Retro-Futuristic Anime Silhouette
A video prompt for Grok Imagine featuring a silhouetted figure in a dynamic pose against cliffs and space in a retro-futuristic anime style.
本页汇集归入“Cinematic Showcase”分类的视频提示词示例。调整示例用于自己的项目之前,可先比较生成结果、构图或镜头选择以及原始写法。
3,858 prompts
用途
A video prompt for Grok Imagine featuring a silhouetted figure in a dynamic pose against cliffs and space in a retro-futuristic anime style.
A silhouetted figure in dynamic pose against cliffs and starry space in retro futurism anime style. Keep reaching never give up!
A prompt for a hyper-realistic cinematic fashion video featuring a woman smoking while a crowd behind her moves in synchronization.
Create a ultra-realistic cinematic fashion video using the uploaded images as exact visual references for the woman, crowd, wardrobe, framing, and atmosphere. A young woman with the same short dark bob wears a fitted black turtleneck, black trousers, and black shoes, standing confidently at the center of a large crowd. Start with her walking slowly toward the middle of the crowd, calm and expressionless, with a lit cigarette naturally held between her lips. She reaches the center, stops, and faces directly into the camera. She takes one slow drag from the cigarette, then removes it from her mouth. She slowly exhales a visible stream of smoke toward the camera, with the smoke naturally drifting across her face. She lowers her hand and becomes completely still, staring directly into the lens. The entire crowd behind her remains frozen for a brief moment. Suddenly, everyone behind her begins moving in perfect synchronization — sharp head turns, shoulder jerks, folding forward and snapping upright. The movement should feel rhythmic, strange, powerful, and physically realistic. The woman does not move at all while the entire crowd moves behind her. Slowly push the camera closer to her, keeping her sharply focused while the crowd has subtle depth-of-field blur. Dark, cold, mysterious lighting with deep shadows, realistic skin, hair, clothing, cigarette ember, and physically accurate smoke. Photorealistic live-action quality, cinematic composition, natural human movement; no animation, CGI look, duplicated woman, distorted bodies, excessive smoke, text, subtitles, or logos.
A video prompt used to generate a chain reaction domino effect.
Dominos lined up and in a long single file line , one pushed over leading to a cascading domino effect falling one after another
A descriptive video prompt showing a woman in a long green dress walking through a forest with a dragon by her side.
Woman walks away green gown color of a forest back of gown is v shaped showing off the upper 2/3 of her back as she walks the forest path a dragon camouflaged to blend in with the forest sprinkles golden dust over woman as she passes the dragon
A workflow description for generating sound effects using Grok Imagine, including a specific example prompt.
A warrior striking 3 times with his Claymore on plate armor, no background noise, no ambiance…
A prompt for generating a realistic early 2000s DV-style video of a young Korean woman doing chores in Seoul.
Create a 30-second, 1080p ultra-realistic early-2000s DV home video of a young Korean woman doing quiet Sunday chores around her home in an older Seoul neighborhood. Purely observational, no dialogue, no narrative arc just rhythmic, textural everyday realism. MAIN SUBJECT Young Korean woman same as , early 20s, natural beauty, realistic skin texture, no makeup, black hair tied up messily in a claw clip, oversized faded T-shirt, rolled-up sweatpants, bare feet or house slippers. Keep her identity, outfit, hairstyle and proportions perfectly consistent throughout. SETTING The front step and small yard/alley outside an older Seoul home. Concrete step, a low gate, potted plants, a garden hose, a trash bin, scattered leaves. Ordinary, lived-in, no landmarks or brand names. SEQUENCE (rhythmic, no dialogue) She sweeps the front step with a short broom, dust and leaves scattering in the light. She crouches down and pours a small amount of dry food into a bowl for a neighborhood cat waiting nearby; the cat eats while she watches briefly. She stands and waters potted plants along the wall with a small watering can, water visibly darkening the soil. She picks up a bagged trash bundle and carries it a few steps to place it by the curb/bin. She wipes her hands on her shirt, looks around the now-tidy step and yard for a moment, then exhales/stretches. She glances toward the camera briefly with a small, tired smile — no words — then turns and walks back inside. Camera holds on the empty, swept step for a beat before cutting to black. CAMERA Raw handheld early-2000s DV camcorder, shaky footage, autofocus hunting, faded colors, exposure shifts, motion blur, soft digital detail, occasional accidental zooms. Observational, documentary-like framing — lingering shots, no cuts within actions. No polished cinematography. AUDIO Natural ambience only — broom bristles on concrete, water pouring, cat eating, distant birds, wind, a far-off scooter or dog bark, plastic bag rustling, faint footsteps. No dialogue, no music. CONTINUITY Broom, watering can and trash bag each remain consistent through their respective actions. Cat stays in frame while eating, doesn't disappear or duplicate. No teleporting or vanishing objects. Smooth, realistic, unhurried movement throughout. NEGATIVE CGI look, plastic skin, identity drift, outfit changes, distorted hands, extra fingers, subtitles, watermark.
A prompt for generating cinematic stills of survivors in an abandoned classroom using Seedance 2.5.
Cinematic photorealistic film still of a young East Asian woman with long straight black hair, cracked round wire-rim glasses, dirty face with orange soup stains, wearing a stained oversized olive green military jacket over a messy white collared shirt and dark clothes, sitting at a rusty wooden desk in an abandoned dilapidated classroom with peeling walls, broken ceiling, chalkboard drawings of schoolgirls behind her, holding a glass laboratory beaker filled with chunky orange tomato soup and greens, melancholic distant expression, looking slightly to the side, golden hour sunlight streaming through torn white fabric hanging over large broken windows, plants growing inside the ruined building, dusty atmospheric haze, shallow depth of field, moody post-apocalyptic survival aesthetic, high detail, 35mm film grain
A detailed prompt for a 30-second 2D hand-drawn Chinese fantasy animation of a monkey swordsman fighting a hydra with specific VFX and choreography.
