [GAME]. For example, if [GAME] is "England vs Croatia" and [GOAL] is "England", then England scores and Croatia defends.
Each team has 10 outfield players plus 1 goalkeeper on the pitch. The teams wear clearly different football kits inspired by their real team colors. No readable player names, no jersey numbers, no logos, no crests and no visible text on any kits. The goalkeeper of the opposing team wears a clearly contrasting bright goalkeeper kit.
The whole video stays in one unbroken handheld one-shot. The camera begins beside the person in the stands, showing them from a close casual angle while also showing the packed stadium crowd around them and the pitch visible below. They are casually eating pizza and watching the match.
The smartwatch gives exactly one short subtle alert sound or haptic-style notification cue. No repeated alert, no double notification, no second alert sound. The alert is brief and natural.
The person notices the smartwatch alert, briefly glances down toward their wrist, then looks toward their friend / the camera with a knowing confident expression and says naturally:
"[GOAL] scored."
The dialogue must use the actual team name from [GOAL]. For example, if [GOAL] is "England", the person says: "England scored."
The notification is understood only through the single smartwatch alert and the person's reaction. Do not show a readable smartwatch screen, no readable notification, no app names, no message content, no numbers, no icons, no watch face details, no visible interface text.
The friend replies from offscreen, surprised:
"Really?"
The person answers confidently:
"Yes."
The friend immediately reacts while still filming. The friend does not cut away. The friend physically pans, tilts, and zooms the same handheld camera from the person down toward the football field in one continuous movement from the same spectator seat.
The camera movement from the person to the pitch must be visibly continuous. The shot must preserve the same handheld camera position, same perspective height, same stadium environment, same ambient crowd audio, and same physical location in the stands. There must be no hard cut, no jump cut, no transition, no inserted football clip, no broadcast insert, no replay, and no separate goal scene.
As the camera swings from the person toward the pitch, the viewer should briefly see natural motion blur, nearby fans, stadium seats, railings, heads of spectators, and parts of the stand passing through the frame edges. These foreground elements prove that the camera is still physically in the spectator stands and is simply being swung toward the field.
The camera must remain in the same one-shot and stay physically in the spectator stands the entire time. It must never cut, never switch to a broadcast angle, never teleport to field level, never become clean sports footage, and never become a separate sports clip.
Use [GOAL_REFERENCES] only to understand the football goal choreography. These images are not video frames and must never appear as shots, cutaways, inserts, full-screen images, or separate camera angles. They only describe the type of attacking movement, goalkeeper reaction, ball path, timing, goal angle, crowd energy, and net impact that should happen inside the same continuous handheld stadium shot.
Do not insert the reference images as separate frames. Do not cut to them. Do not show them as screenshots inside the video. Do not recreate their exact broadcast-camera angle. Do not copy any visible advertising, banners, logos, signs, letters, numbers, scoreboard elements, UI elements, or text from the goal reference images.
The final goal action must happen naturally inside the same continuous handheld one-shot from the spectator stands. The camera angle must stay from the friend's imperfect handheld spectator-seat perspective. It must not become a field-level camera, broadcast camera, replay angle, drone angle, tripod shot, or separate sports clip.
During the continuous pan and zoom toward the field, include a brief realistic mobile-camera refocus effect: for a short moment the image becomes slightly soft and blurry because the camera is refocusing from the person and nearby crowd to the distant pitch below. This should feel like a natural autofocus shift caused by the same continuous handheld camera movement, not like an artificial transition. The blur should be subtle and temporary, then the field becomes sharp enough to understand the goal action.
On the pitch, [GOAL] is attacking. The action is inspired by the movement shown in [GOAL_REFERENCES], but adapted to the current match [GAME] and viewed only from the same handheld spectator perspective in the stands.
A player from [GOAL] creates a clear scoring chance near the penalty area. The opposing defenders and goalkeeper react too late. The attacker from [GOAL] finishes the chance and scores.
