Cinematic realism prompts

Create a 20-second ultra-realistic luxury beauty commercial in vertical 9:16 format, featuring a glossy pink and coral aesthetic throughout. Start with a close-up of a Next Level lip cream standing on a reflective pink surface with a soft splash effect around the base, then smoothly transition into an extreme close-up of naturally textured glossy lips. Show the lips gently opening and moving naturally before introducing the lip cream applicator entering the frame and carefully applying the coral-pink product across the lips. Use detailed macro cinematography to capture realistic lip texture, creamy product shine, soft skin pores, and subtle highlights. Transition into a stylish full-body shot of a confident young East Asian woman wearing an elegant dusty-pink tailored pantsuit, walking slowly toward the camera in a modern pink studio. Keep her appearance natural, polished, and realistic with soft makeup and a subtle smile. Finish with a premium product hero shot showing multiple lip cream shades arranged on a glossy reflective surface, with dramatic coral-pink liquid splashes in the background. Use smooth camera movements, shallow depth of field, soft studio lighting, realistic reflections, cinematic focus pulls, high-end cosmetic advertisement quality, and seamless transitions.

Hermione attacks from the front while Ron flanks; Malfoy scrambles to counter, allowing Ron to snatch the white flag from his back, turning it into a frantic chase with no clear winner yet.

fly into the scene as if it was 3D. orbit around each character to show their over the shoulder view. end at the start position so the video is a loop

Create a 15-second ultra-realistic, high-budget medieval fantasy film featuring a beautiful, fierce female archer with long, loose brown hair, wearing historically inspired dark brown leather armor, fur-trimmed shoulders, a rugged medieval outfit, a leather belt, and a quiver full of arrows strapped across her back. She rides a muscular black horse through a dense ancient pine forest filled with thick atmospheric fog, moss-covered ground, scattered rocks, and towering trees. Begin immediately with a wide cinematic rear shot of the warrior riding her horse along a narrow forest trail as warm golden sunlight pierces through the trees, creating dramatic volumetric light rays and a mysterious atmosphere. The camera follows smoothly behind the horse as its hooves move naturally over the uneven ground, disturbing small leaves, dirt, and moss. Transition into a dramatic low-angle side close-up of the female warrior holding a traditional curved black bow, drawing the bowstring backward with a single arrow, and aiming with intense concentration. Her arm muscles tense naturally, the bow bends under realistic tension, and her hair and fur-trimmed clothing respond to the cool forest breeze. Capture her determined facial expression, realistic skin texture, detailed leather armor, and the individual arrows in her quiver. In the final seconds, transition to a wide rear tracking shot as she rides into a hidden medieval encampment surrounded by towering evergreen trees, rustic tents, wooden structures, and groups of warriors wearing authentic medieval clothing and armor. The warriors turn toward her arrival, creating the atmosphere of a legendary chieftain returning to her people. Maintain consistent character identity, outfit, horse appearance, and realistic body proportions throughout every shot. Use cinematic camera transitions, natural horse locomotion, accurate equestrian anatomy, realistic gravity, inertia, muscle movement, cloth simulation, and physically believable lighting. Premium Hollywood medieval fantasy cinematography, photorealistic textures, atmospheric fog, muted earthy colors, dramatic natural lighting, subtle film grain, shallow depth of field, 4K quality, 24 FPS, immersive environmental sound effects of horse hooves, leather movement, wind through pine trees, and distant camp ambience. No modern objects, no cartoon effects, no subtitles, no text, no logos, and no watermark.

【任务】

生成12秒、9:16竖屏真实手机自拍视频。复刻参考视频《气得肚子疼》的躺床构图、动作顺序、哭笑混杂的表情和节奏，将原人物替换为指定成年女性。

【参考分工与人物锁定】

人物参考图锁定女性面孔 @0ba07db1-974c-467d-80dc-d9dffddac0ba 、五官比例和黑色长发，不继承原视频男性的外貌。

服装和身材比例参考图锁定 @8149c66e-9a91-4b88-bf26-d0a764075ccf ，服装完整穿着。

眼镜参考图锁定银色装饰眼镜 @d80c71c5-d330-4baf-8ecf-8b793ee0fee8 ：细银色金属线、开放式弧形下眼框、透明鼻托、鼻梁附近的小蝴蝶结金属线圈、两侧各一枚垂挂花朵。镜腿正常架在耳朵上，双眼清晰可见。眼镜全程佩戴，不变成普通粗框眼镜，不出现展示架。

