Character video 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。

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.

[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.

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

流れ星が降り注ぐ夜空、ピンク色のガラスで作られた薔薇が所々で光輝く緑色のネオンの地に佇む、ピンクと白を基調とした着物ドレスを纏い、メタリックシルバーの近未来的な高下駄を履いた長い黒髪の若き女性のイラスト。文字やロゴはなし。

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.

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 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 high-quality 15-second vertical 9:16 3D animated educational kids video in a bright, colorful, cute nursery-rhyme style.

Main character:
A cute 2-year-old toddler boy with chubby cheeks, big expressive brown eyes, short light-brown hair, a bright blue T-shirt, yellow shorts, and colorful sneakers. Keep his appearance perfectly consistent throughout the entire video.

Story concept:
The toddler discovers a glowing magical map and follows it on a very short learning adventure to help a cute rabbit find three missing fruits.

0–3 sec — The Discovery

The toddler is playing in a colorful room when a glowing rainbow map suddenly appears.

The map shows three missing fruits:

🍎 Apple
🍌 Banana
🍊 Orange

A cute rabbit appears looking worried.

The toddler points toward the map and excitedly begins the adventure.

3–6 sec — Find the Apple

Fast magical transition into a colorful fruit garden.

A shiny red apple falls gently from a tree.

The toddler catches it and smiles.

Display large clear text:

“APPLE 🍎”

6–9 sec — Find the Banana

The toddler runs a few steps and notices a bright yellow banana.

He picks it up happily.

Display:

“BANANA 🍌”

9–12 sec — Find the Orange

A bright orange rolls across the grass toward the toddler.

He stops it with both hands and laughs.

Display:

“ORANGE 🍊”

12–15 sec — Happy Ending

The toddler places all three fruits into the rabbit’s basket.

The rabbit jumps happily.

A colorful rainbow appears behind them.

The toddler and rabbit wave toward the camera.

Display:

“Great Job! 🌈”

Animation:
Fast but smooth storytelling, natural toddler movements, expressive reactions, accurate hand-object interaction, playful running, picking up fruit, smiling, pointing, and waving.

Camera:
Vertical 9:16, quick child-height tracking shots, gentle push-ins, clear close-ups of each fruit, smooth magical transitions, no confusing cuts.

Visual style:
Premium polished 3D children’s animation, vibrant colors, soft cinematic lighting, glossy surfaces, cute rounded shapes, cheerful preschool atmosphere, clean backgrounds, expressive character animation.

Important:
Keep the entire video within 15 seconds.
Use only one main action per shot.
Keep text large and readable.
Do not overcrowd scenes.
No character morphing, extra fingers, duplicated objects, inconsistent clothing, flickering, warped fruit, or sudden background changes.

recreate the blue beret blob from OpenAI's Dots — fuzzy felt surface, breathing, blinking, squash & stretch, a lagging beret, and a subtle reaction to the mouse.

Realistic personal Japanese family dinner vlog set in early-2000s Tokyo, filmed casually on an authentic consumer DV camcorder. Use the SAME young Japanese woman from the reference image throughout. Keep her exact facial identity, hair, outfit, handbag and appearance consistent.

EXACT ORDER:

0–4s — LOCAL SUPERMARKET: She enters a small early-2000s Tokyo supermarket, takes a basket and walks through the aisles.

4–9s — CHOOSE INGREDIENTS: She selects vegetables, tofu, mushrooms, rice/noodles and fish or chicken. Clearly show her examining and placing them into the basket.

9–12s — CASH PAYMENT: At checkout, the cashier scans the groceries. She pays with Japanese yen cash, receives a receipt and places the groceries into a shopping bag before leaving.

12–16s — RETURN HOME: She walks through a realistic early-2000s Tokyo neighborhood carrying the same grocery bag, then unlocks her home and enters.

16–22s — PREPARE DINNER: In a modest early-2000s Japanese kitchen, she takes out the same ingredients, washes and cuts them, then cooks a simple Japanese dinner using period-appropriate cookware.

