
FIFA World Cup 2026 VIP Broadcast Prompt — Live TV Spectator Cutaway
GPT Image 2 prompt example — copy the text below or click Try this prompt to generate on ImageGen 2.
GPT Image 2 Prompt
Create a photorealistic candid live football television broadcast shot using the uploaded image as the exact facial identity reference. Preserve the subject’s exact face, skin tone, age, facial proportions, distinctive features, gender presentation, ethnicity, hairstyle, and modesty. If the subject wears a hijab, preserve it exactly with no visible hair or neck. Use the uploaded image only as a facial identity reference. Do not copy the original head tilt, expression, pose, or camera angle. The scene takes place during a FIFA World Cup 2026 match between [TEAM A] and [TEAM B] at [STADIUM NAME], [CITY]. The subject supports [SUPPORTED TEAM] and is inside a premium VIP hospitality suite behind a clear glass railing overlooking the pitch. Outfit: • Official [SUPPORTED TEAM] [COLOR] home jersey • Elegant dark navy blazer or cardigan • Black trousers • Preserve the uploaded hairstyle or headwear exactly; if hijab, use a deep navy or team-colored hijab with no visible hair or neck • FIFA-style event lanyard • Slim watch • Small [SUPPORTED TEAM] scarf draped naturally This is a candid spectator cutaway. The subject is unaware of the television camera and fully focused on the match. Body orientation: • Body turned about 45° toward the pitch • Head naturally aligned with the body • Upright posture with balanced shoulders • No awkward tilt Gaze: Toward the [RIGHT/LEFT] side of frame, slightly downward toward the pitch. No eye contact with the camera. Expression: [TENSE AND HOPEFUL / EXCITED AND NERVOUS / CALM AND FOCUSED / SERIOUS AND ANALYTICAL / SHOCKED BUT REALISTIC / JOYFUL BUT NATURAL] Eyebrows slightly [TIGHTENED/RAISED]. Lips slightly [PARTED/CLOSED]. The subject is watching an important [SUPPORTED TEAM] attack in the final minutes. Pose: Both hands rest lightly on the glass railing with realistic anatomy and relaxed fingers. No thumbs-up, waving, peace signs, or camera-facing gestures. Surroundings: • Five supporting spectators around the subject, partially cropped • Spectators wear [TEAM A] and [TEAM B] jerseys or refined matchday clothing • Everyone naturally watches the pitch • Softly blurred heads, shoulders, scarves, and raised hands in the foreground for depth • Do not obstruct the subject’s face Environment: • Premium VIP suite architecture • Dark suite framing • Clear glass railing with subtle reflections • Softly blurred crowd and stadium background • No reflections across the face Camera: Authentic live sports broadcast angle with 200–400mm telephoto compression. Waist-up framing. Face and eyes sharp, surrounding spectators slightly softer. Natural asymmetrical composition. Lighting: Realistic FIFA World Cup stadium lighting mixed with soft VIP-suite ambient light. Natural skin texture, realistic fabric folds, and mild broadcast compression. Add a compact professional scoreboard at the top-left. Scoreboard format: [TIME] [TEAM A FLAG] [TEAM A CODE] [TEAM A SCORE] 🏆 [TEAM B SCORE] [TEAM B CODE] [TEAM B FLAG] Example: 73:18 🇫🇷 FRA 1 🏆 1 SEN 🇸🇳 Scoreboard design: • White rounded timer box with bold black text • Dark charcoal team boxes • Accurate flags • Bold three-letter team codes • Bright cyan score boxes with large black numbers • White center box with a black-and-gold trophy icon • Compact connected graphics • Sharp and readable • No "LIVE" text • Never cover the subject's face The image must look like a genuine spontaneous spectator cutaway from a live FIFA World Cup 2026 television broadcast, not a studio portrait, fashion shoot, advertisement, CGI, or illustration. Photorealistic, realistic anatomy, natural hands and fingers, accurate facial identity, live television realism, 4K broadcast quality, aspect ratio 4:5.
Pro Tips
This is a template prompt — replace [TEAM A], [TEAM B], [STADIUM NAME], [SUPPORTED TEAM], and pick one expression option. The scoreboard example line (73:18 🇫🇷 FRA 1 🏆 1 SEN 🇸🇳) is critical for broadcast UI accuracy. 'Unaware of the television camera' plus 'no eye contact' separates this from portrait shots.