原视频仅锁定表演、自拍角度、动作与节奏。

不要继承此前九宫格中的坠落镜头。

【场景与拍摄】

她仰躺在白色床铺上，头枕白色枕头，长发自然散开。

左手在画外举着手机，前置镜头位于脸部上方约40厘米，向下拍摄脸、肩膀与上半身。脸部占据画面主体。

右手可伸到画面下沿按住腹部。

全程一镜到底，镜头仅随持机手、呼吸和肩膀颤动产生轻微晃动。自然卧室光，普通手机原生画质，真实皮肤纹理，无美颜。

【严格时间与表演】

0—2.8秒：

开场便是气急后的哭笑状态。她眉心紧皱，眼睛挤闭，嘴角横向拉开，断续发出“哈哈哈哈……啊……哈哈”。

笑声带委屈和气恼，肩膀轻颤，头在枕头上小幅偏动。

银色花朵垂饰随头部动作轻轻摆动，鼻托和镜腿始终贴合面部。

2.8—5.8秒：

她停下来吸气，勉强睁眼看手机屏幕，眉头仍皱着，嘴角下撇，带着气恼和委屈说：

“家人们，气得我肚子疼。”

说到后半句时，右手按住腹部，头偏向一侧，眼睛再次挤闭。手机随身体颤动轻微晃动，脸部仍清晰可读。

5.8—9.3秒：

她试着缓一口气，却再次发出破碎的“哈哈哈……啊……”

嘴张开、短暂抿住、又张开，呈现想笑又想哭的反应。眉心挤紧，鼻翼轻动，下巴轻颤，偶尔露齿。

头从侧偏位置回到枕头中央，右手继续按腹部。眼镜随头移动，花朵垂饰自然摆动。

9.3—12秒：

她短暂睁眼看向屏幕，气恼地说：

“气死我了。”

说完闭眼皱鼻，再露出哭笑混杂的表情，以一声短促苦笑和呼气结束。

始终躺在原位，不起身，不增加其他剧情。

【音频】

自然成年女性声线，手机近距离收音，嘴型与台词同步。

笑声断续、有吸气和气音，情绪是气恼、委屈与苦笑交织。

轻微枕头摩擦、衣料摩擦与室内底噪，无旁白、无背景音乐。

若生成工具支持参考视频音频，优先匹配原片的停顿、笑声与说话节奏。

【关键要求】

保留原片夸张的挤眼、皱眉、张嘴和头部摆动，不能变成漂亮微笑或平静口播。

表情挤压五官时仍保持同一人物身份。

眼镜结构、花朵数量、服装、发型、床铺与光线全程一致。

不换脸，不让眼镜悬浮或穿过皮肤，不增加花朵挂件，不出现额外手臂或异常手指。

不切镜，不坠落，不翻滚机位，不慢动作，不电影运镜。

生成画面不添加字幕、截图贴纸、水印或平台界面。

将 <<<图片 @1cbc28c8-e2a8-40e8-bfd6-7b3a7db70034 >>> 的每一帧组合起来，制作一段视频。这是一段手机后置镜头主观视角意外脱手坠落 × 同次坠落连续九连拍 × iPhone失败多连拍 × 夸张广角透视 × 随机旋转机位、失焦、运动模糊与画面角度。

THE CORONATION — 20-SECOND CINEMATIC COMEDY

MODEL: Seedance 2.5
DURATION: 20 seconds
ASPECT RATIO: 16:9
STYLE: Photorealistic live-action medieval fantasy film with subtle absurdist comedy.
REFERENCE IMAGES AND CHARACTER LOCK
Use the uploaded King character sheet, Prince character sheet, and Random Man character sheet as the definitive visual references.
King: Preserve his exact face, gray-streaked hair, beard, crown, and burgundy royal outfit.

Prince: Preserve his exact face, hairstyle, navy-and-gold coronation outfit, blue cloak, and crown once placed.

Random Man: Preserve his exact face, hairstyle, modern casual outfit, and body proportions.

Maintain consistent character identities, costumes, lighting, and the layout of the throne room throughout the entire video.
LOCATION AND ATMOSPHERE
An enormous medieval royal throne room with towering stone pillars, golden chandeliers, tall stained-glass windows, red velvet banners, and a magnificent golden throne. The royal court stands silently on either side of a red carpet.

The atmosphere is extremely serious and emotionally grand, like the climax of an epic fantasy film. Warm golden sunlight streams through the windows. The music is majestic, with a full orchestral score.

The modern man must look completely out of place in this medieval setting.

SHOT 1 — THE MOMENT OF CORONATION

0–5 seconds

Wide cinematic establishing shot of the royal throne room. The prince kneels on a cushion before the king. The king stands solemnly in front of him, holding an ornate golden crown with both hands.

The court watches in absolute silence.
Cut to a medium close-up of the king slowly raising the crown above the prince's head.

The king speaks in a deep, solemn voice:

KING: "Today, you become king."

The orchestral music swells dramatically. The prince bows his head with complete seriousness.

SHOT 2 — THE WRONG MAN ENTERS

5–9 seconds

Just as the king is about to lower the crown, a casually dressed modern man in a dark hoodie, jeans, and sneakers walks into the royal ceremony from the side of the hall.

He walks directly between the king and prince as though he belongs there.
The king freezes with the crown suspended in midair. The prince remains kneeling, looking slightly confused. The courtiers stare in silent disbelief.