22–26s — SET THE TABLE: She brings the finished food to the dining table and sets rice, soup, vegetables/protein, bowls and chopsticks. Her family joins and sits down.

26–30s — FAMILY DINNER: The family eats together, casually talks and smiles. She takes a bite and briefly looks toward the camera with a natural smile before continuing dinner.

ERA LOCK: Everything must authentically belong to early-2000s Japan—fashion, supermarket, packaging, cars, appliances, kitchen, furniture, television and tableware. No smartphones, modern LED screens, AirPods, modern cars, contemporary interiors or current packaging.

CAMERA STYLE: Raw DV footage with subtle handheld shake, imperfect framing, autofocus hunting, exposure shifts, soft digital detail, mild CCD/DV noise, motion blur and occasional awkward zooms. Natural home-video behavior, realistic skin and movement. No 4K sharpness, stabilization, beauty filters, VHS effects or cinematic lighting.

CONTINUITY: Same woman, outfit, hairstyle, bag, ingredients and family throughout. The purchased ingredients must be the same ones used for cooking and served at dinner. No teleportation, identity drift, disappearing props, reordered scenes or modern elements.

FINAL FEEL: A genuine early-2000s Japanese family memory—from grocery shopping and cooking to sitting down for an ordinary family dinner.

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.

保持参考图中的人物五官、发型、蓝白碎花吊带裙、身材比例、阳台、桌面物品和海景环境一致，不换脸，不改变服装。

10秒真实旅行抓拍视频，像朋友在酒店阳台随手拍摄。

开始时，年轻亚洲女性自然坐在阳台沙发上，侧头安静看着远处海面和夕阳，海风轻轻吹动长发和裙摆，人物自然眨眼，身体有轻微呼吸起伏。

约第3秒，一阵突然变大的海风从侧面吹来，桌上的一张轻薄餐巾被吹起来，沿着桌面滑向阳台边缘。女生先愣一下，低头看到后，下意识快速伸手去抓。

约第5秒，她差一点没抓住，身体微微向前探，头发也被风吹乱。最后成功抓住餐巾，她先低头笑了一下，然后带着一点无奈的表情重新靠回沙发。

最后2秒，她把餐巾压在桌面上，一只手顺势整理被风吹乱的头发，再抬头看向远处夕阳，嘴角还有轻微笑意。

整段保持真实手机抓拍感，镜头轻微手持，不环绕，不快速变焦，只允许非常缓慢自然的向前推进。海面波光、远处帆船、窗帘和发丝都保持自然运动。

强调真实人体动作和重力惯性，人物面部始终稳定，手指正常，裙子结构稳定，桌子和饮料不变形。

避免：人物突然站起来、夸张大笑、餐巾飞得太高、身体大幅扭曲、脸部漂移、换脸、手指畸形、衣服变化、桌上物品突然消失、强烈电影运镜。

5-beat multi-shot prompt: setup > acceleration > peak > escape > out

Each beat gets its own camera move + sound cue:
• Setup: wide, city normalcy
• Acceleration: push-in through traffic
• Peak: low Dutch tilt, fireball behind the lean
• Escape: track past as a second blast hits
• Out: camera holds as he vanishes into smoke

Locking low angle, 28mm, and fire vs. cold city tones across all 5 keeps it one coherent shot instead of five random clips

