Промпты для видео "Гонка с истребителем"
Я все делал в Syntx.ai (https://syntx.ai/welcome/mEQ2WKuT) Нейросети: Gpt Image 2 и Seedance 2.0 (доступен от подписки PRO и выше) Нужно: фото машины, фото водителя, фото пилота. Мой результат ищите в https://t.me/viviannru
*Важно! Промпты универсальные, подходят для любой машины и людей (кроме суперзвезд) *Смотрите скрины, чтобы понимать, куда и какие изображения я отправлял.
1.Подготавливаем фотографии.
(Раздел ИЗОБРАЖЕНИЯ - Gpt Image 2 - Соотношение сторон 16:9 - Детализация среднее - Качество 2к)
5 РАКУРСОВ:
1. Верхний левый кадр — вид строго спереди (фронтальный вид, видно решётку радиатора, фары, бампер, капот, лобовое стекло и часть крыши).
2. Верхний правый кадр — вид три четверти спереди (примерно под углом 45 градусов спереди-сбоку, видно переднюю часть, боковую сторону и крышу).
3. Нижний левый кадр — вид три четверти сзади с противоположной стороны (примерно под углом 45 градусов сзади-сбоку, с другой стороны кузова, видно заднюю часть, противоположный бок и крышу).
4. Нижний правый кадр — вид строго сзади (задний вид, видно задний бампер, задние фонари, багажник, заднее стекло и часть крыши).
5. Крупно значок авто спереди
РАКУРС КАМЕРЫ:
На всех четырёх кадрах камера расположена чуть выше уровня капота, немного сверху, под лёгким наклоном вниз, так чтобы хорошо была видна крыша автомобиля сверху. Не строго на уровне колёс, а немного приподнято.
АВТОМОБИЛЬ:
Точно сохрани модель, форму кузова, цвет, диски, фары, решётку, все детали и пропорции автомобиля с референса. Машина должна быть идентична оригиналу на всех четырёх ракурсах.
ФОН И СВЕТ:
Одинаковый нейтральный фон на всех четырёх кадрах — однотонный светло-серый студийный фон или чистый асфальт без посторонних объектов. Мягкое равномерное освещение, без резких теней, как в студийной автомобильной фотосессии.
ТЕХНИЧЕСКИЕ ТРЕБОВАНИЯ:
Формат 16:9. Все кадры, аккуратно разделены тонкими белыми линиями или небольшими отступами. Максимальный фотореализм, как реальная студийная съёмка автомобиля. Также добавь текст название автомобиля.
CRITICAL — preserve identity 100%:
Keep the face absolutely identical to the reference: same facial features, same face shape, same eye shape and color, same nose, same lips, same eyebrows, same skin tone, same age, same makeup (if any).
Keep the hair 100% identical: same color, same length, same hairstyle, same parting, same texture, same volume.
Do NOT beautify, do NOT change proportions, do NOT make the person younger or older, do NOT alter ethnicity. The person must be perfectly recognizable in every shot.
CRITICAL — preserve outfit and accessories EXACTLY as in the reference:
Keep the clothing 100% identical to the reference photo(s): same garment, same color, same cut, same fabric, same details, same prints, same stripes, same logos, same brooches/pins, same neckline. Do not add a jacket, blazer, scarf, hat, sunglasses or any other clothing item that is not visible in the reference.
Keep all accessories 100% identical: same earrings, same necklace, same rings, same watch, same brooch — exactly as shown in the reference.
Do NOT add any new accessories. Do NOT remove existing accessories.
If only the upper body is visible in the reference, logically extend the outfit downward in a neutral, realistic way that matches the style and color palette of the visible clothing (for example simple matching trousers/skirt and plain shoes), keeping it minimal and non-distracting.
Style: hyper-realistic photography, studio quality, 8K, sharp focus, professional color grading, cinematic soft lighting, shot on Hasselblad, 85mm lens, clean neutral light grey studio background, soft even lighting without harsh shadows. Consistent lighting and background across all 6 shots.
COMPOSITION — single reference sheet, overall canvas aspect ratio 16:9 (horizontal), divided into a strict, clean grid with thin neutral dividers between panels:
LEFT HALF of the canvas (occupies 50% of the width, full height) — split vertically into 2 EQUAL TALL VERTICAL PANELS (full-body shots, head to toes, character fills the panel from top to bottom with small headroom):
Left vertical panel — Full body, FRONT view: standing straight, natural relaxed confident pose, arms relaxed at sides, looking at camera.