【全局·画风设定】 顶尖2D手绘国风动画,精致角色立绘级别质感(参考高精度游戏立绘)。线条清晰锐利,色彩饱满通透,光影层次丰富,保留2D动画的丝滑高帧流畅度与夸张形变张力。宏大悬空海崖神战遗迹,巨型断崖悬浮于怒涛狂浪之上,黑云压顶,青色闪电撕裂苍穹,狂风卷起千堆海浪与水雾,断壁残垣与破碎石柱在风雨中若隐若现。可连锁破坏:海崖崩裂→石柱倒塌→神光炸裂→海水冲天,破坏痕迹永久保留。 【全局·角色与对手】 主角:2D精致立绘风。墨黑长发凌乱狂舞,眉眼冷厉睥睨,额间一抹幽蓝水滴神纹,身披暗灰蓝白战损长袍,背负长剑,衣袂随动作剧烈飞扬。动作特征:像猴子一样极度灵活,四肢并用弹射、空中翻滚、贴壁借力、身法诡谲,全速移动化作青金红2D流光残影。 对手(巨型九头蛇):2D手绘巨兽。蛇身如山岳般粗壮,暗黑鳞甲闪烁幽绿毒光,九颗巨大的蛇头如龙颈般修长,赤红竖瞳。受伤系统:被击中会溅出暗绿与暗红的鲜血,鳞甲崩裂,断头处喷涌血液,尸体永久保留在海崖上,最终全灭后蛇身坍塌,砸碎海崖。 【全局·核心规则与铁律】 60fps高帧,2D手绘动画,全程快节奏,无慢镜头/定格/子弹时间。动作密度:高速连击段8-12动作/秒,SSS级仙法段14-18动作/秒。打击感=亮度骤增+镜头急推+冲击波放大+受击方猛飞。伪一镜到底(WHIP/PUSH/DOLLY)。场景破坏永久保留。双方每镜剧烈反击。纯动作流。 【分镜表·30秒·主角2技能+对手2技能·极致灵活猴系身法·受伤见血·尸体保留】 镜头1(t0-1s)MS+贴地平移长镜:0帧起手,主角从画面左侧悬空海崖倒挂跃下,如猿猴般四肢并用在崖壁上疯狂弹射折返,贴地滑铲穿过九头蛇首波撕咬并借力蹬柱,反手横斩砍在蛇颈上溅出暗绿血液,低机位仰拍结合贴地平移跟拍,落地瞬间镜头剧烈震动。 镜头2(t1-3s)MS+高速横移镜:主角如猿猴般在空中连续翻滚、四肢并用在九头蛇九颗头颅的夹击中快节奏钟摆式弹射折返,左突闪避蛇头撕咬反向右突上挑斩击蛇颈,带出青金红2D残影与墨迹爆裂,九头蛇喷吐幽绿毒息并甩动巨尾横扫,高速横移镜贴身跟拍。 镜头3(t3-5s)MCU+极速甩镜:九头蛇发动技能一【九首毒狱】,九颗蛇头同时喷吐幽绿毒息与黑色魔雷形成覆盖全场的毒雷领域,主角如灵猴般在毒雷缝隙中贴壁攀爬、极限翻滚闪避,反手劈、肘击、回旋踢、侧踢四连击串连续命中蛇头,每一击炸开青金红2D墨点与暗绿血雾,极速甩镜从左侧甩到右侧。 镜头4(t5-8s)MS+2D环绕镜:主角旋身掐诀起手技能一【青金红·灵猿踏虚斩】,化作青金红2D残影在九头蛇九头之间疯狂来回穿梭折返,每一次折返都留下猿猴般的身影残影同步挥剑绞杀,蛇颈喷涌暗绿墨血,九头蛇疯狂甩头扑咬反击,2D环绕镜持续跟随极速残影轨迹。 镜头5(t8-10s)FS0.5s→MS:灵猿踏虚斩范围扩大到极致,满屏青金红2D剑气同时爆发横扫大半个画面,九头蛇两颗头颅被斩落,断口喷涌大量暗绿血液,巨兽仰天悲鸣,全景0.5s后极速甩镜回MS。 镜头6(t10-12s)MS+FPV贴背:段间零空场衔接,主角化作青金红2D流光瞬移穿群到九头蛇后方落地横扫,落点炸开环形2D冲击波与青金红泼墨巨浪,九头蛇残存七头同时反扑喷吐黑雷与毒息,FPV贴背跟随,主角立即反向折返突入。 镜头7(t12-15s)MCU+极速推镜:九头蛇发动技能二【万蛇噬天咬】,七颗蛇头同时化作巨大黑影疯狂扑咬合围,主角如猿猴般在蛇头之间弹射借力、空中翻滚折返,旋身掐诀起手技能二【青金红·千机破浪阵】,挥舞长剑凝聚青金红巨大雷电剑气,在蛇头之间疯狂来回突刺,剑气如狂草般贯穿路径上的蛇颈并引发连环爆炸,蛇头喷溅暗绿血液,极速推镜锁定贯穿中心。 镜头8(t15-18s)FPV+贴地平移:千机破浪阵持续扩大,主角在雷电残影中贴地滑铲躲过巨尾横扫、上跃下劈并折返三方位突入,青金红雷电与2D墨点炸裂且海崖地面裂痕永久保留,九头蛇从半空俯冲扑咬,贴地平移+极速甩镜。 镜头9(t18-20s)FS0.5s→MS:千机破浪阵吞没大半个画面,九头蛇再度被斩落三颗头颅,断口喷涌血液如雨,巨兽庞大身躯被雷电贯穿震退,全景0.5s后甩镜回近景。 镜头10(t20-22s)MCU仰拍上摇:段间零空场衔接,主角跃空掐诀,九头蛇残存四头仰天咆哮垂死反扑,喷吐黑雷与毒息试图反杀,主角在天地之间极速来回穿梭,MCU仰拍上摇。 镜头11(t22-26s)FS满屏俯瞰旋转:主角双技能连携爆发,满屏青金红2D神剑与雷电如暴雨般持续轰击九头蛇全身,覆盖全面面,每一道剑光砸落都炸开2D蘑菇云,主角如灵猴般在剑雨之间来回极速穿梭收割,九头蛇庞大身躯被神剑钉在海崖上疯狂挣扎,剩余头颅被逐一斩落,鲜血喷涌,满屏俯瞰旋转。 镜头12(t26-28s)MS+FPV:余波中主角极剑穿梭接回旋斩清残,青金红2D烟尘冲天与三色墨迹丝线密布,九头蛇垂死反扑被瞬间斩碎最后一颗头颅,FPV贴背。 镜头13(t28-29s)MCU+极速甩镜:主角左突右闪钟摆折返,左突斩反向右突挑,带出青金红2D残影与墨迹爆裂且剑影成片,九头蛇无头身躯轰然坍塌砸碎海崖,尸体沉重砸落在废墟之上,极速甩镜。 镜头14(t29-30s)CU尾帧全灭巨兽:主角立于海崖之巅收剑横于身前,满屏青金红2D光爆将九头蛇残躯彻底蒸发为漫天2D粒子与暗绿碎屑,九头蛇庞大尸体永久保留在崩塌的海崖废墟之上,暗绿血液从断颈处持续涌出,画面中再无任何活着的巨兽,主角微微抬头眼神睥睨,CU极速推镜+定格0.3-0.5s,宣告全灭。 【完整负面提示词】 禁止:3D渲染、UE5、Lumen、写实风格、照片写实、欧美卡通、皮克斯风格、塑料感、单色特效、文字、水印、UI、字幕、LOGO、生硬跳切、静止不动、面对面站立对视、招式对撞僵持、血液喷溅失控、断肢、内脏、伤口特写、皮肤撕裂、肢体扭曲、关节反折、手指过多、眼睛变形、角色面部崩坏、特效遮挡面部、镜头穿帮、透视错误、比例失调、人物重叠穿模、动作迟滞、动作凝滞、连击中断、站桩输出、蓄力对峙、摆POSE、收刀入鞘、战斗结束感、喘气休息、全程同一速度、慢动作、慢镜头、定格、暂停、顿帧、hit-stop、bullet time、子弹时间、时间凝滞、长前摇、攻击后停顿、巨兽不再反击、巨兽站着挨打、一方绝对碾压无反击、单方面受击、画面有空旷区域、巨兽静止不动、巨兽不再穿梭补位、巨兽反击敷衍、人体负伤、人体流血、物理切割、贯穿、穿透、超远景EWS、景别拉远、远景、全景打斗、运动拖影、2D特效太稀薄、速度感缺失、命中无爆裂感、攻击无力反馈、受击方无反应、特效不满屏、技能不覆盖大半个画面、释放瞬间画面留有大面积空白、特效只集中在主角身上而非吞没画面、技能名称错误、非战斗段落、台词过多、尾帧没有全灭巨兽、精英怪、魔将、BOSS、小怪、人形魔物、蛇形穿模、雾山五行。
A prompt for generating a 10-second realistic martial arts action scene set inside a Korean subway car with detailed choreography.
