Целью было снять одним кадром конкретную комнату в фотореалистичном миниатюрном кукольном домике, завершив движение камеры переходом в следующую комнату. Длительность около девяти секунд. Крошечный трейдер ест лапшу перед тремя мониторами. Гигант (я) наблюдает за ним через заднее окно. Трейдер резко бросает: «Оставь меня в покое!» и что-то кидает в стекло. Гигант говорит: «Прости!», и камера плавно переезжает в соседнюю йога-студию, где женщина смотрит в планшет.

Изначально короткий кадр казался простым, но на каждом этапе производства возникли сложности: два говорящих персонажа с липсинком, бросок с реалистичной физикой, непрерывное движение камеры между двумя комнатами и крупный план лица, удерживающий кадр несколько секунд. Вот результаты, представленные рядом с промптами.

План: сначала три изображения

Метод заключался в том, чтобы утвердить ключевые изображения перед генерацией любого видео: начало комнаты трейдера, гигант, наблюдающий за ним, и финальный кадр в йога-студии.

Начало

Комната трейдера

Миниатюрный трейдер за тремя мониторами с чашкой лапши; край лица гиганта у окна; темная разделительная стена слева.

Часть предыдущей комнаты, перегородка и лишь край лица гиганта.

Середина

Гигант наблюдает

Лицо огромного блондина занимает всё заднее окно, он смотрит вниз на трейдера.

Его лицо заполняет окно, взгляд прикован к трейдеру. Позже этот кадр станет общей точкой монтажа.

Конец

Зал для йоги

Зал для йоги по соседству: женщина на коврике с планшетом, великан у окна, слева - стена торгового зала.

Тот же размер окна, высота пола и масштаб лица, одна комната правее.

Картинки, раунд 1: 33 изображений в чате ChatGPT

Первая попытка была обычным диалогом с ChatGPT на плане Plus: описать комнату, прикрепить фото моего лица, попросить изменения. Это потребовало от меня 26 сообщений и привело к созданию 33 изображений, при этом около 18 моих сообщений были исправлениями. Каждый ответ перестраивал сцену с нуля, поэтому исправление одной детали ломало другую.

Пустая комната с окном и столом, без мониторов и людей.
Нет мониторов, нет трейдера.
Захламленный торговый зал ночью с видом на город, без гиганта в окне.
Слишком хаотично, и великан отсутствует.
Зал для йоги, где слева все еще виден трейдер из предыдущей комнаты.
Трейдер из старой комнаты все еще в кадре.
Портрет блондина с заметно отличающейся от референса формой головы.
«Совершенно другой человек»
Лицо гиганта разделено между двумя окнами, словно это два разных человека.
Я, разделенный на два окна.
Зал для йоги с окном, которое заметно меньше референсного.
Окно размером 78%, как и запрашивалось.

Ближе к концу я указал точную геометрию пикселей для окна и обоих людей, а затем попросил чат измерить собственный результат. Он сообщил, что окно составляет 485 × 644 px при 621 × 811 px в промпте: 136 px слишком узкое и 167 px слишком короткое. Модель, которая перерисовывает изображение по словам, не может попасть в точные значения пикселей, какими бы точными ни были слова.

Изображения, раунд 2: 11 изображений, в основном с первой попытки

Второй раунд начался с лучшего изображения из раунда 1 и был запущен в Codex через платформу easyai.video с установленными нашими навыками работы с изображениями. Восемь запросов позволили получить одиннадцать изображений. Шесть из восьми запросов были новыми изменениями, каждое из которых было одобрено с первой попытки; два других были исправлениями положения стены и высоты пола.

Изображение комнаты трейдера из раунда 1, со светящимся потолком и необъяснимым светом на постере с автомобилем.
Начало: лучший кадр из раунда 1.
Та же комната с другим освещением от потолочного светильника, с более четким лицом у окна.
1 · один источник света, более четкое лицо.
Та же комната, но взгляд великана опущен на трейдера.
2 · фокус на трейдере.
Та же комната, сместившаяся за темную перегородку; гигант виден лишь у края окна.
3 · стена между комнатами.
Зал для йоги с той же геометрией и гигантом в окне.
4 · йога-студия.

Между раундами не произошло никаких магических изменений. Изменился способ постановки задачи:

  1. Редактируйте, а не перегенерируйте. Каждый запрос основывался на последнем утвержденном изображении и сохранял всё, что уже было сделано правильно.
  2. Одно изменение на запрос. Сначала свет, затем лицо, затем взгляд, затем композиция. Никогда не вносите четыре правки в одном сообщении.
  3. Одна задача на одно исходное изображение. «Изображение 1 является основным объектом редактирования. Изображение 2 служит только для левой полосы».
  4. Сначала измерьте, затем закрепите. Вместо «сделай комнату уже» в промпте указывалось положение объектов в исходнике и их новое положение: сместить комнату на 275 px вправо с масштабом 100%, перекладина окна остается на y = 626.
  5. Используйте навык, а не импровизацию. Навыки работы с изображениями определяли сценарий использования (композитинг, сохранение идентичности) и каждый раз писали промпт в одной и той же структуре.

Вы можете сделать то же самое в своей среде. Codex и Claude Code поддерживают загрузку навыков: папки с инструкциями и, опционально, скриптов, которые агент считывает перед выполнением действий. На GitHub и других публичных ресурсах доступен широкий спектр навыков для работы с изображениями и видео. Выбирайте навыки, которые подходят вашей модели и задачам монтажа, и используйте их для автоматического улучшения промптов. Платформа easyai.video уже включает эти навыки, а также форматы промптов, которые ожидают каждая видеомодель.