The modern man barely acknowledges anyone. He notices the crown, looks at it critically, and gives a small disapproving shake of his head.

The orchestral music abruptly softens into an awkward, sustained note.

SHOT 3 — THE UNEXPECTED FIX

9–14 seconds

In one continuous, clearly visible action, the modern man casually takes the crown from the king's hands.

He notices a small paper price tag hanging from the crown, removes it, and slips it into his pocket. He then gently straightens the prince's crooked collar and nudges the royal throne a few inches into better alignment with the carpet.
His movements are practical, quick, and completely unbothered.

The king stands frozen, visibly bewildered but trying to preserve his royal dignity. The prince looks from the man to his father, unsure whether he is allowed to move.

The man steps back, examines his work, and gives one satisfied nod.

RANDOM MAN: "Much better."

Deliver the line casually, in a natural conversational voice, without a dramatic pause or exaggerated comic delivery.

SHOT 4 — BACK TO BUSINESS

14–17 seconds

The modern man turns around and casually walks out of the throne room the same way he entered.

No one stops him. Nobody speaks.
The king slowly follows him with his eyes, then looks down at the crown in his hands as if trying to understand what just happened.

The prince remains kneeling in the exact same position.

The man exits the frame completely.

SHOT 5 — THE CORONATION CONTINUES

17–20 seconds

Cut to a cinematic medium close-up of the king taking a slow breath, regaining his composure, and carefully positioning himself to continue the ceremony.

He raises the crown again.
The prince bows his head.

The orchestral music resumes its original majestic intensity, as if the interruption never happened.

KING: "Today… you become king."

End immediately on the king's perfectly serious face.

Cut to black.

CAMERA AND EDITING

Use professional cinematic framing, smooth controlled camera movements, realistic depth of field, natural facial micro-expressions, and clean film-style cuts. Establish the room before moving into medium shots and close-ups. Make the modern man's entrance and practical actions easy to see.

Keep the comedy understated and driven by timing, awkward silence, and the contrast between the epic ceremony and the man's mundane behavior.

AUDIO DESIGN

Majestic orchestral music during the coronation, subtle footsteps and clothing movement, a slight musical interruption when the man enters, a soft paper rustle as he removes the price tag, and a return to full orchestral grandeur for the final line.

All dialogue must be clearly audible, naturally spoken in English, and not overly theatrical.

STRICT NEGATIVE CONSTRAINTS

Do NOT generate any subtitles, captions, text overlays, watermarks, logos, or on-screen text of any kind.
Do NOT display the spoken lines as written text on screen.
Dialogue must exist only as spoken audio, never as visible typography.

Vertical 9:16 cinematic video, 10 seconds, starring Sydney Sweeney as the main character, with her recognizable facial features, wavy blonde hair, and expressive smile. Ultra-fast pacing, whip-pan transitions, and beat-synced cuts approximately every second.

0–2 seconds: Sydney Sweeney, wearing a sleek black freediving wetsuit with a small action camera attached to her chest strap, swims rapidly through crystal-clear turquoise water above white sand. Sunbeams ripple across her face as the camera tracks her with dynamic underwater movement.

2–4 seconds: She speeds past vibrant coral reefs toward a shimmering curtain of iridescent beads. A dramatic speed ramp follows as she bursts through the sparkling curtain. The camera whip-pans into a mysterious dark coral cave, where violet light illuminates the surrounding water.

4–6 seconds: Explosive reveal of a futuristic underwater nightclub filled with neon lasers, colorful strobes, floating luminous star-shaped sunglasses, and tropical fish moving rhythmically to the music. Sydney emerges through a glowing violet portal as cyan, magenta, and purple lights illuminate her face.

6–10 seconds: Sydney puts on oversized neon star-shaped sunglasses, spins playfully in zero gravity underwater, and laughs as glowing bubbles and particles swirl around her. The camera circles her rapidly with energetic zooms, sharp whip-pans, and smooth speed-ramp transitions, ending on a dramatic close-up of her smiling face against the vibrant nightclub.

Visual style: Hyper-realistic cinematic footage, lifelike facial details, consistent character appearance, realistic underwater physics, volumetric lighting, vivid turquoise water, neon magenta and cyan highlights, violet glow, floating particles, smooth motion blur, high contrast, premium music-video aesthetics, 24 fps.

Audio: Energetic electronic dance music, deep underwater whooshes, sparkling sound effects, and a bass drop during the nightclub reveal.

Continuity: Keep Sydney Sweeney recognizable and visually consistent throughout all shots. No face distortion, duplicate characters, flickering facial features, unwanted text, logos, or watermarks.