Generated video: Generated video: 10-second cinematic video prompt Duration: 10 seconds. Create a photorealistic Hollywood-style martial-arts action scene inside an empty modern Korean-style subway carriage at night. A young East Asian woman with long straight black hair and bangs stands alone, wearing a black leather jacket, dark fitted top, black pants, and heavy black combat boots. Blue seats, stainless-steel poles, hanging hand straps, metallic doors, Korean-style warning signs, and cool fluorescent ceiling lights create a dark blue-gray, tense atmosphere. 0–2s — Tension: Wide establishing shot of the empty carriage. A tall, bald, muscular man in a dark olive-gray military-style jacket walks toward her aggressively. Handheld camera slowly tracks backward as he approaches. She notices him, staying completely calm and focused. 2–4s — Attack: Medium close-up. The man suddenly reaches to grab her arm. She reacts instantly, smoothly blocking his hand and redirecting his momentum. Quick handheld camera movement, realistic body mechanics, natural facial expressions and subtle motion blur. 4–7s — Counterattack: Dynamic sequence of fast, precise martial-arts movements. She delivers controlled strikes to force him backward, maintaining realistic balance and believable physical reactions. Cut between a tight facial close-up, medium action shot, and wide shot showing the subway carriage. 7–9s — Powerful kick: Low-angle cinematic close-up of her heavy black combat boot driving forward into the attacker, pushing him backward with strong but realistic physical impact. His body reacts naturally to the force. Brief dramatic slow-motion emphasis with realistic motion blur. 9–10s — Impact detail: Extreme low-angle close-up of the rugged sole of her black combat boot landing firmly against the subway floor after the kick. The camera briefly follows the boot, capturing subtle floor reflections, dust movement, and realistic weight transfer. Cinematic handheld cinematography, shallow depth of field, dramatic close-ups, wide environmental shots, low-key fluorescent lighting, dark blue-gray color grading, realistic skin texture, individual hair movement, natural expressions, detailed subway materials, realistic physics, grounded martial-arts choreography, strong physical impact, thriller atmosphere, photorealistic, high detail, 4K, 24fps, natural motion. No gore, no weapons, no text, no subtitles, no watermark.
A detailed prompt for creating a realistic early 2000s home video style clip of a Korean woman making a mistake with sauce while cooking.
Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and casual pants. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Small old Seoul apartment kitchen during a dark, rainy early morning. Slightly worn kitchen counter, simple bowl of food, sauce bottle, wooden cabinets, rain-covered window and blurred neighboring apartment buildings outside. Steady rain can be seen through the window. Lighting & Atmosphere: Cozy, dim blue-hour ambience. Cold blue-gray light from the rainy window mixed with a weak warm kitchen light. Muted colors, soft shadows, slightly underexposed interior and a quiet sleepy atmosphere. Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person holding the camcorder. Completely candid and unstaged. Natural handheld shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle low-light digital noise and microphone noise. Smooth continuous real-time motion throughout. No stuttering, judder, frame skipping, duplicated frames, stop-motion appearance, excessive motion blur, speed changes or low-frame-rate look. No stabilization or modern cinematic movement. 00:00–00:04: She stands at the kitchen counter preparing a simple bowl of food. She casually squeezes some sauce over it while looking away for a moment. 00:04–00:07: Far too much sauce suddenly comes out of the bottle. She immediately stops squeezing and stares down at the food in silent disbelief. 00:07–00:10: She slowly tilts the bowl toward herself, inspecting the excessive amount of sauce as if trying to figure out whether it can somehow be saved. 00:10–00:13: She looks toward the camcorder with a helpless, slightly miserable expression, then looks back down at the ruined-looking bowl. 00:13–00:15: She gives a tiny defeated sigh, looks directly into the camera and says in a funny, genuinely confused tone, **“What do I do now?”** She gives a small helpless shrug. Audio: Natural location sound only—steady rain against the window, sauce bottle squeezing, subtle kitchen sounds, refrigerator hum, fabric movement and distant apartment ambience. Her spoken line is natural and quiet. No music, narration or added sound effects. Goal: Cute, spontaneous and lightly comedic, like a tiny everyday mistake accidentally captured on an old family MiniDV camera. Her reaction should be subtle and genuinely confused rather than exaggerated. The spoken **“What do I do now?”** should feel like an impulsive reaction to the mistake, not a scripted performance. Motion quality: Keep every movement smooth, continuous and physically realistic. The sauce should visibly come out too quickly and create a believable mess. Avoid sudden camera movements or exaggerated acting. The vintage MiniDV aesthetic
A highly detailed prompt for generating a 15-second cinematic Chinese Xianxia short film using Seedance 2.0 Mini, including instructions for character consistency and Arri Alexa visual aesthetics.