Видео, попытка 1: вся сцена одним 8-секундным планом

После утверждения трех изображений в первых попытках создания видео я просил всё в одной генерации: поесть, заметить, закричать, бросить, извиниться, перейти в следующую комнату. В качестве эксперимента я начал с бесплатных генераций Google Flow. Google Flow использовал три изображения в качестве референсов; в дубле 2 использовался переписанный промпт, где указывался говорящий для каждой реплики и прослеживался путь чашки к заднему окну. Seedance 2.5 использовал изображения как начальный кадр, референс изображения и конечный кадр в своем режиме omni-reference.

Дубль 1

Google Flow

Начинается с нашего кадра, затем великан произносит обе реплики, прежде чем что-либо будет брошено. Чашка летит в камеру, а не в окно, и трейдер оставляет свою чашку себе. Зал для йоги появляется через подмену, а не через сдвиг.

Дубль 2

Google Flow

Наш первый кадр проигнорирован: вместо него - арочный дверной проем и более светлая комната. Появляются два гиганта, затем входит человек в полный рост и бросает чашку. Никто не говорит «Извините». Финал происходит в другой йога-студии.

Дубль 3

Seedance 2.5 · 480p черновик

Самый близкий из трех: чашка улетает от нас и разбивается о заднее стекло, а камера скользит в йога-зал. Рендеринг в виде дешевого чернового варианта 480p.

Проблема была не в изображениях. В кадре было запрошено слишком много вещей одновременно, и модель проигнорировала часть из них или изменила порядок остальных.

Видео, попытка 2: два коротких плана через общий кадр

Решением стало разделение сцены в месте естественного разрыва. Кадр A длится от начального до среднего кадра в течение 3 секунд: трейдер ест, а гигант поднимается в окне. Кадр B длится от того же среднего кадра до конца в течение 6 секунд: линия, бросок, извинение и переход в йога-студию. Два кадра имеют общий кадр, что обеспечивает общую композицию на монтаже. В этой версии трейдер бросает наушники вместо чашки с лапшой: разлетающиеся по окну макароны выглядели неприятно, и Seedance отрисовал их слишком крупными.

Оба кадра были созданы с помощью Wan 3.0 на Higgsfield, в нативном разрешении 1080 × 1920 при 30 fps с генерацией звука.

Кадр А · 3 с

Wan 3.0

Трейдер продолжает есть и не поднимает глаз; гигант входит в кадр и замирает в центре.

Кадр B · 6 с

Wan 3.0

«Оставь меня в покое!», наушники ударяются о стекло и падают, «Извини», затем переход в йога-студию, завершающийся на финальном кадре. В конце добавилось несколько музыкальных нот, что противоречило промпту.

A + B · 9 s

Объединены в общем кадре

Во второй части текстура кожи лица немного отличается, поэтому склейка заметна. Для непрерывности действия предпочтительнее модель, способная выдать один цельный кадр, такая как Seedance.

Тот же кадр на MiniMax H3: полная модель против turbo

Затем мы снова отрендерили кадр B на MiniMax H3, используя нашу собственную копию модели в рамках ежедневной квоты Hugging Face на GPU, с теми же двумя кадрами, тем же сюжетом и тем же сидом (42). Платформа easyai.video сначала переписывает промпт в формат, который ожидает H3; ниже представлен промпт, который был отправлен в модель после этой переработки.

Кадр B · Wan 3.0

1080 × 1920 · 30 fps

Референс: каждое действие по порядку, завершающееся на финальном кадре.

Кадр B · H3 полный

768 × 1344 · 24 fps · 28 шагов

Сравнимо с Wan 3.0 в этом кадре: линия, бросок, извинение и движение - всё выдержано. Разрешение ниже; расходуется часть ежедневной квоты GPU.

Кадр B · H3 turbo

768 × 1344 · 24 fps · 6 шагов

Соблюдает сюжетные моменты, но крупное лицо, наушники и переход между комнатами выдают генерацию.

Лицо гиганта в тот же момент: H3 full слева и H3 turbo справа; у turbo-версии на коже видны темные пятна.
Тот же момент, 1.6 с кадра B, в полный размер. Слева: H3 full. Справа: H3 turbo, с темными пятнами на коже.
H3 турбо-кадр, где брошенные наушники появляются в виде плоской черной иконки на носу великана.
Turbo, 2.0 с: наушники выглядят как плоская иконка, наложенная на лицо, а не как объект в полете.
H3 turbo-кадр при переходе между комнатами, с лишними листьями, пролетающими на переднем плане.
Turbo, 4.3 с: никто не просил о дрейфе на переднем плане во время движения.

Turbo подходит для черновиков. Это удобно для планирования движения камеры или проверки композиции кадров. Если лицо занимает весь кадр, рендерите дубль на полной модели.

Сводка затрат по каждой модели

Красные крестики обозначают неприемлемые дубли. Желтые галочки обозначают дубли, близкие к цели, но с оставшимися несоответствиями; для Seedance к ним относятся слишком крупные макароны. Каждая строка таблицы соответствует одной модели и платформе, с указанием общей стоимости футажа.