全片生物、面部近景、建筑和远景统一为明显电脑生成的高品质AAA奇幻游戏过场动画，使用数字雕刻脸模、经过美术设计的材质光影与成束头发，不混入实拍演员，不采用2D动画、赛璐璐描边或普通gameplay。整体是由连续硬切连接的末日奇幻战争蒙太奇：巨型军团推进、远超军团尺度的骨架生物显露、城内两只巨人短暂肉搏，最后切到另一只猿形巨人的咆哮蓄能；不同生物保持各自身份，不把这些切镜做成同一角色连续变形。环境与色彩：密集的中世纪半木构城市，红褐瓦顶、深棕木梁、浅米色墙面、窄石街、烟囱、尖顶塔楼与高耸外围石墙；所有普通房屋、街道和塔楼都远小于巨人，战斗者的腰胸高过附近屋顶，巨型军团更高，远处骨架生物又远超整个军团。厚重灰褐烟云和橙金逆光覆盖城市，浮尘、碎瓦和蒸汽形成多层纵深；开头为浓重焦褐尘雾，中段为暖金天空照亮的城内废墟，结尾为巨大圆形金色逆光与翻卷云雾，保持同一末日暖金色系。A巨型军团：多排无发的超巨大成年男性化人形生物，宽肩厚胸、深红肌束与浅象牙腱膜、深陷眼窝和清楚齿列，肋部及肩胸表面具有连续雕刻组织；这是生物本来的完整外观，不是新鲜伤口，没有流血。它们空手、无衣甲，前后排列有真实纵深，头肩与步幅略有差异，沿同一个方向持续缓慢行进，身体周围蒸汽升腾，脚下带起尘浪，不是静止观众或重复粘贴的同一人。B骨架巨构：军团后方仅有一个远比它们庞大的非人骨架生命体，浅褐象牙色中央脊柱高耸，两侧大量狭长弧形肋骨向外展开再向下弯曲，像覆盖军团上空的巨大骨架穹顶，肋弓之间有真实空隙，不是翅膀或建筑。前部低悬着一张狭长的红褐骨质面孔，深眼窝、尖长耳、露齿下颌，黑色长发成束垂落在面部两侧，头部通过颈部连接同一骨架，不是独立漂浮的头。最初眼睛暗，随后两眼亮起翠绿色光。C黑发硬拳巨人：中段肉搏主角之一，强健修长的人形非人生物，棕褐皮肤与清楚胸腹肌束，肩背宽而腰收，长深棕黑发、尖耳、强下颌与齿列，双眼翠绿发光。两只拳头及下段前臂覆盖浅灰白色粗糙硬化结晶，晶层依附真实拳指与腕部，仍是同一双手，不是手持石块或拳套武器；肘关节以上保留原本肌肉形态。D浅金骨甲巨人：另一名肉搏者，体量与C接近但更宽厚，短浅色头发、浅金色眼光，脸、胸、背、肩和四肢有层叠浅金褐色生物骨甲，深褐肌束连接甲片之间，甲片是身体的一部分，不是穿戴金属盔甲。空手，两臂与头部全程完整，肩颈逸出薄蒸汽。E黑鬃猿形巨人：末段独立角色，厚重黑褐毛发覆盖巨大肩背与极长双臂，躯干前倾，腿较短且强健，沉重猿人面孔、后梳深色头发、突出眉弓、尖耳与猩红眼睛，嘴中有成排尖齿。它与C、D和B是不同生物；长臂、黑毛与红眼始终保留。0.00–2.20秒：立即从浓重橙褐烟尘中的略倾斜近中景开始，前景破碎屋脊、墙板与石块遮住画面下部，数名A的巨大无发头颅与肩胸从废墟后方逼近，后面还能看见更大的模糊肋骨轮廓。摄影机沿废墟缓慢侧移，近处残墙与碎片快速横过，远处头颅较慢移动形成尺度与parallax；蒸汽和尘流不断穿过它们面前。2.20–4.20秒：切到接近地面的斜侧宽景，整排A从画面近侧延伸到远处，宽肩、长臂与肌束胸腹从烟中显出，身体随沉重步伐交替起伏，手臂自然摆动。摄影机沿军团方向缓慢退移，前景滚动尘浪，后排继续推进，不能让军团站定摆姿势。4.20–7.20秒：硬切正面低角极宽景，A的前排头肩横贯画面下方，B的巨大中央骨架与两侧肋弓在它们后方高高耸起。