一、任务目标 生成一段 严格 15 秒、16:9 横屏、电影级写实质感 的中国仙侠短片。 整体风格: 纯古风中国仙侠美学 Arri Alexa 电影机质感 稳定锐利的面部微细节 细腻胶片颗粒 自然体积光 成熟的战术悬念 克制但持续绷紧的情绪力量 依靠误导和潜台词推进的资深编剧式对白 动作设计简单、清楚、可读、真正有武侠身体逻辑 核心反转: 所有人最初都以为剑仙师姐为了逃避决斗,把小师妹推出去挡剑。随着剧情推进,观众才明白,真正被困住的是敌人自己。他花了十年研究怎样击败最有名的白衣剑仙,却从来没有认真看过一直站在她身边、被所有人轻视的小师妹。 模型使用: Seedance 2.0 Mini 二、参考使用规则 人物参考 按上传顺序的 第1张人物参考图 和 第2张人物参考图 作为两名主角的固定身份锚点。 背景参考 本轮新上传的全部环境与地点参考图,共同决定一套新的统一环境 DNA。 正式构图前,先无声重组并统一以下内容: 真实地形 建筑语言 空间尺度 材质 植被 水体 天气 山雾 倒影 主光方向 空气纵深 形成一个本轮独有、完整统一、可信的新空间。 环境总原则 背景始终持续鲜活,但叙事上绝对中立。 持续自然存在并保持连贯的元素包括: 风 水体 山雾 植被 衣料轻微摆动 倒影 远处人物 空间环境声 这些元素只负责建立真实世界感,不主动制造冲突,不帮助任何一方,不决定胜负。 三、角色设定 角色 ID A|剑仙师姐|对应第1张人物参考图 始终保持同一人物,不得变脸、变装、换武器: 25–30 岁东亚女性 椭圆白皙面庞 深色杏眼 黑色长发半挽 白玉簪固定 身材高挑纤细 白色刺绣真丝汉服 银色腰封 玉佩 白色布靴 唯一一柄银色长剑 人物气质: 冷静 克制 权威感强 对局势有更深判断 情绪表达极少,但有分量 角色 ID B|小师妹|对应第2张人物参考图 始终保持同一人物,不得变脸、变装、换武器: 20–25 岁东亚女性 圆润灵动的脸 黑发编辫 身形娇小 青绿色亚麻汉服 深色腰带 木簪 黑色布鞋 唯一一柄深色钢剑 人物气质: 平时容易被低估 反应敏锐 真正动手时简单直接 起初带一点迟疑,后面迅速站稳自己 其他角色 一名真正有实力的敌方剑客 一名年长师父 两名宗门弟子 数名远处见证者 其他角色只负责衬托主线,不夺走情绪中心。 四、镜头结构 镜头 1|0–5s|“她来” 景别与运镜 全景或远景 运镜克制、稳定 用干净方式建立人物站位与空间关系 保持真实视差 画面内容 同一个敌方剑客站在两名女子正前方 同一个年长师父、两名宗门弟子和数名远处见证者只作为次要人物存在 画面清楚建立三方对峙关系 对白与表演 敌人直接喊道: “白衣剑仙,出来。” 同一个师姐站在原地,没有移动,只平静说道: “她来。” 同一个小师妹瞬间转头: “我?” 敌人忍不住冷笑: “拿师妹挡剑?” 表演重点 师姐没有辩解,没有多余动作 小师妹第一反应要自然,短促,带一点意外 敌人语气里有真实的轻视 观众在这一镜必须先被误导,以为师姐真的把她推出去了 镜头 2|5–10s|“所以他只会赢我” 景别与运镜 中景或牛仔景 保持与上一镜完全一致的地理空间 动作与对白都要清楚、易读 对白与表演 小师妹盯着师姐: “你真让我上?” 师姐平静回答: “他拆了我十年剑谱。” 保留半拍停顿。 小师妹压低声音: “所以拿我试?” 直到这时,师姐才真正看向她: “所以他只会赢我。” 现场瞬间安静。 动作设计 紧接着,敌人突然出剑。 敌人使用一套明显经过多年准备、专门克制师姐惯用剑路的成熟反制动作。 小师妹不使用复杂大招,只完成一组简单、快速、清楚的动作: 斜向进步 切进敌人盲区 一次清楚的剑身接触 将敌方兵器拨离中线 动作要求 所有动作必须简单、迅速、物理合理 不能花哨 不能堆招 兵器轨迹必须让观众看得懂 胜负的关键要来自敌人对她完全陌生 镜头 3|10–15s|“一次都没算过她” 景别与运镜 特写或极近特写 表情、停顿、视线关系是核心 保持画面稳定,不做夸张推拉 画面内容 敌人失去重心,单膝落地 主体仍然是三人关系 远处师父和其他人保持浅景深存在感 对白与表演 敌人第一次真正露出错愕: “这是什么剑法?” 小师妹下意识回头看向师姐,像过去一样等待答案。 师姐一句话都不说。 小师妹停顿一下,重新看向敌人: “不知道。” 敌人愣住: “不知道?” 小师妹稳住自己的站姿,只回答: “我刚想的。” 极近特写中,师姐克制的神情终于出现一个极小、真正带骄傲的笑。 敌人越过小师妹看向师姐: “你早算到了?” 师姐直接回答: “没有。” 保留半拍停顿。 随后重新把目光放到小师妹身上,说出最后一句: “但他算了我十年,一次都没算过她。” 表演重点 小师妹说“我刚想的”时,要自然、直接、没有卖弄 师姐最后一句要平静,但极有力量 敌人这一刻才真正意识到自己输在何处 结尾留在人物关系与认知翻转上,不加多余动作 五、视觉与动作控制原则 摄影 电影级写实 Arri Alexa 质感 清晰稳定的面部细节 胶片颗粒克制自然 光线方向稳定 摄影机运动干净、连续、可信 动作 少而准 简单清楚 快速可读 每一个动作都服务剧情反转 不允许复杂炫技 不允许夸张仙法大招 不允许无逻辑剑气 人物调度 师姐始终控制局面,但不抢小师妹的战斗完成权 小师妹从被推出去的错觉中,逐步站成真正的主角 敌人从轻视,到错愕,到彻底理解自己的盲点 师父和弟子只负责衬托,不插手战斗 六、声音设计 原生同步普通话对白。 重点强化以下声音: 剑锋破风声 金属碰撞声 脚步声 衣料声 自然环境声 呼吸声 声音要求: 口型精准 音画同步稳定 动作节点要有明确声音支撑 情绪停顿处要敢留静默 不用过满配乐压住对白和兵器声 七、连续性要求 全程严格保持稳定: 师姐身份稳定 小师妹身份稳定 敌人身份稳定 师父与弟子位置逻辑稳定 人物服装稳定 长剑稳定 地理空间稳定 光线方向稳定 天气稳定 面部不漂移 发型不变化 动作前后因果清楚 八、严格避免 画面问题 blurry bad quality low quality low resolution noisy jpeg artifacts watermark text error out of frame bad composition 人体问题 deformed bad anatomy poorly drawn hands disfigured mutated face morphing inconsistent character changing clothes 连续性问题 background shift glitching cuts disappearing props unstable geography weapon inconsistency 风格问题 随机剑气 光污染 过度特效 软绵绵动作 不可读战
Prompts for generating anime-style scenes depicting a girl skateboarding on a hillside road in a colorful coastal town with ocean views.
A cinematic anime-style scene of a young female traveler skateboarding downhill through a colorful coastal hillside town. She rides smoothly down a winding residential road, carrying a green backpack and orange shoulder bag, while the camera follows behind her in a dynamic tracking shot. Below, a breathtaking turquoise ocean stretches along a curved sandy coastline with white waves crashing against the shore. Colorful houses, utility poles, lush greenery, distant mountains, and enormous fluffy clouds fill the landscape. Strong summer sunlight, vivid blue sky, detailed hand-painted anime aesthetic, subtle wind moving her hair and clothes, realistic skateboard motion, smooth camera movement, atmospheric depth, highly detailed background, adventurous peaceful travel mood, cinematic composition, 9:16 vertical, seamless natural motion.
A complex prompt for generating realistic cinematic videos showing the evolution of weapons from stone tools to orbital rings with strict continuity.
GLOBAL: Photorealistic cinematic 16:9. Each scene directly continues the previous; exact final frame = next Start/Reference Frame. Preserve same subject, position, orientation, motion, lighting, background and camera. ALWAYS SCREEN-LEFT → SCREEN-RIGHT. Never reverse, U-turn, 180° rotate, flip camera, change trajectory, disappear or touch ground. No text/logo/watermark/UI. 1 — CHIMP → STONE: Realistic chimpanzee in ancient dry wilderness at golden hour throws a rough dark stone toward the horizon. Stone stays airborne, travels LEFT → RIGHT slightly upward. Camera tracks it continuously. End with stone visible near RIGHT. Exact frame → 2. 2 — STONE → ARROW: Same stone, same frame and motion. While flying LEFT → RIGHT, it physically cracks and transforms into a wooden arrow: arrowhead RIGHT, feathers LEFT. Background smoothly becomes early historical/archery era. End with complete arrow. Exact frame → 3. 3 — ARROW → BULLET: Same arrow continues LEFT → RIGHT and progressively becomes a realistic metallic firearm bullet: shaft → body, arrowhead → FRONT/RIGHT, feathers → REAR/LEFT. Background smoothly becomes early-modern industrial/firearm era. End with bullet. Exact frame → 4. 4 — BULLET → MISSILE: Same bullet continues LEFT → RIGHT and physically becomes a realistic military missile: body lengthens, nose RIGHT, fins and rocket engine REAR/LEFT. Background smoothly becomes modern industrial/military. End with missile. Exact frame → 5. 5 — MISSILE → FIGHTER JET: Same missile continues LEFT → RIGHT and transforms into an advanced realistic fighter jet: fuselage expands, wings unfold, cockpit RIGHT, stabilizers/engines LEFT. Background smoothly becomes modern high-altitude aviation. End above Earth with atmosphere visible. Exact frame → 6. 6 — FIGHTER JET → ORBITAL RING: Same jet continues LEFT → RIGHT and progressively transforms into a gigantic futuristic orbital ring: wings curve into rings, fuselage expands into connected sections, concentric rings form. No replacement spaceship. Background becomes advanced near-space technology with Earth below. End with ring moving LEFT → RIGHT. Exact frame → 7. 7 — ORBITAL RING → ENERGY SPHERE: Same ring continues LEFT → RIGHT. Rings rotate; blue-white energy flows inward as the structure contracts into one brilliant energy sphere. Background becomes deep futuristic space, Earth distant. Sphere keeps LEFT → RIGHT. Exact frame → 8. 8 — SPHERE → POINT OF LIGHT: Same sphere continues LEFT → RIGHT, compresses into a tiny brilliant point and accelerates toward RIGHT with subtle light trail. Camera pulls back to reveal deep-black star field. Point becomes smaller and fades into distance. No reversal, U-turn or explosion. NEGATIVE: new/different object, replacement, sudden cut/morph, background or lighting jump, right-to-left, reverse, backward, U-turn, 180° rotation, camera flip, traje
A complex character and scene generation prompt depicting two middle-aged men in gaudy K-Pop suits taking photos with fans on stage.
Two middle aged men (early 50’s, one ultra skinny and bald the other dad bod with head of blonde hair). Dressed up in K-Pop clothing (tacky fancy suits) above them the letters: OSNTA make it look like we are posing on stage lots a fans in audience....
A detailed prompt for generating a 3D cartoon cooking comedy video showing a young chef making an omelet with character consistency.