Модель · платформаФутажРезультатБазовая стоимостьПрибл. EUR
Google Flow2 × 8 с720 × 1280Бесплатные ежедневные кредиты€0
Seedance 2.5 черновик · Higgsfield8 с480 × 85424 кредитов€1.05
Wan 3.0 · Higgsfield3 с + 6 с1080 × 1920 · 30 fps31.5 кредитов (3.5 за секунду)€1.38
MiniMax H3 full · Hugging Face6.58 с768 × 1344 · 24 fps≈ 10.9 / 40 ежедневных GPU минут (27.3%)€0.073
MiniMax H3 turbo · Hugging Face6.58 с768 × 1344 · 24 fps≈ 4.2 / 40 ежедневных GPU минут (10.5%)€0.028

Оценки Higgsfield основаны на записанном плане за $49 / 1,000 кредитов, при условии использования всех кредитов. Оценки Hugging Face распределяют ежемесячную подписку в $9 на 30 дней, а затем умножают эту дневную долю на процент квоты в логах запуска, включая кондиционирование. Это распределенные затраты на подписку, а не счета за каждый запуск; неиспользованная квота повышает эффективную стоимость.

Конвертация: $1 ≈ €0.893, округлено по справочному курсу ЕЦБ. Тарифы и квоты могут меняться; проверьте цены Higgsfield и Hugging Face PRO для вашего аккаунта.

Основные выводы

  1. Сначала создайте ключевые кадры, а затем анимируйте переходы между ними. Общие кадры помогают согласовать многокадровую сцену, но проверяйте текстуру кожи и освещение в местах склейки.
  2. Вместо повторного запроса отредактируйте утвержденное изображение. Одно изменение за запрос, одна задача на одно исходное изображение, используйте реальные позиции вместо прилагательных.
  3. Turbo-модели предназначены для черновиков. Рендерите финальные дубли на полной модели, если лицо занимает большую часть кадра.
  4. Модель с открытым исходным кодом может не уступать платной модели в конкретном кадре. Сравнение H3 и Wan 3.0 здесь. Использование OSS-модели на GPU может дать схожий результат при гораздо меньших затратах, чем платная модель через API, в зависимости от использования оборудования и стоимости хостинга.
  5. Используйте навыки для автоматического улучшения промптов для изображений и видео. Специальные инструкции преобразуют короткий запрос в структуру и ограничения, необходимые каждой модели.

Раунд 1 · чат ChatGPT

Один из промптов с точной геометрией пикселей

Use gpt_mainref_shot1.png as the strict geometry and scale reference. Recreate the same dollhouse room proportions, camera position, perspective, window size, giant-person scale, and miniature-person scale. Change only the room content from the trader bedroom into a yoga/living room.
Final canvas: exactly 941 × 1672 px, vertical.
Do not change the camera position, focal length, room depth, wall proportions, floor perspective, or window proportions from gpt_mainref_shot1.png.
Main window geometry must match gpt_mainref_shot1.png exactly:
outer window frame: x=169 to 789, y=197 to 1007
outer window size: 621 × 811 px
visible glass area: x=193 to 767, y=230 to 988
glass size: 575 × 759 px
horizontal window divider: x=181 to 779, y=620 to 637
window center approximately x=479
the window must occupy about 66% of the entire image width
do not make the window smaller
do not move the bottom edge of the window upward
Behind the window is one giant adult man. Use the supplied male portrait reference for identity and pose. Preserve the same face proportions, head shape, nose, jaw, forehead, hairline, eye spacing, skin texture, light blond hair, stubble, light-blue T-shirt, and body proportions.
The giant man must have the same scale as the person in gpt_mainref_shot1.png:
head from top of hair to bottom of chin approximately x=292 to 710, y=228 to 824
head size approximately 419 × 597 px
visible shoulders and upper torso extend across almost the entire 575 px width of the window
the giant person must visually fill the window, not appear distant
his head and shoulders must remain much larger than the miniature person inside the room
Pose of giant man:
body turned approximately 25 to 30 degrees toward screen-right
shoulders turned by the same angle as the head
head slightly turned toward screen-right
eyes looking downward and inward into the room at the woman
expression curious and observant
do not make him look toward the camera
do not reduce his face size
do not shorten or round his head
do not create a second copy of him anywhere
Room geometry must preserve the same apparent size as gpt_mainref_shot1.png. The floor, ceiling, left wall, right wall, and back wall must occupy the same proportions. The camera remains outside the dollhouse, looking slightly downward into the room from the same elevated frontal angle.
On the extreme left, include a narrow slice of the previous room followed by a full-height dark dividing wall. The dividing wall must run continuously from the top edge to the bottom edge of the image and clearly separate the two rooms. The previous room must occupy only a very narrow strip and must not contain any visible person.
Replace the trader bedroom with a bright, realistic yoga/living room.
Inside the new room:
one young adult woman doing yoga on a mat
one tablet standing in front of her, showing a yoga instruction video
one comfortable chair
a soft dress and light fabric casually draped over the chair
one small dressing table on the right side with a few cosmetic bottles
a vase with flowers
minimal tasteful plants
no bed
no desk with computers
no paper
no garbage bin
no cluttered trash
The miniature woman must use approximately the same scale as the trader in gpt_mainref_shot1.png.
Target miniature-person scale:
overall body region approximately 265 × 438 px
top of head around y=925 to 950
lowest visible body point around y=1360
do not place her higher in the frame
do not enlarge her beyond the trader’s scale
she must remain clearly miniature compared with the giant man outside
Place the yoga woman lower in the composition, around the lower central area of the room. Her head should begin approximately where the trader’s head begins in the reference. The majority of her body must stay below the bottom edge of the window.
Yoga mat:
place it low in the frame
approximately x=185 to 710
approximately y=1180 to 1510
roughly 525 × 330 px
keep perspective aligned with the floor exactly like the rug area in gpt_mainref_shot1.png
The woman is seated in a clear seated spinal twist yoga pose. Her torso remains upright. One hand supports her on the mat. Her legs are folded. The tablet is positioned in front of the mat near the lower-left edge of the mat, angled toward her.
Lighting:
natural daylight only, entering through the giant window
neutral soft daylight
ceiling lamp present but switched off
no warm yellow glow
no wall lamps
no hidden artificial lighting
no cinematic orange lighting
room illumination must come primarily from the window
Keep the room realistic and naturally lived-in, but clean.
Critical constraints:
window size must remain exactly equivalent to gpt_mainref_shot1.png
giant man scale must remain exactly equivalent to gpt_mainref_shot1.png
miniature woman scale must remain equivalent to the trader scale in gpt_mainref_shot1.png
woman must be positioned low in the composition
camera must not zoom out
camera must not move backward
do not increase visible wall space around the window
do not shrink the window
do not shrink the giant face
do not create duplicated body parts or duplicated people
do not show any part of the giant man inside the narrow previous-room strip on the far left
preserve one continuous architectural dividing wall from ceiling to floor
photorealistic, realistic lens perspective, consistent scale, high detail, 9:16 composition.