【整体设定】

10秒，9:16竖屏，真实手机餐馆随手拍，一镜到底。

上传的重绘图片作为尾帧参考，锁定鞋底状豆腐干的形状、夹持位置、餐桌布局、服务员外貌与最终构图。

【场景与拍摄关系】

普通中式小餐馆，暖色吊灯、米色餐桌，背景有自然吃饭聊天的顾客。

前景是装着红油、豆腐干、面条与蔬菜的白色大碗，旁边有汤碗、茶壶和纸巾盒。

坐着的成年男子用左手持手机拍摄，用右手持两根木筷夹菜。只有夹菜的手进入画面，男子的脸与身体始终在画外。

服务员穿黑色上衣和酒红色围裙，位于桌对面的画面右侧。

手机轻微手持晃动，自然室内曝光，普通手机压缩质感，无美颜、无电影调色。

【关键道具】

只有一片鞋底状豆腐干：棕黄色、薄片、表面挂着红油和葱花，有清晰方格压纹，轮廓与尾帧一致。

它是柔韧的食物，不是真鞋底，不出现鞋面、橡胶或鞋子。

筷子夹住豆腐干上端，两根筷子的接触点准确，夹起后下端自然垂落。

【严格时间分镜】

0—2秒：

镜头略向下对着菜碗。男子的右手从左侧伸入画面，用两根木筷夹住碗内那片豆腐干的上端。

豆腐干此时部分浸在红油里，尚未完整露出轮廓。

2—4.5秒：

男子缓慢向上提起筷子。

整片豆腐干从碗里连续抽出，先露出上端，再露出方格纹路、收窄的中段和圆弧下端，逐渐呈现鞋底般的完整形状。

豆腐干轻轻摆动，两三滴酱汁落回碗中。

镜头随持机手小幅向上抬，使整片豆腐干始终留在画面内。

4.5—6秒：

男子停住筷子，像在仔细看这片食物，低声疑惑地说：

“这豆腐干……”

服务员听见声音，从桌对面稍微靠近，目光先看向筷子，再移到豆腐干。

6—9秒：

男子保持夹持，轻轻将豆腐干朝服务员方向展示，问：

“服务员，怎么长得跟鞋底似的？”

语气自然、困惑，带一点难以置信，不大声斥责。

服务员低头看它，眉头逐渐皱起，嘴唇轻抿，停顿一下，没有立即回答。

豆腐干仍悬在菜碗上方，不触碰服务员。

9—10秒：

镜头停留在完整豆腐干与服务员疑惑的反应上。

筷子、豆腐干、餐具和服务员位置对齐尾帧参考，最后保持至少一秒，留下安静的喜剧停顿。

【声音】

成年男子自然说话声，来自镜头附近。

保留筷子轻碰碗沿、酱汁滴落、邻桌低声聊天与餐具碰撞声。

无旁白、无背景音乐、无夸张喜剧音效。

【连续性与约束】

必须先夹住再提起，豆腐干沿连续轨迹从碗中出现，不瞬移、不复制。

夹起前后保持同一形状、尺寸、方格纹路和颜色。

筷子保持两根，不穿透食物，不变形；手指正常。

服务员只自然靠近并观察，不抢走食物，不提前夸张惊叫。

不切镜、不突然变焦、不慢动作、不添加鞋子或其他解释道具。

生成时不添加文字、水印和平台界面。

[参考锁定]

使用新生成的首帧@1作为外形与环境参考。

男性为38岁左右成年人，寸头、短胡茬，赤裸上身，深灰色橙边运动短裤、灰黑运动鞋。

肩背已有异常肌肉肿块，开场就存在，不在视频里重新长出来。

左肩胛至肋部是一块纵向、不对称的巨大隆起；右肩有较小的叠层肌肉鼓包。

左侧肿块表面两道暗紫色裂隙状创口，边缘皱缩、不规则。

肿块有真实重量，随肌肉收缩轻微挤压，不能像气球一样充气。

无喷血、组织爆裂或额外肢体。

[风格与镜头]

9:16竖屏，12秒连续手机录像。

摄影者站在男子左后方约两米，胸口高度拍摄。

开场以三分之二背面角度呈现，肩背肿块、手臂和曲杆杠铃同时可见。

轻微手抖、小幅构图调整，不环绕、不切镜、不慢动作。

普通旧健身房记录：平淡荧光灯、轻微噪点、压缩痕迹、汗水反光和自然运动模糊。

没有恐怖电影灯光，没有背景音乐。

[环境与道具]

旧社区地下健身房，白色立柱、浅绿墙裙、磨损灰色地面、红色训练凳、哑铃架和墙上风扇。

背景一名灰衣成年健身者继续训练，不围观、不尖叫。

主角双手握同一根曲杆杠铃，两侧黑色杠铃片数量固定。

[0—4秒｜认真完成弯举]

男子双脚站稳，双肘靠近身体，将杠铃从髋部抬向胸前。

前臂先弯曲，肱二头肌随后收紧。

背部巨大隆起随着肩部受力轻微挤压，两道创口位置保持不变。

他低头看杠铃，表情吃力，短促呼气。

手机轻微调整，保持异常肩背和弯举动作同框。

[4—7秒｜缓慢放下]