Create a 30-second original 3D cartoon cooking comedy. A cute young chef attempts to make an omelet in a cozy home kitchen. VISUAL STYLE: Original stylized 3D cartoon, rounded shapes, expressive face, simple appealing character design, colorful kitchen, soft lighting, clean textures. Do not imitate any existing animation studio, movie, game, or character. CHARACTER: Young chef with short dark hair, white chef coat, red neckerchief, and white chef hat. Keep the same character throughout. 0–4s: She cracks eggs into a bowl. One small eggshell falls in. She carefully removes it. 4–8s: She whisks the eggs too enthusiastically. A little egg splashes onto her cheek. She wipes it off and keeps whisking. 8–12s: She adds chopped vegetables and pours the mixture into a hot frying pan. The omelet starts cooking. 12–16s: She tries to loosen it with a spatula, but it sticks. She carefully scrapes around the edges and adds a little oil. 16–20s: She tries to fold the omelet. It tears slightly. She looks worried and covers the damaged area with shredded cheese. 20–25s: The cheese melts. She carefully folds the omelet again and successfully forms it into one piece. 25–30s: She slides the omelet onto a plate, adds a small garnish, proudly admires it, then takes a bite and smiles. Keep every action continuous and physically logical. Objects remain consistent between shots. No teleporting, sudden object changes, impossible movements, dialogue, subtitles, text, logos, existing characters, or references to copyrighted franchises. Include natural cooking sounds such as egg cracking, whisking, sizzling, scraping, and
A prompt for creating a cute 3D animated video showing a heartwarming scene of two chicks reconciling in a sunny garden after a spat.
Create a cute, heartwarming, ultra-realistic 3D animated video in a cinematic family-friendly style. A peaceful, sunlit garden path surrounded by lush green plants, tiny white and purple flowers, and a rustic wooden fence in the background. Warm golden-hour sunlight creates soft highlights and natural shadows. The environment feels cozy, magical, and wholesome. CHARACTERS: Two adorable fluffy yellow baby chicks with soft detailed feathers, tiny orange beaks and feet, expressive oversized eyes, and highly detailed facial expressions. The chick on the left is slightly taller and has small feather tufts on its head. The chick on the right is smaller, with two cute little feather puffs resembling tiny pigtails. Both characters have expressive eyebrows and subtle rosy cheeks. ACTION: The two chicks stand together on the garden path, initially looking annoyed at each other. The smaller chick crosses its wings and gives an angry, stubborn expression while the taller chick looks at it with curiosity. The taller chick then walks around and interacts playfully with the smaller chick. Their expressions gradually change from irritation and stubbornness to surprise and affection. By the end, the two chicks become friendly again. They stand close together, exchange a warm affectionate look, and happily walk side-by-side while smiling. ANIMATION: Natural, smooth character movement with believable walking, tiny head movements, blinking, subtle feather motion, expressive eyes, wing gestures, and adorable comedic timing. Emphasize the emotional progression from annoyance to reconciliation. CAMERA: Vertical 9:16 composition. Cinematic medium shots and gentle close-ups. Slow, subtle camera movement with a shallow depth of field. Keep both chicks clearly visible and centered throughout the scene. VISUAL STYLE: High-end cinematic 3D animation, photorealistic fluffy feathers, detailed eyes, realistic soft lighting, beautiful depth of field, natural environmental textures, warm color grading, soft bokeh, polished movie-quality rendering. MOOD: Cute, funny, emotional, wholesome, playful, and heartwarming. QUALITY: Ultra-detailed, cinematic, smooth motion, physically believable animation, realistic feather physics, expressive facial animation, 4K quality, clean composition, no text, no watermark.
A prompt for creating cinematic dark fantasy battle scenes, depicting a lone warrior using fire magic and shockwaves to repel shadow creatures.
Cinematic dark fantasy wuxia battle, captured from a dramatic low-angle tracking shot. A lone male warrior dressed in black martial robes and protective arm guards stands in a vast field of tall grass beneath a gloomy, overcast sky. He spins with precision, swinging a blazing sword that creates brilliant orange fire trails and showers of sparks. A huge swarm of dark shadow creatures rushes toward him. With a powerful strike, he unleashes a devastating ground shockwave, sending dirt, smoke, and glowing embers flying through the air. A circular grid of red targeting markers and energy beams rapidly expands toward the approaching creatures. The warrior calmly places his burning sword over his shoulder and walks forward in slow motion as embers drift around him, smoke fades, and black ash dissolves into the air. Photorealistic VFX, cinematic motion blur, ultra-detailed visuals, 8K quality.
Prompts for generating viral videos featuring a stationary woman in white contrasting with a synchronized dancing crowd behind her.
Use the uploaded image as the exact visual reference for the characters, wardrobe, composition, lighting, and overall cinematic look. Create a photorealistic live-action video, A young woman wearing a long, fully closed ivory-white tailored coat, black sunglasses, and black pointed heels walks slowly and confidently straight toward the large crowd. Her posture is elegant and controlled, her arms relaxed naturally at her sides, and her expression remains serious and calm. Start with a medium-wide frontal shot. The woman walks directly toward the camera and toward the center of the crowd. The camera smoothly tracks backward at the same pace, keeping her perfectly centered. The crowd remains completely still, watching forward. She reaches the front-center position of the crowd and comes to a complete stop. Her feet settle naturally, arms remain at her sides, shoulders relaxed. She looks directly into the camera through her black sunglasses. The woman remains 100% completely still. Then, precisely behind her, the entire crowd suddenly begins moving in perfect synchronized rhythm. Their movement should be sharp and unsettling: heads jerk quickly to one side shoulders snap upward upper bodies briefly lean forward they suddenly snap upright again repeat the movement together like a perfectly synchronized group The movement happens across the entire crowd, from the closest people to the deepest background rows. The woman does absolutely nothing. No head movement. No body movement. No hand movement. No walking. No reaction. She simply stands motionless while everyone behind her moves aggressively in synchronization. The camera slowly pushes closer toward the woman while the crowd continues its synchronized movements behind her. Keep her face and white coat sharply focused while the moving crowd has subtle cinematic depth-of-field blur. End with a powerful centered close/medium shot. The woman is completely motionless in the foreground while the crowd performs one final synchronized head-and-shoulder snap behind her. Hold on her still expression for the final moment. Visual Direction Dark, cold, high-end cinematic fashion aesthetic. Raw concrete environment, deep shadows, soft overhead lighting, realistic skin and fabric, natural hair physics, realistic human movement. The central visual contrast is extremely important: ONE perfectly still woman in white + a large crowd in black moving violently in perfect synchronization behind her. No duplicate lead. No additional white outfits. No men. No cartoon or animation. No CGI appearance. No exaggerated camera shake. No text. No subtitles. No logos. No sudden scene changes. No extra characters appearing or disappearing.
A detailed prompt for Seedance 2.0 Mini to generate a 15-second comedic Chinese Xianxia short film about a generational hierarchy realization during a duel.