Right vertical panel — Full body, BACK view: exact same standing pose seen from directly behind, same scale and same vertical alignment as the front view, showing the back of the outfit and hair.
RIGHT HALF of the canvas (occupies the other 50% of the width, full height) — split into a 2x2 GRID of 4 EQUAL PANELS (close-up portraits, head and shoulders, tight framing on the face):
3) Top-left panel — Face CLOSE-UP, FRONT view: head and shoulders, looking straight at camera, neutral calm expression.
4) Top-right panel — Head CLOSE-UP, BACK view: directly from behind, showing the back of the head and hairstyle in full detail.
5) Bottom-left panel — Face CLOSE-UP, THREE-QUARTER view from the RIGHT side (face turned slightly so we see more of the right side of the face).
6) Bottom-right panel — Face CLOSE-UP, THREE-QUARTER view from the LEFT side (face turned slightly so we see more of the left side of the face).
All 6 shots must show the SAME person, SAME outfit, SAME accessories, SAME hairstyle, SAME lighting, SAME background — only the camera angle and framing changes. Consistent character design across all frames, like an official movie character turnaround or a fashion lookbook.
Layout rules: keep the 16:9 master frame; left side = 2 vertical full-body panels of equal width and full height; right side = 2x2 grid of equal close-up panels; thin clean separators between all panels; no text, no labels, no watermarks, no logos, no extra characters, no duplicates of the person inside a single panel.
Ultra-detailed, photorealistic skin texture, realistic fabric texture, realistic hair strands, natural shadows. The final result must look like six real photographs of the same real person taken in one studio session, assembled into one professional 16:9 character reference sheet.
CRITICAL — preserve identity 100%:
Keep the face absolutely identical to the reference: same facial features, same face shape, same eye shape and color, same nose, same lips, same eyebrows, same skin tone, same age, same makeup (if any).
Keep the hair 100% identical: same color, same length, same hairstyle, same parting, same texture, same volume.
Do NOT beautify, do NOT change proportions, do NOT make the person younger or older, do NOT alter ethnicity. The person must be perfectly recognizable in every shot.
CRITICAL — preserve outfit and accessories EXACTLY as in the reference:
Keep the clothing 100% identical to the reference photo(s): same garment, same color, same cut, same fabric, same details, same prints, same stripes, same logos, same brooches/pins, same neckline. Do not add a jacket, blazer, scarf, hat, sunglasses or any other clothing item that is not visible in the reference.
Keep all accessories 100% identical: same earrings, same necklace, same rings, same watch, same brooch — exactly as shown in the reference.
Do NOT add any new accessories. Do NOT remove existing accessories.
If only the upper body is visible in the reference, logically extend the outfit downward in a neutral, realistic way that matches the style and color palette of the visible clothing (for example simple matching trousers/skirt and plain shoes), keeping it minimal and non-distracting.
Style: hyper-realistic photography, studio quality, 8K, sharp focus, professional color grading, cinematic soft lighting, shot on Hasselblad, 85mm lens, clean neutral light grey studio background, soft even lighting without harsh shadows. Consistent lighting and background across all 6 shots.
COMPOSITION — single reference sheet, overall canvas aspect ratio 16:9 (horizontal), divided into a strict, clean grid with thin neutral dividers between panels:
LEFT HALF of the canvas (occupies 50% of the width, full height) — split vertically into 2 EQUAL TALL VERTICAL PANELS (full-body shots, head to toes, character fills the panel from top to bottom with small headroom):
Left vertical panel — Full body, FRONT view: standing straight, natural relaxed confident pose, arms relaxed at sides, looking at camera.
Right vertical panel — Full body, BACK view: exact same standing pose seen from directly behind, same scale and same vertical alignment as the front view, showing the back of the outfit and hair.
RIGHT HALF of the canvas (occupies the other 50% of the width, full height) — split into a 2x2 GRID of 4 EQUAL PANELS (close-up portraits, head and shoulders, tight framing on the face):
3) Top-left panel — Face CLOSE-UP, FRONT view: head and shoulders, looking straight at camera, neutral calm expression.
4) Top-right panel — Head CLOSE-UP, BACK view: directly from behind, showing the back of the head and hairstyle in full detail.
5) Bottom-left panel — Face CLOSE-UP, THREE-QUARTER view from the RIGHT side (face turned slightly so we see more of the right side of the face).
6) Bottom-right panel — Face CLOSE-UP, THREE-QUARTER view from the LEFT side (face turned slightly so we see more of the left side of the face).