男子控制杠铃下降，直到双臂接近伸直。

肩背软组织随卸力稍微下沉、晃动，然后稳定。

汗水沿皮肤流下。

不能突然缩回正常身材，不能新增肿块。

[7—10秒｜结束训练]

他屈膝、向前俯身，把杠铃放到脚前地面。

杠铃片先接触地面，再松开双手。

传来一次沉闷金属碰响。

手机自然向下跟一点，随后抬回上身。

男子直起身体，粗重呼吸。

[10—12秒｜发现有人拍他]

男子先转头看镜头，再转动肩膀和躯干，变成偏正面的站姿。

双臂自然垂下，肩背异常体积仍能从轮廓辨认。

他看着拍摄者喘气，嘴微张，没有扑向镜头。

画面直接结束。

[现场声音]

呼吸、鞋底摩擦、杠铃片轻响、器械碰撞和墙上风扇。

无配乐、旁白、字幕或怪物吼叫。

[连续性约束]

只有一个主角、两条手臂、一根杠铃。

异常肌肉和创口保持固定位置，不逐帧换形。

握杠、弯举、下降、落地、松手的顺序完整。

镜头留在同一观察位置，由男子转身呈现正面。

不加入袭击、触须、突然变身或血腥爆裂。

Created a video 30 seconds, Beautiful Korean girls enjoying a late-night ramen break at a Korean convenience store. Three stylish young Korean women with natural Korean beauty, realistic skin texture, dark expressive eyes, and casual streetwear gather around a ramen counter under bright fluorescent lights. One girl wears a blue-and-black sporty jacket with loose navy track pants, another has short silver-gray hair and a black jacket, and the third wears a dark casual outfit with straight black hair. They prepare instant ramen, hold chocolate milk and snacks, and share a relaxed late-night meal together. Show cinematic close-up shots of steaming ramen cups, chopsticks lifting noodles, a girl gently blowing on hot noodles before eating, and friends enjoying their food while chatting naturally. Transition to a wider shot of the girls sitting at a small round table beside the convenience store window, with city lights glowing outside and reflections on the glass. Near the end, one girl gets up, adjusts her backpack, and heads toward the glass entrance while the others remain seated. Capture authentic Korean convenience-store culture, candid friendship moments, subtle facial expressions, natural movements, realistic food textures and steam, handheld camera motion, shallow depth of field, cool blue cinematic color grading, soft reflections, moody nighttime atmosphere, ultra-realistic live-action cinematography, consistent characters, detailed clothing textures, smooth transitions, vertical 9:16 aspect ratio, 4K quality, no subtitles, no text, no watermark.

Create a 30-second, ultra-realistic cinematic video featuring a beautiful young adult Korean woman inside a spacious, modern dance studio with smooth wooden flooring, large mirrors, and soft indoor lighting. At the beginning, show several dancers practicing in the background while the camera captures the girl's bare feet and black loose-fitting pants as she walks across the studio floor. She is wearing a fitted black long-sleeve top and loose black trousers, with her dark hair tied back casually and a few strands falling naturally across her face. As the video progresses, she appears tired and emotionally overwhelmed after practice, slowly sitting down against a light grey studio wall with her knees drawn close to her chest. She gently holds her injured ankle, which is wrapped in a light-colored bandage, and looks down with a quiet, sad expression. Other dancers continue practicing in the background, creating a realistic contrast between the busy studio and her lonely moment. Use a mixture of wide shots, medium shots, and intimate close-ups of her face, hands, and bandaged ankle. Her movements should feel subtle, natural, and emotionally believable, with realistic skin texture, delicate facial details, and consistent character appearance throughout the video. Use soft cinematic lighting, muted neutral colors, shallow depth of field, smooth camera movements, and a professional Korean drama aesthetic. Maintain a photorealistic look, natural body proportions, realistic studio details, and high-quality 1080p visuals in vertical 16:9 format. Avoid exaggerated expressions, artificial skin, distorted hands, extra fingers, flickering, and unwanted text or watermarks.

15s studio motion-design reel, 1920x1080.
Warm off-white, black type, one orange accent only.
A single orange circle with motion blur is the through-line and the cut.
Show: toggle click, the word Motion, shape morphs, dotted connector, rounded diamond, circular kinetic type (KINETIC TYPE · 3D · LOOPS · SPRINGS · EASING), dot grid, then the card “Opus 5.5 / Motion designer. / 0 keyframes”.
Springs, no glow, no particles, no default easing.
Looks like a refined product-studio showreel, not an AI trailer.