Раунд 2 · Codex с навыками работы с изображениями

Исправление геометрии, которое сработало

Use case: compositing. Generate one corrected photorealistic 9:16 dollhouse room-reveal keyframe, 941x1672 composition. Image 1 (mf1_sharp_reference_face) is the authoritative edit target for exact room geometry, object sizes, vertical positions, furnishings, person, face identity, textures and light. Image 2 (mf1_partition_reveal) supplies ONLY the left foreground strip and the giant man's partial-face placement. Image 3 (pasted plate) demonstrates the intended right-side cropping of the original room, keeping its proportions.

GEOMETRY IS THE PRIMARY EDIT. The left foreground strip in image 2 measures approximately 275 pixels of a 941-pixel width: neighboring-room glimpse at x=0..159, dark vertical dividing wall at x=160..274. Preserve this strip in the corrected frame. The remaining x=275..940 must show the LEFTMOST 666 pixels of image 1 at precisely its ORIGINAL SCALE and ORIGINAL HEIGHT. Translate image 1's room scene 275 pixels to the RIGHT and allow its rightmost 275 pixels to fall beyond the right border. This is a lateral camera reveal across a continuous dollhouse set. Keep the original room width and object proportions, expressed through partial offscreen framing. Use translation and clipping, with scale fixed at 100 percent. Maintain the source vertical coordinates throughout. Concrete anchors: original pendant center at x about 470 becomes x about 745, staying at y about 150; original window left glazing edge x about 193 becomes x about 468, with window top staying y about 230 and horizontal crossbar staying y about 626. The original window extends past the right frame border. Original bed left edge x about 593 becomes x about 868, so ONLY a narrow portion of the bed is visible at the extreme right. The original trader, chair and three monitors keep their exact source sizes and shift right by 275 pixels. The car poster remains its original size and shifts right identically. The original right wall artwork is beyond the frame edge. The rug and floor keep their original scale, pattern and vertical positions. The foreground strip aligns naturally with the room's open front.

FACE CHANGE: keep the same sharp blond man's identity, realistic skin, hair and original head scale from image 1, but move him laterally OUTSIDE the window to its left, as in image 2. Just a narrow sliver of blond hair, forehead, one eye, cheek and jaw peeks into the glazing along its LEFT edge, approximately x=468..525 in the final composition. The rest of the visible window is blue evening sky. Preserve the window frame and crossbar foreground occlusion. This partial visibility is achieved by the window edge clipping his head; preserve realistic head proportions.

World contract: same seated young man with glasses, black hoodie, dark trousers and white trainers at the same crypto workstation; same wood furniture and warm floor, dark rumpled bedding wherever visible, warm-white downward-facing pendant illumination with physically consistent falloff and shadows, softly dark ceiling, blue evening sky outdoors, crisp photorealistic facial detail. Preserve the source lighting and colors. Deliver exactly one corrected still with the room at full original scale and the right-side framing naturally clipped.

Google Flow · дубль 1 · 8 с, три референсных изображения

Промпт, использованный для дубля 1

Create an 8-second photorealistic cinematic video with synchronized English dialogue, in vertical 9:16.

REFERENCE ROLES
Opening: @generated/images/mf1_partition_reveal_corrected.png. Begin on this exact trader-room composition, including the foreground partition, neighboring-room sliver, original room proportions, floor height, tall window, pendant, workstation and cropped bed.
Intermediate appearance reference, around 2 seconds: @generated/images/mf1_looking_at_guy.png. Match the giant observer’s recognizable face, blond hair, blue eyes, realistic skin texture, light-blue T-shirt, head scale and downward gaze toward the seated trader. This guides his appearance during the encounter; camera movement determines the framing.
Ending: @generated/images/lf1_partition_reveal_corrected.png. Land on this exact yoga-room composition and final observer pose.