Seedance 2.0 Mini|15 秒仙侠短片提示词 项目目标 生成一段 严格 15 秒、16:9 横屏 的电影级写实中国仙侠短片。 整体风格要求: 电影级写实质感 纯古风中国仙侠美学 史诗级挑战者登场镜头语法 冷面喜剧 默片式反应节奏 港式动作喜剧的利落效率 经典三拍递进结构 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 原生同步普通话对白 不生成字幕 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: 一名年轻敌方剑客气势汹汹前来挑战剑仙师姐,本以为马上会开始一场传奇决斗。 结果通过他自己报出的师承关系,现场突然发现: 按照武林辈分,他居然比剑仙师姐低一辈。 于是,原本严肃的生死挑战,瞬间变成一场极其尴尬的 认亲式武林礼数现场。 笑点只能来自: 身份地位反转 纯古风武林礼法 一本正经地执行辈分规则 绝不能依赖: 随机环境事故 低级出丑 夸张胡闹表演 参考图绑定 人物身份锚点 @图片 1 对应 剑仙师姐 始终保持: 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 白玉簪固定 同一套白色刺绣真丝汉服 银色腰封 玉佩 白色布靴 唯一一柄银色长剑 @图片 2 对应 小师妹 始终保持: 20–25 岁东亚女性 身形娇小 圆润灵动的脸 黑发编辫 同一套青绿色亚麻汉服 深色腰带 木簪 黑色布鞋 唯一一柄深色钢剑 背景与空间 本轮新上传的全部背景与地点参考图,共同决定 同一套环境 DNA。 生成前先无声整合: 真实地形 建筑语言 材质年代感 空间尺度 植被 水体 天气 山雾 主光方向 反光关系 空气纵深 真实可行走路线 重新规划为一个 完整统一、真实可信的新空间。 环境规则 背景中的以下元素持续自然鲜活: 自然风 水体 植被 云层 远处普通弟子 空间环境声 但在叙事上必须 绝对中立,不能主动制造包袱,也不能帮忙推动笑点。 镜头结构 0–5s|第一镜|挑战登场 景别 全景或远景 画面 同一个剑仙师姐与同一个小师妹站在根据本轮参考图自然形成的开放区域中。 一名年轻敌方剑客大步进入画面,猛然拔剑,气势十足地宣布: “剑仙!我奉师命来败你!” 同一个白衣剑仙完全没有紧张,只平静问: “你师父是谁?” 敌人极其骄傲地回答: “赵无尘!” 要求 这一镜要先成立真正史诗级挑战感 敌人的登场必须认真,不搞笑 剑仙师姐的平静要形成第一次反差 空间关系清楚,人物站位稳定 5–10s|第二镜|辈分反转 景别 中景或牛仔景 画面 保持同样人物、同样服装、同样长剑和完全一致的地理空间。 一直在两人数步后方自然坐着的同一个年长师父,像听见熟人名字一样,随意抬起眼睛,平静说道: “小赵啊,我教过他三年。” 全场安静。 同一个敌人非常缓慢地转头看向师父,脸上的气势第一次开始松动。 同一个小师妹立刻认真推算辈分关系,然后一本正经地说道: “那你得叫师姐…… 师姑。” 敌人整个身体当场僵住,难以置信地重复: “师姑?” 同一个剑仙师姐从头到尾保持绝对端庄严肃。 要求 这一镜的包袱要清楚落地 “师姑”必须成为整个喜剧的第一次真正爆点 师父口气越平常越好 小师妹必须不是取笑,而是认真推算辈分 敌人的气势要真实塌第一层 10–15s|第三镜|礼数先行 景别 特写或极近特写 画面 同一个敌人手中的长剑已经不自觉降低一点,却仍试图维持挑战者尊严: “我今日是来挑战的。” 同一个年长师父完全一本正经回答: “挑战归挑战,辈分不能乱。” 同一个小师妹极其认真地点头补一句: “先叫人。” 完整留出一个让敌人极其痛苦的半拍停顿。 敌人几次想开口,最终只能非常小声地挤出一句: “…… 师姑。” 同一个白衣剑仙极其端庄地点一下头,只回答一个字: “乖。” 同一个小师妹瞬间把脸转向另一侧,肩膀极轻微颤动,拼命忍住笑。 敌人脸已经快挂不住,却仍然重新举起自己的剑: “现在能打了吧?” 同一个剑仙师姐平静地将银色长剑从剑鞘中拔出大约半寸,眼神终于进入真正高手状态,却依旧不紧不慢地回答: “可以,师侄。” 敌人的表情再次当场垮掉。 在这个第二次精神受创的表情上精准切黑。 要求 “乖” 是第二个明显笑点 “可以,师侄” 是最后回马枪 师姐必须始终端庄严肃,不能故意耍人 小师妹要强忍笑,但不能抢戏 敌人不能演成蠢,只能演成被礼法困住 表演要求 剑仙师姐 全程冷静 全程端庄 不戏弄人 像真的在遵守武林礼数 最后半拔剑时,真正高手气场要明显成立 小师妹 负责认真推导辈分关系 喜剧感来自过分认真 不是插科打诨 忍笑必须克制 年长师父 一本正经 语气越平常越好 像只是在纠正一件再正常不过的礼数问题 年轻敌方剑客 前半段必须真的是气势汹汹的挑战者 被辈分反转时,气势一点点塌掉 不能演成傻子 笑点来自尊严被礼数架住 摄影与声音要求 3 个连续清晰镜头 总时长严格 15 秒 16:9 横屏 原生同步普通话对白 精准口型 明确喜剧停顿 前景、中景、远景保持真实视差 空间环境声真实存在 真丝衣料和头发物理效果自然 镜头克制稳定,不炫技 声音重点 拔剑声清楚 环境风声、水声、远处空间声自然 关键停顿要让对白落得住 “师姑” “乖” “师侄” 这三个词必须成为明确节拍点 连续性要求 必须全程稳定: 人物身份 发型 面部 服装 长剑 师父位置 地理空间 视线关系 光线方向 背景结构 避免项 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 夸张搞怪表情 低级恶搞 环境事故包袱 随机插科打诨 字幕
A prompt for generating a cute 3D animation video showing playful interactions between two rabbits on a sofa with Pixar-style visuals.
Create a cute, heartwarming, ultra-realistic 3D animated video featuring two adorable fluffy rabbits sitting together on a cozy beige sofa in a warm modern living room. One rabbit wears a blue shirt and a small golden bunny necklace, while the other is soft pink with a large pink bow and a heart-shaped necklace. The pink rabbit applies lipstick while making funny, confident expressions. She then playfully interacts with the other rabbit, who has pink lipstick kiss marks all over its face and ears. They cuddle, laugh, and playfully tumble together on the sofa. At one point, they hide under a soft beige blanket decorated with pink lipstick kiss marks, then pop back out laughing and hugging each other. Warm golden lighting, cozy home interior, soft cushions, wooden furniture, plants and framed artwork in the background, expressive faces, detailed fluffy fur, cinematic camera movement, shallow depth of field, adorable comedic atmosphere, polished Pixar-style 3D animation, highly detailed, smooth natural motion, 4K quality.
A text-to-video prompt depicting a cinematic battle between a mountain warrior and a giant organic creature in a stormy highland setting.