你咋一天这么多事，要打就打
prompt：

电影级写实质感，纯古风中国仙侠美学。

把真正庄严的高手挑战，与 “提前包装江湖名声” 的元喜剧进行碰撞。
吸收：
默片式反应节奏

英式一本正经逻辑
港式喜剧快速铺垫与回收
经典“三拍递进”结构
采用：

Arri Alexa 电影机质感

稳定清晰的面部微细节
细腻胶片颗粒
自然体积光
核心喜剧主线

整段只保留一条第一遍就能立即看懂的喜剧主线：

一个极其自信的敌方剑客，为了证明自己即将获得一场传奇胜利，专门带来一名江湖记事先生“客观记录”；结果真正的决斗还没开始，图一图二两名女子就发现——敌人连最后怎么写都已经提前花钱定好了。

角色功能原则

记事先生始终只承担一本正经的辅助角色

年长师父只负责最后一次补刀
参考与环境
将 @图片 1 和 @图片 2 严格作为人物身份锚点。

本轮新上传的所有背景与地点参考图，共同决定同一套环境 DNA。
正式构图前，无声整合能够互相兼容的：

真实地形

建筑语言

材质年代
植被

水体
天气
山雾
主光方向
反光关系
空气纵深
人物真实可行走路线
再重新规划成本轮独有、完整统一的新空间。
背景原则
背景中的以下元素始终持续自然鲜活，但在叙事上绝对中立：
自然风

水体

植被
云层

远处普通弟子
空间环境声
角色设定
角色 ID A｜剑仙师姐
始终是同一个 @图片 1 剑仙师姐：
25–30 岁东亚女性

身材高挑纤细

椭圆脸

深色杏眼
黑色长发半挽，以白玉簪固定

始终穿同一套白色刺绣真丝汉服
银色腰封
玉佩
白色布靴
持唯一一柄银色长剑
角色 ID B｜小师妹
始终是同一个 @图片 2 小师妹：
20–25 岁东亚女性
身形娇小
圆润灵动的脸

黑发编辫
始终穿同一套青绿色亚麻汉服

深色腰带
木簪
黑色布鞋
持唯一一柄深色钢剑
其他角色
敌方剑客
气势十足
极其自信
非常在意自己的江湖名声

江湖记事先生

唯一一名中年记事先生
手中只有毛笔和一卷没有任何可读文字的素色纸卷
始终一本正经、职业化、认真执行自己的“记录工作”
年长师父

始终沉稳
只在最后完成一次一本正经的补刀
分段结构
0–5s｜全景或远景

一名气势十足的敌方剑客进入根据本轮参考图自然形成的开放区域，身旁跟着唯一一名中年江湖记事先生。
记事先生手中只有毛笔和一卷没有任何可读文字的素色纸卷。
敌人拔剑，非常郑重地宣布：

“今日请先生作证，免得有人输了不认。”

同一个小师妹看了一眼旁边的记事先生，平静评价：

“还挺正式。”

同一个白衣剑仙从头到尾保持冷静。

5–10s｜中景或牛仔景

保持：

同样人物

同样服装

同样长剑

同一个记事先生

同一卷纸

完全一致的地理空间

真正决斗还没有开始，记事先生突然非常职业化地稍微靠近敌人，小声确认：

“公子，还是按‘十招大胜’记？”
全场绝对安静半拍。
敌人的身体当场僵住，立刻压低声音恼火反问：
“不是说打完再写吗？”
记事先生一本正经回答：
“定金付的是这个结局。”

同一个小师妹非常缓慢地把眼神从记事先生移到敌人脸上，难以置信地问：

“结局都买好了？”

同一个剑仙师姐什么都没说，只极轻微地抬起一侧眉毛，第一次产生真正兴趣。

整个背景从头到尾持续自然运行，却完全不参与笑点。

10–15s｜特写或极近特写

同一个白衣剑仙非常认真地问记事先生：

“若他输了呢？”

同一个记事先生几乎零停顿回答：

“补银子，可改成‘虽败犹荣’。”

敌人瞬间恼羞成怒：

“我不会输！”

镜头焦点转移到两人数步后方自然存在的同一个年长师父。

师父从头到尾保持绝对一本正经，只淡淡说道：

“那先替他记一句：未开打，先改稿。”

同一个记事先生非常职业化地点一下头，立即抬起毛笔准备继续记录。

敌人这一次真正慌了，马上喊道：

“这句别记！”

记事先生停顿半拍，看着他认真评价：

“这句也挺好。”

极近特写：

同一个小师妹迅速转开脸，肩膀出现极轻微颤动，拼命忍住笑

同一个剑仙师姐则依旧保持真正高手的庄重表情，非常礼貌地向敌人做出一个继续比武的手势：

“现在能打了吗？”