CAMERA AND GEOGRAPHY
One continuous lateral dolly to camera-right along the open front of a physical dollhouse. The trader room is left of the yoga room. As the camera travels right, the fixed rooms slide left across the image and their dividing wall passes through the foreground. Keep camera height, viewing direction and focal length constant. Preserve the original width and height of each room: furniture and architecture retain their dimensions and leave the image through natural cropping. Maintain a common floor level and consistent miniature scale. The observer remains a single giant man outside the windows throughout.

0.0-2.2 SECONDS
The miniature trader, wearing glasses, a black hoodie, dark trousers and white trainers, eats instant noodles from a cup with a fork while watching his three monitors. The camera glides slowly right from the opening reveal toward a clearer view of the workstation. Outside, the giant blond man leans into the window from its left edge until his face is clearly visible. He tilts his head and looks directly down at the trader, matching the intermediate appearance reference. His expression is curious and mildly intrusive.

2.2-3.4 SECONDS
The trader notices him, pauses with the fork raised, turns his head and upper body toward the window and snaps angrily in English: “Leave me alone!” His mouth movement matches the words. The observer listens.

3.4-4.2 SECONDS
Immediately after finishing the line, the trader throws the noodle cup from his hand toward the observer’s face. The cup travels away from the trader and strikes the INSIDE surface of the window glass. Broth and noodles splatter on the interior glass directly in front of the giant’s face. The glass stays intact and separates the observer from the cup and splatter.

4.2-4.8 SECONDS
The observer flinches, blinks and replies apologetically in English: “Sorry!” His mouth movement matches the word. He then withdraws from the trader’s window and moves physically right outside the building toward the neighboring yoga-room window.

4.8-7.6 SECONDS
The camera continues its rightward dolly, smoothly traversing the foreground dividing wall and revealing the brighter yoga room. The trader room and its splattered window slide out to the left. The woman wears a mauve sports bra and leggings, with dark hair in a bun. She remains seated low on her mat in the reference pose, calmly following the tablet on the floor. Her gaze stays on the tablet. Preserve the cream chair, pink throw, plants, bottle, rug and visible furniture from the ending reference. The house poster and EasyAI artwork remain in the narrow neighboring-room strip left of the partition.

7.6-8.0 SECONDS
The camera gently settles into the ending reference. Match its floor height, window dimensions and placement, woman’s position and pose, furniture scale, partition thickness and framing. The giant has reached the exact final head position, orientation and window-relative scale shown there, wearing the same light-blue T-shirt. He holds that pose while the woman continues focusing on her tablet.

LOOK AND SOUND
Keep the trader room’s warm pendant lighting and the yoga room’s soft natural daylight, with stable exposure and reference-matched colors. Natural facial animation, grounded body motion and believable miniature materials. Maintain continuous spatial movement throughout, with transitions produced by the camera passing the physical wall. Sound consists of quiet computer hum, fork and noodle sounds, the trader’s shout, a cup impact and wet glass splatter, the observer’s brief apology, then calm yoga-room ambience. Only the two specified spoken lines. Ambience and effects form the soundtrack; the image remains free of captions and graphic overlays.

Google Flow · дубль 2 · 8 с, три референсных изображения

Промпт, использованный для дубля 2

Create an 8-second photorealistic vertical 9:16 video with synchronized English dialogue.

REFERENCES
First frame: @generated/images/mf1_partition_reveal_corrected.png - opening trader-room composition.
Intermediate appearance reference: @generated/images/mf1_looking_at_guy.png - giant observer’s identity, scale and downward gaze toward the trader.
Last frame: @generated/images/lf1_partition_reveal_corrected.png - final yoga-room composition and observer pose.

CHARACTER AND SPEAKER ASSIGNMENTS
TRADER: the miniature young man INSIDE the bedroom, wearing glasses, a black hoodie, dark trousers and white trainers. He alone says: “Leave me alone!” He throws the noodle cup.
OBSERVER: the giant blond man OUTSIDE the rear window, wearing a light-blue T-shirt. He quietly watches the trader and trading monitors. His sole spoken line is: “Sorry!”

GEOGRAPHY
The camera views the miniature room through its open front. The trader is inside, between the camera and the rear window. The giant stands outside, behind that window. The window glass physically separates them. The cup travels from the trader toward the BACK of the room, away from the camera, and strikes the interior surface of the rear window directly in front of the giant’s face.

0.0-2.5 SECONDS - SILENT OBSERVATION
Begin on the first reference. The trader eats noodles while watching his three monitors. The giant gradually leans into view from the window’s left edge, matching the intermediate reference. His eyes move naturally between the trader and the screens below. His lips remain together, his expression quietly curious, his hands below the window sill.

2.5-3.3 SECONDS - THE TRADER SPEAKS
The trader notices the giant, puts his fork on the desk, and turns his head and shoulders toward the rear window. His mouth is visibly readable in profile as he angrily shouts in English: “Leave me alone!” Use a young male voice originating inside the room. During this entire line, the giant keeps his lips together and listens with a surprised expression.

3.3-4.1 SECONDS - THE TRADER THROWS
The trader transfers the SAME cup he was eating from into his right hand, draws that arm back, then swings toward the rear window and releases it. Show the release and continuous flight clearly. His throwing hand is visibly empty afterward. The separate cup already resting on the desk stays there.

The thrown cup remains miniature, matching the trader’s hand. It recedes through the room toward the rear glass, becoming slightly smaller with distance. It strikes the pane in front of the observer’s face. Broth and noodles splash onto that rear pane and cling to it; the cup falls inside beneath the window. The glass remains intact. The foreground viewing opening and camera view remain clean. The giant stays outside throughout.