CHARACTER REGISTRY: Exactly one adult male mountain warrior. He has a compact, broad and extremely powerful build. He wears an original dark gunmetal suit of medieval fantasy plate armor: enclosed pointed helmet, layered shoulder plates, articulated arm protection, heavy gauntlets, reinforced breastplate, leather waist panels, dark trousers, steel greaves and heavy armored boots. His armor is weathered, scratched and wet from the storm. He carries exactly one enormous two-handed warhammer. It has one long reinforced dark-metal shaft and one heavy symmetrical rectangular hammer head. The weapon remains the same length, shape and weight throughout. He controls it with both hands during jumps, climbing and striking. Exactly one colossal organic humanoid giant, more than thirty times the warrior’s height. It has immense muscular shoulders, extremely long arms, huge humanlike hands, coarse charcoal-gray skin, visible pores and scars, a heavy brow, broad nose, powerful jaw and long tangled black hair. It is an organic living titan—not a statue, robot, machine or stone golem. No additional warriors, giants or background armies. ENVIRONMENT: A windswept highland battlefield beneath a violent blue-gray thunderstorm. The uneven ground is covered with dark wet soil, flattened grass and thousands of small pale flowers. Strong wind bends the grass and flowers in irregular waves. A ruined medieval fortress stands on a distant hill at screen-left. Broken towers remain visible through low drifting fog. Lightning intermittently illuminates the fortress and storm clouds. The giant occupies the battlefield’s screen-right side. The warrior begins in the center foreground, running toward the giant. Preserve this geography and screen direction throughout every cut. CHRONOLOGICAL ACTION AND CAMERA: 0.00–3.30 — CHARGE TOWARD THE GIANT Begin immediately with a low rear tracking shot, close behind the armored warrior as he runs powerfully through the wet field toward the colossal giant. He carries the warhammer horizontally across his body with both hands. The heavy hammer head remains toward screen-right while the lower shaft extends toward screen-left. His boots compress the wet ground with every step, throwing soil, crushed flowers and droplets backward only after physical contact. The giant’s legs and enormous right hand enter from the upper-right side of the frame. The giant bends down and extends its open hand toward the charging warrior, intending to scoop him from the ground. The fingers move independently with believable joints and weight. The giant does not instantly grab or teleport the warrior. Camera movement remains low, fast and smooth, emphasizing the extreme difference in scale. The ruined fortress stays visible on the distant screen-left horizon. 3.30–5.80 — LEAP ONTO THE GIANT’S HAND As the giant’s open hand sweeps low across the warrior’s path, the warrior plants his right boot firmly into the ground. His knee compresses, hips lower and rear leg drives upward. He performs one powerful forward jump. Use controlled cinematic slow motion as he rises in front of the giant’s separated fingers. His legs tuck slightly beneath him while both hands raise the same warhammer above his shoulders for balance. The warrior lands with both boots on the back of the giant’s middle and ring fingers. Show clear physical contact: boots touch skin, knees absorb impact, the giant’s flesh compresses slightly and the warrior’s armor reacts to the landing. The giant begins lifting its hand toward its face. The warrior does not float or hang in empty air. Use a dramatic low-angle crane that travels upward beneath the warrior, with the enormous hand filling the background. 5.80–9.00 — RUNNING UP THE ARM Return to fast natural action. As the giant raises its arm, the warrior runs from the fingers across the back of the hand and onto the wrist. His footfalls alternate correctly and visibly grip the uneven moving surface. The giant rotates its wrist and attempts to shake him loose. The warrior lowers his center of gravity, widens his stance and keeps the hammer close to his torso until the arm stabilizes. He then accelerates along the giant’s forearm toward the elbow. Each step follows the arm’s changing angle; his boots do not slide through the skin. Camera tracks beside and slightly below him, rising along the length of the giant’s arm. Near parts of the arm cross the foreground quickly while the giant’s head and distant fortress move more slowly, creating powerful parallax and scale. 9.00–12.00 — CLIMB TO THE SHOULDER The warrior reaches the upper arm as it rises steeply toward the giant’s shoulder. He hooks one forearm and the warhammer shaft against a natural ridge of muscle for leverage, plants his right boot, pushes through his leg and pulls himself onto the shoulder in one connected climbing action. The giant turns its head toward him. Its eye tracks the warrior, its brow tightens and its jaw opens in a deep nonverbal roar. Hair and skin move from the rotation of its head. The warrior remains attached to the shoulder through real hand and boot contact. He climbs diagonally across the upper shoulder toward the base of the giant’s neck. Use a close side-tracking shot that keeps the complete warrior, warhammer and giant’s facial profile readable in the same frame. 12.00–15.00 — FULL HAMMER STRIKE TO THE JAW The warrior reaches a stable position on the giant’s sloped shoulder near its neck. He plants his left boot forward and braces his right boot behind it. Both feet visibly press against the giant’s skin. He rotates his hips away from the target and draws the warhammer backward with both hands. Show the complete preparation before impact: feet plant → knees compress → hips load → torso rotates → shoulders draw the hammer backward → arms guide the heavy hammer head into its starting position. At 13.00 seconds, the warrior releases one complete horizontal two-handed swing toward the giant’s jaw. The power travels continuously from his legs through his hips, torso, shoulders and arms. The hammer head follows one clear uninterrupted arc. It does not jump positions or touch the face before the swing is complete. At 14.00 seconds, enter explicit ultra slow motion for the decisive contact. The rectangular hammer head strikes the side of the giant’s lower jaw with its broad striking face—not the shaft or handle. Show skin and cheek tissue compressing around the impact, the giant’s jaw shifting sideways, loose hair whipping outward and a radial burst of rain, dust and skin debris. The warrior’s arms resist the sudden deceleration. His shoulders recoil while his body continues through a controlled follow-through. No blood, exposed tissue, gore or dismemberment. 