All 6 shots must show the SAME person, SAME outfit, SAME accessories, SAME hairstyle, SAME lighting, SAME background — only the camera angle and framing changes. Consistent character design across all frames, like an official movie character turnaround or a fashion lookbook.
Layout rules: keep the 16:9 master frame; left side = 2 vertical full-body panels of equal width and full height; right side = 2x2 grid of equal close-up panels; thin clean separators between all panels; no text, no labels, no watermarks, no logos, no extra characters, no duplicates of the person inside a single panel.
Ultra-detailed, photorealistic skin texture, realistic fabric texture, realistic hair strands, natural shadows. The final result must look like six real photographs of the same real person taken in one studio session, assembled into one professional 16:9 character reference sheet.
2.Создаем видео.
Переходим в Раздел Видео - Выбираем Seedance 2.0 - Режим Pro - 720p (если мажоры, то 1080р) - Соотношение сторон любое (у меня 4:3 или 16:9) - Длительность 15 сек. Загружаем фото машины, фото водителя, фото пилота, после вставляем промпт и вручную удаляем все "@image1" , "@image2" и "@image3" в промпте и заново их прописываем (когда будете вводить "@" там можно будет выбрать нужный кадр), так они привяжутся к промпту:
【Style】Ultra-cinematic blockbuster cinematography in the tradition of Michael Bay action films, shot on professional cinema camera with anamorphic lenses, 2.39:1 widescreen, shallow depth of field, dynamic motion blur, deep rich color grade, sharp highlights, golden bright daylight, lens flares on the sun, high dynamic range, professional film quality. 【Duration】15 seconds 【Native Audio】Powerful cinematic engine roar building in pitch, screaming jet afterburner howl, rushing wind, tire roar, deep bass impact, no dialogue. [00:00-00:03] Shot 1: THE DRIVER (Side Close-up, through side window). Bright daytime. Side profile of the car driver (face and outfit reference @Image2) seated inside the car (interior matches the car from @Image1), shot through the side window from a low close angle. The driver grips the wheel, jaw tight, eyes locked forward with fierce determination, body subtly vibrating from extreme speed. Sun glints sharply across the glass. Tight slow push-in. Engine roar builds. [00:03-00:06] Shot 2: THE PILOT (Side Close-up, matching angle). Cut to the same framing logic: side profile of a fighter-jet pilot (face clearly reference @Image3) inside the cockpit of a Russian Su-57 fighter jet. The pilot's helmet visor is fully raised, his entire face clearly visible and well-lit, eyes intense and focused, sweat on his brow. Bright daylight fills the cockpit, sun reflecting on the canopy. Tight slow push-in. Jet howl rises in the mix. [00:06-00:08] Shot 3: BACK TO THE DRIVER (Side Close-up). Cut back to the driver (@Image2) through the side window, same tight side profile, his expression hardening, knuckles white on the wheel, intensity peaking. Slow push-in. Engine and jet noise both layered loud. [00:08-00:13] Shot 4: THE RACE (Crane Pull-Back to Front-Side Wide). Smooth cinematic crane move: the camera lifts and glides backward away from the driver, pulling out to a dynamic front three-quarter angle revealing the full chase on a long straight runway in bright daylight. On the RIGHT, the car from @Image1 hurtles forward at insane speed, wheels a blur, asphalt streaking, faint tire smoke. On the LEFT, a Russian Su-57 fighter jet FLIES low through the air just above the car's height, afterburners blazing, not touching the ground, ripping through the sky beside it. Extreme speed and energy: roadside markers, grass, debris and dust streak past and fling violently backward, heavy motion blur on everything except the two subjects. Camera locks to a front three-quarter tracking position, both racing toward and past the lens at blistering velocity, neck and neck. Overwhelming engine and jet sound. [00:13-00:15] Shot 5: THE WIN (Same Front-Side Angle, fixed). Camera holds the exact same front three-quarter level. The car (@Image1) slams the throttle and surges forward with a burst of raw power, pulling decisively ahead of the Su-57, the jet visibly falling behind into the background as the car dominates the frame. Maximum dynamic blur, dust exploding behind it. Engine roar peaks. Triumphant final daytime frame. Car appearance, color and details stay identical to @Image1 throughout. Driver identity matches @Image2, pilot face clearly matches @Image3 with raised visor and visible face, faces stable with no distortion. Su-57 design consistent and always airborne. Cinematic professional camera look maintained the whole time.