4.1-4.6 SECONDS - THE OBSERVER REPLIES
After the impact, the giant gives one startled blink. Only now his lips move as he softly says in English: “Sorry!” Use a distinct mature male voice originating outside the window. The trader’s mouth stays closed during this reply.

4.6-8.0 SECONDS - NEXT ROOM
The giant withdraws and moves right outside the building. The camera continues its smooth lateral dolly right along the dollhouse front. The fixed trader room slides left; the physical dividing wall passes through the foreground, revealing the yoga room. Maintain camera height, focal length, room dimensions, window geometry, shared floor level and furniture scale.

Gently settle into the last reference by 7.6 seconds and preserve that composition through 8.0 seconds. The woman in mauve yoga clothes remains focused on her tablet in the reference pose. The giant reaches the reference’s exact window-relative position and head orientation.

STYLE AND AUDIO
One continuous shot. Preserve each reference room’s lighting, materials and architectural proportions. Natural restrained acting. Sound: computer hum, eating sounds, the trader’s “Leave me alone!”, cup release, rear-window impact, wet splatter, the observer’s “Sorry!”, then quiet yoga-room ambience. The two lines occur separately, with the visible speaker’s lips synchronized to each line. Ambience and effects provide the soundtrack.

Seedance 2.5 · 480p черновик · omni-reference, начальный кадр + референс изображения + конечный кадр

Промпт, использованный для этого черновика

8-second contemporary digital comedy scene inside a physical miniature dollhouse. One continuous take: a giant’s quiet curiosity provokes a miniature trader, then the camera reveals the calm neighboring yoga room.

MODEL: Seedance 2.5, omni-reference.
FORMAT: 9:16, 8.0 seconds, photoreal digital cinema.

REFERENCES
@Image1 - generated/images/mf1_partition_reveal_corrected.png, supplied as START FRAME. Preserve its opening composition, architectural proportions, floor height, window geometry, furniture and lighting. Use it for the opening only; the camera subsequently travels right.
@Image2 - generated/images/mf1_looking_at_guy.png, supplied as IMAGE REFERENCE. Take the giant observer’s exact identity, blond hair, blue eyes, light-blue T-shirt, face scale and downward gaze. Use this appearance during the trader encounter; do not insert this still as a separate shot.
@Image3 - generated/images/lf1_partition_reveal_corrected.png, supplied as END FRAME. Match its final composition, yoga-room geometry, woman’s pose, furniture and observer orientation. Its interior belongs only to the neighboring yoga room.

SUBJECTS AND SPEAKERS
TRADER: miniature young man inside the room, glasses, black hoodie, dark trousers, white trainers. He alone says “Leave me alone!” and throws the noodle cup he is holding.
OBSERVER: giant blond man outside the rear window, matching @Image2, wearing a light-blue T-shirt. His only line is “Sorry!”
WOMAN: miniature woman in the yoga room, dark hair in a bun, mauve sports bra and leggings. She remains silent and focused on her tablet.

STYLE: reference-matched lens perspective, deep enough focus to read the trader and observer together, restrained facial acting, natural skin texture and cloth movement. Must feel like a photographed miniature set with a real person outside, not generated footage.
COLOR: warm brown and charcoal in the trader room; cream, muted mauve and oak in the yoga room; blue daylight outside. Stable reference-matched exposure.
ENVIRONMENT: trader room left, yoga room right, connected by a common floor level and separated by a thick structural wall. Warm overhead pendant illuminates the trader; daylight enters through the rear windows. Architecture and furniture remain fixed.

CAMERA: physical lateral dolly to camera-right along the open dollhouse front. Constant height, viewing direction and focal length. Rooms move left across the image through parallax and natural cropping. Motion preset: none. The following numbered beats are phases within the same shot, not cuts.

Shot 1 [0.0s-2.2s] - wide room view from the opening reference: the trader continues eating and watching his three monitors. The observer leans into view until his appearance matches @Image2, quietly looking between the trader and monitors. His lips stay closed and his hands remain below the sill.
Camera: slow rightward dolly.
SFX: faint computer hum and fork contact.

Shot 2 [2.2s-3.3s] - same wide view and angle: the trader puts down his fork and turns toward the rear window while retaining his cup. The miniature trader angrily says, “Leave me alone!” His lips alone articulate these words; the observer listens with his lips closed.
Camera: continue the slow rightward dolly, keeping both faces visible.
SFX: the trader’s young male voice originates inside the room. Realistic lip articulation, no exaggerated mouth opening, no head turns while speaking.

Shot 3 [3.3s-4.1s] - same room view: the trader draws back his cup-holding arm, swings toward the rear window and releases that same miniature cup. Show hand, release and flight as one connected action. His hand is empty afterward. The cup travels away from the camera into the back of the room, becoming smaller with distance, and strikes the interior glass directly in front of the observer’s face. Broth and noodles stick to the rear pane; the cup drops inside below it. The separate cup on the desk stays in place. Glass remains intact; the observer stays outside behind it.
Camera: continue rightward, retaining the throwing hand and rear pane in view.
SFX: cup impact and wet splatter.

Shot 4 [4.1s-4.6s] - same room view: the observer blinks at the impact, then softly says, “Sorry!” Only the giant observer’s lips articulate this word. The trader’s mouth stays closed.
Camera: continue the rightward dolly.
SFX: distinct mature male voice from outside, brief apologetic delivery with realistic lip articulation.