The ball must stay clearly visible during the scoring moment. It must clearly cross the goal line and hit the inside of the net. The net visibly ripples on impact. The goalkeeper and defenders arrive too late.
The goal must be clear and not only implied by the crowd. The viewer must see the attacking action, the ball crossing the goal line, and the ball hitting the net, all from the same handheld spectator-seat angle.
The packed stadium instantly erupts with loud cheering, fans jumping, waving arms and celebrating. The audio should remain continuous and natural, with no sound break or edited transition.
Still in the same continuous one-shot, the friend quickly swings the camera back up to the person sitting beside them in the stands. This must also be a continuous handheld camera movement, not a cut. The same stadium seating location must again be obvious: packed fans around them, regular seats, stadium rows, railings and the pitch below.
The person smiles proudly, takes another bite of pizza with the pizza hand, looks toward the camera and says:
"I told you."
The person keeps eating pizza while the crowd roars around them. The tone is funny, confident, spontaneous and viral, like a perfect real-life vlog moment captured by a friend.
Visual style:
realistic smartphone-style vlog footage, authentic handheld filming, natural daylight, casual influencer energy, slight natural camera shake, friend-filmed perspective, believable stadium seating perspective, realistic football match atmosphere, realistic crowd behavior, realistic football physics, spontaneous viral realism, no cinematic perfection, no glossy commercial look, no drone shots, no tripod shots, no scene cuts, no montage, no slow motion.
Important continuous shot rule:
The entire video is one continuous handheld shot. The friend starts filming the person, hears the prediction, then physically swings the same camera down to the field, zooms in from the stands, captures the goal live, and physically swings the same camera back to the person. No cuts, no jump cuts, no inserted clips, no separate football footage, no replay, no broadcast angle, no full-screen match insert, no change of camera position.
Important camera movement rule:
The move from the person to the pitch must be a visible handheld pan / tilt / zoom from the spectator seat. Nearby fans, seat rows, railings, and stadium foreground elements should remain visible during the movement or around the frame edges. The goal is captured from the same spectator-seat position, not from a new camera.
Important reference rule:
Use [GOAL_REFERENCES] only as choreography references for the football goal. Do not treat them as sequential video frames. Do not insert the screenshots as separate frames, do not cut to them, do not recreate their broadcast-camera angle exactly, and do not copy any text, logos, ads, banners, signage or scoreboard elements from them. The goal must happen naturally inside the same handheld one-shot from the spectator stands.
Important hand rule:
The person has exactly two visible hands and two visible arms throughout the entire video. One hand holds pizza. The other hand rests on the lap / upper thigh and wears the smartwatch. No extra hands, no third hand, no duplicated hands, no distorted fingers.
Important location rule:
The person must be visibly sitting in a normal spectator seat in the stadium stands, surrounded by fans. Do not place them on the roof, outside the stadium, on a rooftop platform, in a VIP suite, on a balcony, on a terrace or anywhere unusual.
Important smartwatch rule:
There is exactly one smartwatch in the scene: one black modern smartwatch worn on the wrist of the hand resting near the lap / upper thigh. The watch gives exactly one short subtle alert. The watch display must not be clearly readable. No readable smartwatch notification, no readable watch text, no visible message, no visible app name, no visible numbers, no detailed watch UI, no extra smartwatches.
Important device rule:
No smartphone is visible anywhere in the video. No phone in hand, no phone on lap, no phone on seat, no phone in pocket visible, no second device, no extra device.
Important football rule:
[GOAL] scores the goal. The ball must clearly cross the goal line and hit the net. The goal must be shown visually, not only suggested by the crowd reaction.
Absolutely no text in the video. No captions, no subtitles, no title cards, no labels, no letters, no numbers, no logos, no watermarks, no UI text, no phone interface text, no watch interface text, no menu text, no street sign text, no random typography, no written words, no text overlays, no text artifacts anywhere in the video.