镜头缓慢上仰并略微前推，烟云先遮住上部结构再被气流拨开，低悬长发面孔位于中央骨架下方。两次短促金色闪电在远后方云层中亮起，瞬间照亮肋骨边缘、云团与军团轮廓后迅速衰退，闪电不是射向士兵的攻击，也不把已有生物变成其他形态。7.20–9.60秒：切B低悬面孔的正面紧近景，巨大的弧形肋骨仍在头后形成连续背景。黑发束垂在两颊旁，尖耳向外，头部微微抬正；先保留深暗眼窝，随后两眼由暗变为清晰翠绿光，视线凝向前方。烟和小尘粒持续通过镜头，不让脸冻结，不添加对白或眼部光束。9.60–11.60秒：以烟雾中的硬切转入另一片城内街区，低角正面中全景，C从灰褐尘幕中向前迈步显露，双拳低垂，胸腹与肩背随步伐运动，两侧较小塔楼和红瓦屋顶明确显示巨人尺度。镜头略向前接近，翠绿眼光透过黑发可见，两只浅灰硬化拳和前臂同时保持清晰；这不是B缩小成人形，也不复制出第二个C。11.60–12.40秒：突切向上仰拍的云天，一具蜷曲的巨大人形轮廓处于金色分叉闪电和近圆形发光蒸汽团中央，身体向下坠近，一臂抬过头侧，一膝收起。电弧沿周围空气和身体轮廓分叉，强光短暂压暗背景。只展示这个有实体身体的空中电光片段，不插入小人长大或从C体内分裂出的过程。12.40–13.20秒：切城内贴石街的倾斜低机位，远处房屋之间D已处于落地后的低蹲，石块和瓦片被震起，贴地尘浪沿街涌向镜头；落地位置与尘浪源点一致。高墙和红瓦屋顶上方可见一艘遥远的浅色长椭圆飞艇，缓慢漂移，不发射、不爆炸。镜头随地面冲击短震，屋顶和瓦片为巨人尺寸参照。13.20–14.20秒：切贴近D侧面的快速跟拍，D从低姿势向前冲出，躯干前倾、双脚交替蹬地、弯肘摆臂，肩颈蒸汽向后拖；浅金骨甲保持固定在同一身体上，双手空着，背景瓦屋和烟囱迅速后移。14.20–15.00秒：切C略低角胸上近景，C迅速转头、转肩看向冲来的D，长黑发被甩向一侧，翠绿眼睛锁定对手，下颌绷紧，身体开始转髋迎击；镜头贴近其面部短促跟转，不停下来重新对峙。15.00–16.00秒：切街道低位双人宽景，C在screen-left，D在screen-right，两者在小型房屋之间快速缩短距离。C踩稳前脚、后脚抓地，右肩和右髋向后蓄力，右侧硬化拳明显拉到身后，左臂在前方保持平衡；D继续向C压近并抬臂，瓦片和灰尘从两者脚边翻起。完整看见脚底支撑、转髋与拳头准备，不出现瞬移换边。16.00–17.40秒：摄影机快速贴过C肩侧并跟随右臂前送，C由后脚蹬地、髋部旋转带动肩和右侧硬化拳，沿单一清楚弧线打向D面侧。黑发向后甩，眼部转动带出极短翠绿拖光而不是激光；拳头逼近时短暂放慢以看清轨迹，随后清楚接触D脸侧骨甲。接触产生紧凑粉尘、小硬质碎屑与少量火星，D的头和肩先受力偏转，再带动上半身后仰。拳臂没有穿过头颅，没有血或断裂肢体，摄影机在接触瞬间短促震动。17.40–18.50秒：顺接倾斜的D近中景，他的头、肩和胸甲沿第一拳的力量方向扭转后退，两臂被甩开后开始重新收拢，脚下在瓦砾间调整支撑。镜头随上半身退移，下方红瓦屋顶保持远小于他，C仍在同一侧近处，不把这一反应剪成新变身或完全倒地。18.50–20.40秒：切回较宽的双人侧面构图，C再次把右侧硬化拳抬高至头上方形成威胁，另一只硬化拳处于较低前方。D向前顶身并...