Shot 5 [4.6s-7.5s] - wide view along the same dollhouse front: the observer withdraws from the trader window and moves right outside the building. The camera passes the physical dividing wall, revealing the yoga room. The woman stays seated in her reference pose, eyes on the tablet. The observer arrives at the yoga window and settles into @Image3’s exact head position and orientation.
Camera: continuous rightward translation, gently decelerating into the end-frame composition.
SFX: computer hum fades with distance into quiet room ambience.

Shot 6 [7.5s-8.0s] - held wide composition matching @Image3: preserve floor height, window size and placement, partition thickness, woman’s position, furniture and observer scale. Everyone holds the established ending.
Camera: settled and locked.
SFX: silence holds the final 0.5 seconds.

AUDIO: the two assigned English lines are clear and prominent; synchronized effects are secondary, room ambience subtle.
- No music, no library audio, no voiceover narration, no on-screen text, no subtitles, no added logo.

CONSTRAINTS: one unbroken continuous take. No cuts, dissolves or black frames. No zoom or focal-length change. The trader alone delivers the angry line and throws his own cup. The observer watches silently until his apologetic reply. Preserve each person’s identity and wardrobe. Preserve miniature-to-giant scale, room dimensions and window geometry. The woman’s attention remains on the tablet. Existing wall artwork stays part of the set.
Stable face throughout. No morphing. No deformation. Photoreal cinematic finish.

Wan 3.0 · план А · от начального до среднего кадра, 3 с

Промпт, использованный для кадра A

3-second contemporary digital comedy shot inside a physical miniature dollhouse. One continuous take: a miniature trader eats noodles at his desk while a giant, unnoticed, slowly rises into view behind his rear window.

FORMAT: 9:16, 3.0 seconds, photoreal digital cinema with native sound.

START AND END: open exactly on the supplied start frame (trader room; trader holding his noodle cup near his mouth; only a sliver of the giant observer's face visible at the far left edge of the rear window) and end exactly on the supplied end frame (same room; the observer's whole face filling the rear window, looking down at the trader). Keep both frames' composition, proportions, floor height, window geometry, furniture, desk items and lighting.

TRADER: miniature young man at the desk, glasses, black hoodie, dark trousers, white trainers. He eats continuously for the whole shot: cup held near his mouth in one hand, lifting forkfuls of noodles, chewing, eyes on his three monitors. He never notices the observer, never turns, never speaks. Black over-ear headphones lie untouched on the desk beside the keyboard.
OBSERVER: giant blond man, blue eyes, light-blue T-shirt, outside the rear window; exactly the man in the end frame. He moves from almost out of view at the left edge across and into the window, curious, settling into the end frame's head position, angle and downward gaze. Lips closed, silent, hands below the sill.

STYLE: frame-matched lens perspective, deep focus holding trader and observer together, restrained acting, natural skin and cloth. A photographed miniature set with a real person outside, not generated footage.
COLOR: warm brown and charcoal room under a warm pendant; blue daylight outside the window.
ENVIRONMENT: the trader room only: desk with three monitors, keyboard, headphones, bed, rug, wall artwork. Architecture and furniture stay fixed.

CAMERA: very slight physical dolly to camera-right along the open dollhouse front, matching the small shift between the start and end frames; constant height, direction and focal length. No zoom.

[0.0s-2.5s] The trader keeps eating - forkfuls lifted and chewed, eyes on the monitors. The observer glides in from the left edge of the rear window, his face rising and sliding across until it fills the window, quietly watching the trader eat. SFX: faint computer hum, fork against the cup, soft slurping, chewing.

[2.5s-3.0s] Held composition matching the end frame: the observer's face filling the rear window, eyes on the trader; the trader still eating, unaware. Camera settled.

AUDIO: eating sounds and computer hum only; subtle room ambience. No dialogue, no music, no narration, no on-screen text, no subtitles, no logo.

CONSTRAINTS: one unbroken take; no cuts, dissolves, black frames or zoom. Nobody speaks. The trader keeps eating and never looks at the window. The headphones stay on the desk. Preserve identities, wardrobe, miniature-to-giant scale, room dimensions, window geometry and desk items. Stable faces throughout, no morphing, no deformation, photoreal cinematic finish.