敌人先看看记事先生，再看看自己手中的剑，最后又看看后方师父，突然意识到现在真正岌岌可危的已经不是自己的身体，而是自己苦心经营的江湖名声。

在他回答之前精准切黑。

喜剧节奏原则

整段必须符合清楚的“三拍递进”：

第一拍

敌人郑重带着记事先生上场，像要见证一场传奇胜利。
第二拍

记事先生职业化暴露：胜负文案已经提前付费定好。

第三拍

师父一本正经补刀，记事先生准备如实记下，敌人终于发现真正危险的是自己的名声。

表演原则

敌方剑客

不是丑角表演

不是故意滑稽
必须认真维护自己的排场和体面

喜剧感只能来自他越想保住名声，越暴露自己提前包装结果
记事先生

必须极端职业化
一本正经

逻辑清楚

完全不觉得自己荒唐

他的喜剧感来自“过度认真”
剑仙师姐
全程冷静
不嘲讽
不抢台词

后半段才因为事情的荒谬性，第一次表现出真正兴趣
小师妹
反应要自然
不夸张大笑
重点是“忍笑”
年长师父

必须绝对平静
那句“未开打，先改稿”要像陈述事实，而不是故意抖包袱
硬性要求
严格总时长 15 秒
16:9 横屏

三个连续清晰镜头
原生同步普通话对白
精准口型
明确的喜剧停顿

针对 Seedance 2.0 Mini 强化多参考人物身份连续性
人物面部全程稳定
发型全程稳定

服装全程稳定

长剑全程稳定

记事先生道具全程稳定
配角位置全程稳定
地理空间全程稳定
人物走位简单清楚
真丝衣料和头发物理效果真实
前景、中景、远景保持自然视差与真实空间环境声
不生成字幕
Negative
blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Cinematic 4K action sequence in a dark movie theater. A young Asian woman with long black hair and a green long-sleeve top is eating popcorn, watching a sci-fi blockbuster on screen. Suddenly, a robotic cyborg villain with glowing red eyes leaps out of the movie screen into the theater. The environment instantly shatters and transitions into an epic ancient ruin courtyard with stone columns under a stormy sky. Dynamic camera movement tracking intense hand-to-hand combat between the woman wielding swirling green magical energy and the metallic cyborg casting purple spell circles. High-budget Hollywood blockbuster aesthetics, dramatic lighting, particle effects, slow-motion impacts, and hyper-realistic textures.

جربت Motion بـ Claude Opus 5.5
Headless chrome
Canvas API (Assets Generation/ Paper textures)
Yoga-layout
Prextext
Floating UI
وقلت له يسوي
Vox-vibe video
وعطيته ملفات PDFs وصور

帮我生成一段约 3 分钟的视频，解释太阳系的各大行星。做科普知识讲解，让高中生都能听得懂，解释完太阳系再讲解银河系的相关知识。画面要炫酷展现出浩瀚的宇宙，配上中英字幕。

Create a cinematic sci-fi battle sequence in a wet industrial harbor. Scene 1: close-up tracking shots of a heavily armored futuristic warrior, detailed black tactical armor, helmet and glowing blue accents. Scene 2: close-up of his armored hand activating a powerful glowing blue energy sword. Scene 3: wide shot as he walks forward across the rain-soaked dock, sword glowing beside him, cargo cranes in the background. Scene 4: several dark monstrous creatures suddenly rush toward him from the distance. Scene 5: the warrior fights them with fast, powerful sword movements, dodging and striking through the creatures. Scene 6: intense close-up of his face inside the helmet, blue reflections across his eyes. Scene 7: he launches into the air and attacks between the creatures with the energy blade. Scene 8: final wide shot as he lands and unleashes a powerful blue energy strike, water splashing dramatically around him. Photorealistic, dark cinematic sci-fi, dramatic overcast lighting, realistic rain, wet reflections, dynamic handheld camera, fast action, high detail, seamless motion, epic movie-quality VFX.

【全局设定】
古风写实电影镜头，东方古典生活叙事，雨后江南古镇：青石台阶、青砖黛瓦、木质廊檐、雕花木门、竹帘、湿润石板巷道。阴天柔和漫射光，低对比度，冷灰青与温暖木色融合，轻微35mm胶片颗粒，真实皮肤、木石与织物纹理，电影级浅景深，8K，16:9。

女主A：图1
女主B：图2

全片严格保持角色身份、空间位置、左右关系、行进方向、天气、光线、色调连续。

【核心摄影技法】
全片以“渐进式光学变焦”为唯一核心运镜。摄影机尽量固定机位，不依赖实体移动，通过缓慢连续的光学推近、拉远改变人物画面占比与空间关系。保持真实镜头压缩、景深变化和光学特征，禁止数字裁切。前景遮挡、浅景深、焦点转移辅助叙事，形成“远处发现→隔巷对视→空间压缩→情绪确认”。

【0-4s】
中景起幅，35mm，固定机位，视线高度。女主A沿青石台阶缓慢下行至巷口，停步转身抬头，看见远处廊檐下的女主B。镜头从较宽环境关系构图开始，仅缓慢光学推近，逐渐收紧至女主A中景，摄影机不移动。