15.00–17.30 — GIANT RECOIL AND WARRIOR FALL Return immediately to natural speed. The giant’s head snaps sideways from the impact. Its upper body recoils and the struck shoulder drops sharply. This sudden downward movement removes the warrior’s footing and throws him away from the giant. The warrior falls toward the battlefield while retaining the same warhammer with both hands. He does not float or perform an additional jump. Cut to a ground-level side view. His boots contact first, his knees collapse under the momentum and he rolls once across one shoulder. The hammer head strikes the soil beside him and digs a shallow trench, throwing wet earth and pale flowers outward. The giant’s huge face descends into the upper-right portion of the frame as it struggles to regain balance. It does not crush or intersect the warrior. 17.30–20.00 — RECOVERY AND FINAL STANDOFF The warrior stops his roll in a low kneeling position. He plants the warhammer head into the soil, grips the shaft with both hands and uses it as support to rise steadily to one knee. He then pulls the hammer free and
A detailed prompt for generating a 15-second cinematic martial arts fight video, including specific camera angles, character consistency, and physics-based choreography.
一、核心定位 生成一段 严格 15 秒、16:9 横屏、24fps、电影级写实质感 的中国仙侠硬派战斗短片。 整体风格: 纯古风中国仙侠硬派战斗美学 高张力、强节奏、空间关系极清楚 突然爆发、猛烈撞击、瞬间刹停 观众只能在瞬间捕捉动作,但始终不会丢失方位 吸收胡金铨武侠的空间与剪辑精髓,但不复刻任何具体电影 Arri Alexa 电影机质感 稳定锐利的面部微细节 细腻胶片颗粒 自然体积光 真实运动模糊 克制特效,禁止光污染 这支短片的核心爽点来自: 长兵器对短兵器的距离压制 戟的“直刺、勾挂、控线、身体撞击”多功能威胁 师姐前两次被压制 第三段通过顺势借力、主动抢近、拆解戟头有效攻击轴线完成反制 高速切镜中仍然清楚可读的地理方位与兵器归属 禁止把战斗拍成: 软绵绵的舞蹈套招 特效堆砌 随机瞬移 看不懂方位的乱打 机械碎切 二、人物身份锚点 按上传顺序的 第1张人物参考图 与 第2张人物参考图 锁定人物身份。 角色 ID A|第1张人物参考图|剑仙师姐 始终保持同一个人物: 东亚女性,25–30 岁 椭圆脸 白皙自然肤色 深色杏眼 黑色长发半挽 白玉簪固定 高挑纤细体型 同一套白色刺绣真丝汉服 半透明分层宽袖 银色腰封 玉佩 白色布靴 唯一一柄银色直剑 剑鞘全程保留且可参与动作 人物气质: 冷静 判断极快 动作干净 不炫技 每一次变化都带明确战术目的 角色 ID B|第2张人物参考图|小师妹 始终保持同一个人物: 东亚女性,20–25 岁 圆润灵动的脸 黑发编辫 娇小体型 同一套青绿色亚麻汉服 深色腰带 木簪 黑色布鞋 唯一一柄深色钢剑 人物功能: 全程不加入搏斗 远处见证 被战局震住 结尾只克制地呼出一口气,不追加解释性台词 角色 ID C|敌方戟手 同一个成年东亚男性 穿深铁灰色古风武服 老练、稳定、反应快 明显具有实战经验 会判断、会学习、会临场修正 前两段确实压住师姐 不是站桩送招的工具人 角色 ID D|年长师父 同一个年长师父 始终在远处作为见证者 全程不出手 只在结尾平静说一句点评 三、敌方兵器设计|长柄戟 敌方武器是一柄 经过电影化设计、但建立在古代戟基本结构上的长柄戟。 必须保留以下特征: 前方尖锋 侧向枝刃 长柄结构明确 可直刺 可横勾 可控制对手兵器线路 可利用长柄进行短促、沉重的身体撞击 表现重点: 第一段 用前尖直刺建立长兵距离威胁 第一段后半 用侧枝勾入银剑线路,将师姐剑路拖开 第一段结尾 利用长柄高度和重量做近距离撞击 第二段 连续完成直刺、低位勾挂、反向撞击、近身控线 第二段结尾 戟侧枝勾住师姐故意递出的剑鞘口 第三段 师姐顺着这次“勾住”反向借力,拆掉戟头有效轴线 全片只此一柄戟,设计、尺寸、方向、持握方式全程稳定。 四、环境 DNA 本轮新上传的全部背景与地点参考图,只作为 背景与地点参考 使用。 正式构图前,先无声整合彼此兼容的: 真实地形 建筑语言 空间尺度 材质年代 植被 水体 天气 山雾 主光方向 反射关系 空气纵深 合理战斗路线 重新组合成本轮独有、但与全部参考图统一可信的新空间。 环境规则 必须保持: 地点真实 空间可走通 战斗路线合理 主光方向稳定 地理关系稳定 前景、中景、远景层次清楚 背景始终自然鲜活: 风持续吹动衣摆、发丝、植被 水体自然流动 山雾缓慢游移 倒影与湿面反光微小变化 远景人物轻微自然活动 背景始终叙事中立: 不主动制造机会 不突然塌陷或绊倒人 不帮任何一方遮挡 不决定胜负 只有当人物真正: 踩踏 碰撞 擦过环境 带动地面或器物 局部才出现: 扬尘 水纹 碎屑 枝叶位移 衣料被动甩动 五、镜头总原则 整体镜头语言 0–5s、5–10s、10–15s 三个明确叙事段落 全片约 6–7 个真正有功能的内部切镜 每次切镜只能由以下原因触发: 真实撞击 运动方向突然反转 兵器遮挡镜头 身体失衡 戟头或剑身大幅掠过镜前 禁止: 机械平均切镜 毫无原因碎切 全程手持乱晃 炫技式环绕 过度慢动作 快速飞行镜头 游戏化镜头 运动原则 动作必须具备: 明确重量 明确惯性 明确启动 明确撞击 明确刹停 每次爆发后都允许极短静默,让危险感落地。 六、15秒三段战斗结构 Shot 1|0–5s|长戟先手压制 景别与摄影 全景 / 远景 0.0–1.0s 使用 24mm 固定大全景 清楚交代双方距离、方向、退路 小师妹与师父在远处,可见但不抢戏 画面内容 同一个白衣剑仙师姐站在前方。 正前方只有一名同一个深铁灰戟手。 同一个青衣小师妹与同一个年长师父留在远处作为见证者。 0.0–1.0s 所有人静止,形成压迫。 随后敌人毫无预警,沿中线突然直刺。 立刻硬切低机位 28mm,让戟尖贴着摄影机前景猛烈穿过。 同一个白衣剑仙在最后时刻以爆发式斜步擦锋避开。 但敌人完全不停。 戟的侧枝立即横向勾入她银剑的运动线路,强行把剑路拖开。 紧接着,敌人利用长柄完成一次极短、极重的身体撞击,把她整个身体硬生生撞偏一个完整身位。 双方骤然刹停。 不摆姿势。 不做多余表演。 本段目标 让观众明确知道: 敌人很强 戟的威胁是真实的 师姐前一段没有占到便宜 空间关系完全看得懂 Shot 2|5–10s|戟锁再压,师姐埋伏反制条件 景别与摄影 中景 / 牛仔景 35mm 近距离摄影 尽量保留一整段连续压迫 不疯狂碎切 动作内容 保持: 同一个白衣剑仙 同一个戟手 同一柄银剑 同一柄长戟 完全连续的空间关系 敌人继续连续施压: 上路直刺 回收戟身转成低位勾挂 立即利用长柄反向撞击 师姐第一次突然暴抢近身。 敌人已读懂她的战术。 他马上缩短握距,把原本的长兵器变成更紧凑的近身控制,再次封死她的进入位置,证明他会判断、会适应。 随后敌人再次发动熟练的侧枝勾锁。 这一次,师姐没有把银剑送进去。 她故意把 空剑鞘 递到攻击线路上。 戟的侧枝准确勾住剑鞘口。 完整保留极短半拍。 敌人误以为自己第二次成功控制她,立刻猛烈回拉。 本段目标 完成第三段反制的必要前提: 敌人相信自己重新锁住了她 戟与剑鞘发生明确勾挂关系 师姐已经主动把“借力顺势”的条件准备好 Shot 3|10–15s|顺势借力,抢近封喉 景别与摄影 特写 / 极近特写起步 动作完成后进入 50mm 冲击镜头 最终落到 85mm 极近特写 动作内容 同一个白衣剑仙完全不与敌人这股回拉力量正面对抗。 她反而顺势爆发前冲。 在向敌人抢近身位的同时,旋转被勾住的剑鞘,让剑鞘围绕戟的侧枝改变角度。 这个动作要清楚可读: 她不是蛮力夺戟 她是在改变戟头的有效攻击轴线 让整枚戟头暂时失去继续直刺与横勾的空间 长柄扫满整个镜头,形成一次天然兵器遮挡切镜。 下一镜 50mm 冲击镜头 中: 她已经贴入敌人近身距离, 以肩部一次短促、猛烈的撞击,打散对方身体轴线。 与此同时,同一柄银色直剑始终自由掌握在另一只手中。 她顺着敌人失衡方向贴着前肩旋身越过。 银剑没有花哨旋转。 直接完成一次极短前送
A cinematic video prompt showing a small bear interacting with and driving a vintage car in a rural setting.
Created a video in a cinematic, ultra-realistic storytelling style: a cute brown bear cub walks across a peaceful countryside farm toward an old vintage blue car parked near a rustic wooden barn. The bear curiously approaches the car, climbs inside, and naturally sits in the driver’s seat with its paws on the steering wheel. The camera captures close-up details of the bear’s realistic fur, expressive eyes, tiny paws, and the aged interior of the classic car. The car then starts moving slowly along a wet rural road, creating subtle reflections and natural motion. Wide cinematic shots reveal green fields, hay bales, a small farmhouse, and warm golden-hour sunlight in the background. Use smooth camera movements, realistic depth of field, soft lens flare, natural shadows, detailed textures, and authentic environmental lighting. The overall mood should feel charming, adventurous, cinematic, and slightly playful, with realistic animal movement and believable interaction with the car, filmed like a high-budget wildlife movie.
A detailed visual prompt describing a young woman wearing exquisite Gothic attire with red eyes and a bow.
A young woman with long, flowing black hair adorned with a large red bow, wearing an elaborate black and red gothic dress with puffed sleeves, lace-up corset, and ruffled skirt. She has a gentle smile, red eyes, and fair skin, standing with her hands...
先选择与目标相符的示例,清楚描述主体和预期结果,再补充视频生成所需的构图、镜头、光线、音频、运动或版式细节。生成前请替换产品、品牌、参考素材和对白变量。
打开卡片,对照预览与原始写法,再将原始 Prompt 复制到 Topview AI 或兼容的生成器中。请根据项目调整参考素材、限制条件和风格说明。
请将每条提示词视为经过展示的示例或起点,而不是结果保证。应根据所选模型检查品牌准确性、版权、安全性和生成能力。
可以。媒体主页会链接到独立分类页;每个分类页只保留一种分类条件,使示例范围和搜索意图更加清晰。
当前提示词库包含 Seedance 2.5, Seedance 2.0, Wan 3.0, GPT Image 2, Nano Banana Pro, Gemini Omni, Grok Imagine 的示例,具体可用内容会随媒体类型和筛选条件变化。
当前浏览“Cinematic Showcase”用途分类下的视频提示词。