Wan 3.0 · кадр B · от среднего кадра до конечного, 6 с

Промпт, использованный для кадра B

contemporary digital comedy shot inside a physical miniature dollhouse. One continuous take: a miniature trader, interrupted while eating, snaps at the giant watching him through his window and throws his headphones at him; the giant apologizes and moves on, and the camera reveals the calm neighboring yoga room.
FORMAT: photoreal digital cinema with native sound.
START AND END: open exactly on the supplied start frame @[Image 1](image_1) (trader room; trader eating; the giant observer's whole face filling the rear window, looking down at him) and end exactly on the supplied end frame @[Image 2](image_2) (yoga room; observer full-face at its window). Keep both frames' composition, proportions, floor height, window geometry, furniture and lighting.
TRADER: miniature young man at the desk, glasses, black hoodie, dark trousers, white trainers, noodle cup in hand. Black over-ear headphones lie on the desk beside the keyboard, at his left. He alone says "Leave me alone!" and throws those headphones.
OBSERVER: giant blond man, blue eyes, light-blue T-shirt, outside the rear windows; exactly the man in both frames. His only line is "Sorry!"
WOMAN: miniature woman in the yoga room, dark hair in a bun, mauve sports bra and leggings; silent, focused on her tablet.
STYLE: frame-matched lens perspective, deep focus holding trader and observer together, restrained acting, natural skin and cloth. A photographed miniature set with a real person outside, not generated footage.
COLOR: warm brown and charcoal trader room; cream, muted mauve and oak yoga room; blue daylight outside.
ENVIRONMENT: trader room left, yoga room right, one floor level, a thick structural wall between them. Warm pendant over the trader; daylight through the rear windows. Architecture and furniture stay fixed.
CAMERA: physical lateral dolly to camera-right along the open dollhouse front; constant height, direction and focal length; rooms slide left through parallax. The beats below are phases of one shot, not cuts.
[0.0s-1.4s] The trader stops eating, sets the cup down on the desk, turns to the rear window and angrily says "Leave me alone!" Only his lips move; the observer listens, lips closed. Slow rightward dolly, both faces visible. Young male voice from inside the room, realistic lip sync.
[1.4s-2.3s] The trader snatches the black headphones from beside the keyboard and throws them hard at the rear window, straight at the observer's face - grab, swing, release and flight as one connected action; his hand is empty afterward. The headphones fly away from camera, shrinking with distance, hit the inside of the glass in front of the observer's face and drop to the floor below the window. The cup stays on the desk; the glass stays intact; the observer stays outside. SFX: hard plastic thud on glass, headphones clattering on the floor.
[2.3s-2.9s] The observer blinks at the impact and softly says "Sorry!" Only his lips move; the trader's mouth stays closed. Mature male voice from outside, realistic lip sync.
[2.9s-5.5s] The observer withdraws and moves right outside the building. The camera passes the dividing wall, revealing the yoga room; the woman stays seated, eyes on the tablet. The observer arrives at the yoga window and settles into the end frame's exact head position. Continuous rightward translation, decelerating into the end-frame composition. SFX: computer hum fades into quiet room ambience.
[5.5s-6.0s] Held composition matching the end frame - floor height, window placement, wall thickness, the woman's position, observer scale. Camera settled. Silence holds the final 0.5 seconds.
AUDIO: the two English lines clear and prominent; effects secondary; subtle ambience. No music, no narration, no on-screen text, no subtitles, no logo.
CONSTRAINTS: one unbroken take; no cuts, dissolves, black frames or zoom. The trader alone speaks the angry line and throws the headphones; the noodle cup is never thrown. The observer is silent until "Sorry!". Preserve identities, wardrobe, miniature-to-giant scale, room dimensions and window geometry. Existing wall artwork stays. Stable faces throughout, no morphing, no deformation, photoreal cinematic finish.

MiniMax H3 · кадр B · те же кадры, seed 42

Промпт отправлен в оба прогона H3

How the reference pictures align with the target video - Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 6.58-second mark of the target video.

integrated_multimodal_description: [Shot 1] Photoreal digital cinema, cinematic, a single continuous lateral dolly shot from left to right along the front of a miniature dollhouse, maintaining constant height, direction, and focal length. The scene opens exactly on <Picture 1>: a miniature trader in a warm brown and charcoal room, seated at a desk with three monitors displaying financial charts, a noodle cup in hand, black over-ear headphones resting on the desk to his left. He wears glasses, a black hoodie, dark trousers, and white trainers. Outside the rear window, a giant blond man in a light-blue T-shirt fills the frame, his face visible from forehead to chin, looking down at the trader. The room is lit by a warm pendant light above the desk; daylight streams through the rear windows. The camera begins a slow rightward dolly. At 00:01.400, the trader stops eating, sets the cup down, turns toward the rear window, and with a tight expression, says: <d>[English] Leave me alone!</d> His lips move in realistic sync; the observer’s lips remain closed. From 00:01.400 to 00:02.300, the trader snatches the headphones from the desk, swings his arm forward, and throws them hard at the rear window - a single connected motion. The headphones fly away from the camera, shrinking with distance, strike the inside of the glass directly in front of the observer’s face, and clatter to the floor below the window. The cup remains on the desk; the glass remains intact; the observer remains outside. SFX: hard plastic thud on glass, headphones clattering on floor. From 00:02.300 to 00:02.900, the observer blinks at the impact and softly says: <d>[English] Sorry!</d> His lips move in realistic sync; the trader’s mouth remains closed. From 00:02.900 to 00:05.500, the observer withdraws and moves right outside the building, the camera continuing its rightward dolly, passing the thick structural wall between rooms. The yoga room is revealed: cream walls, muted mauve accents, oak flooring, a woman in a mauve sports bra and leggings seated on a mat, focused on a tablet. The observer arrives at the yoga window and settles into the exact head position shown in <Picture 2>. The camera decelerates into the end-frame composition. From 00:05.500 to 00:06.000, the composition holds exactly as in <Picture 2>: floor height, window placement, wall thickness, the woman’s position, observer scale. The camera is settled. The final 0.5 seconds are silent.

overall_soundscape: The trader’s noodle cup clinks softly as he sets it down. A hard plastic thud and clatter as headphones strike the window and fall. The observer’s voice is clear and soft. Computer hum fades into quiet room ambience as the camera moves into the yoga room. The woman’s breath is shallow and steady; no other sounds.

non_diegetic_music: N/A

Создайте такой кадр самостоятельно

AI Video Starter - это трехчасовой живой воркшоп: идея, план кадра, референсные изображения, генерация, исправление неудачных дублей и монтаж вашего собственного короткого видео.

Смотреть мастер-классы ↗