古镇行人先后从左右前景横向经过，近距离形成自然虚化遮挡，女主A始终保持清晰；遮挡期间曝光、色温、光影稳定。变焦持续平滑克制，最终形成女主A与远处女主B隔巷对视。

【4-9s】
承接上一段，机位完全不变。女主B从画面右侧前景缓慢进入，靠近木质廊柱，与廊柱形成天然前景框；女主A位于左中部巷道深处。

缓慢连续光学变焦，女主A先保持清晰，随后画面逐渐收紧，女主B前景占比增大，女主A退入背景并柔和虚化。逐渐进入长焦端，通过真实空间压缩使古巷纵深被压缩，两人实际距离不变，但视觉距离明显拉近。焦点平滑由女主A转向女主B，最终女主B侧脸清晰、女主A虚化。摄影机不横移、不摇摄、不绕拍，曝光与色调连续。

【9-13s】
保持固定机位与长焦关系。女主B站在木质廊柱旁缓慢转身，看向女主A。仅进行一次极缓慢光学推近，从双人关系构图收紧至女主B中近景。画面左侧保留女主A局部虚化轮廓，形成窥视式前景框架。

女主B成为主要焦点，看向女主A，短暂停顿后轻声说：“好久不见。”露出极轻微笑意。竹帘被雨后微风吹动，屋檐水滴自然落下，湿润青石反射柔和天光。镜头稳定推进，在近距离情绪确认中结束。

【镜头控制】
核心必须是“光学变焦制造叙事距离变化”，而非摄影机移动。镜头语言依次完成：环境建立→发现女主A→缓慢收紧→女主B进入前景→长焦空间压缩→焦点转移→情绪确认。变焦速度缓慢连续，具有真实镜头惯性；保持自然人物比例、真实景深与稳定曝光，明确呈现光学变焦感，但无廉价数码放大感。

【连续性与负面约束】
严格遵循角色卡，禁止外貌、发型、服装漂移；保持空间地理关系、左右位置、运动方向、光线方向一致。禁止现代建筑、交通工具、路牌、现代物件、字幕、水印；禁止新增主要人物、人物重复、肢体异常、身份交换。禁止横移、环绕、突然摇镜、无人机运动、强手持抖动、数字变焦、数码裁切、透视异常、焦距跳变、景深瞬切、曝光闪烁、色温漂移、过度雾化、过度磨皮、AI塑料皮肤。

Cinematic epic 30 second fantasy battle at golden hour sunset. A fierce young East Asian warrior woman with long flowing dark hair, wearing flowing white and crimson hanfu-style robes with a wide red embroidered sash and red shoes, charges through a massive battlefield. She wields a glowing pink-red energy sword that leaves bright crimson light trails as she spins, slashes and cuts down dark armored knights. Dramatic close-ups of her intense determined expression, hair whipping in the wind. Wide shots reveal thousands of fallen soldiers on the dusty ground, burning ruined castles and towers in the background with thick smoke and raging fires. Multiple large dragons with massive wings soar overhead, some breathing streams of fire. Dynamic camera movement, slow-motion sword swings, epic scale, ultra-realistic lighting, volumetric god rays, highly detailed, cinematic 4K quality.

Create a cinematic, highly detailed video showing a group of tiny construction workers building a massive modern amusement park from the ground up. The miniature workers wear construction helmets, reflective safety vests and work clothes while operating cranes, drills, scaffolding and construction equipment.

Show the amusement park being built progressively: foundations first, then enormous roller-coaster supports and tracks, followed by a giant Ferris wheel, colorful rides, carousels, themed buildings, entrance gates, food stalls and attractions.

Emphasize the dramatic contrast between the tiny workers and the gigantic structures they are constructing. Show cranes lifting massive pieces into position while the workers guide and assemble them.

End with the completed amusement park illuminated at night, with the Ferris wheel spinning, roller-coaster trains moving and colorful attractions glowing.

Use cinematic aerial shots, macro close-ups, low-angle shots, crane shots and smooth tracking movements. Photorealistic visuals, realistic construction physics, dramatic lighting, detailed environments, realistic shadows, depth of field and smooth motion.

Make the entire transformation feel satisfying, spectacular and believable.

No text, no subtitles, no logos, no watermark.

Create a 15-second photorealistic vertical smartphone video on an ordinary city street after sunset. A young woman walks through light rain while holding a small umbrella. Suddenly, individual raindrops begin rising upward from the pavement into the sky instead of falling down. She stops and looks around in confusion as puddles slowly become dry while hundreds of droplets float upward around her. Natural human reaction, realistic water physics, authentic handheld phone footage, believable street lighting, subtle camera movement, cinematic realism, no text, no logos, no recognizable brands.

Create a ultra-realistic UGC-style brand commercial for a premium electric cycle called EVOX, featuring a young woman demonstrating the cycle and its wireless remote-control functionality in different environments. The video should feel like a creator discovering and testing an innovative new product, mixed with premium cinematic product shots.

SPEAKER CAROUSEL
<setup>
Claude is connected directly to my open After Effects project through the AE MCP.
Work inside the Inner comp where the speaker ring already exists.
</setup>