Fast Cinematic Transition Challenge
A prompt for creating fast-paced videos with Seedance 2.5, featuring seamless transitions between six reference images.
Bu sayfa “Sports Action” olarak sınıflandırılan Video prompt örneklerini toplar. Bir örneği projenize uyarlamadan önce sonucu, kompozisyonu veya çekimleri ve özgün ifadeyi karşılaştırın.
1,544 prompts
Konular
A prompt for creating fast-paced videos with Seedance 2.5, featuring seamless transitions between six reference images.
Create a fast-paced cinematic transition video using Image1 → Image2 → Image3 → Image4 → Image5 → Image6. Start with the character in Image1 swinging a badminton racket from left to right. Background people move quickly, leaving motion silhouettes. As the swing completes, transition to Image2 by matching the character’s cane position with the final racket position. The Image2 character turns around. Push the camera toward her neck as her flying hair covers the lens, transitioning seamlessly into Image3. In Image3, pull the camera back. A male butler in a suit and white gloves enters from the right and offers the woman a half-filled red wine glass. She takes it and brings the glass toward the camera until it completely covers the frame. Use the wine glass occlusion to transition into Image4. The woman pulls the glass toward herself, then quickly extends it toward the front-right. Match the glass with the prop in Image5 for another rapid transition. In Image5, the woman lowers the gun, turns backward and leans against the rooftop, looking toward the camera. Quickly push into an extreme close-up of her eyes. She gives a subtle wink. Pull the camera back and transition into Image6, ending on a close-up of the woman. Keep the pacing fast, cinematic and seamless, with natural camera shake, strong motion, precise match cuts, consistent characters and props, and energetic BGM synchronized with the transitions.
A detailed text-to-video prompt for Seedance 2.5 to generate a 15-second cinematic fight scene featuring a super-fast elderly Japanese woman against multiple men.
15秒、4:3、実写フォトリアル。日本を舞台にしたシネマティックで真剣な高速格闘シーン。コミカルな演技やバラエティ的な演出にはしない。本気の映画アクションとして描く。ただし、戦闘技として突然「高速キッス」が何度も挟まる。この高速キッスだけが異様な要素だが、登場人物自身は一切ふざけず、必殺技の一種のように扱う。 映像は35mm映画フィルムのような質感。自然なフィルムグレイン、わずかなハレーション、柔らかなハイライト、深い黒、落ち着いた自然な色調、微細なレンズフレア、映画用レンズらしい自然なボケ。デジタル的にシャープすぎず、過剰なHDRやCM調にはしない。日本映画の本編から切り出したようなシネマティックなレンズトーン。文字、字幕、ロゴ、HUDなし。 主人公は日本人の腰の曲がった高齢女性。毎回、外見、顔、髪型、体格、服装を自然にランダム化する。花柄ブラウスとベストの近所のババア、割烹着、農作業着、スーパー帰りの服装、上品なカーディガン、派手な柄物、和服、ジャージ、小柄で非常に腰の曲がったタイプ、痩せ型で鋭い目つきのタイプなどから毎回違う人物にする。白髪、灰色髪、短髪、パーマ、お団子などもランダム。ただし共通して、腰が強く曲がった高齢女性であり、普段はゆっくり動きそうに見えるが、戦闘開始後だけ常識外れの超高速格闘能力を発揮する。 対戦相手は成人男性。高齢男性に限定しない。普通のサラリーマン、若い不良風の男、中年の店主、筋肉質なスポーツマン、作業着姿の職人、宅配スタッフ、スーツ姿の会社員、ストリートファッションの若者、観光客風の男性、頑固そうな中年男性などから毎回ランダムに設定する。年齢、体格、服装、髪型も毎回変更する。ババアより大柄でもよい。 ロケーションも毎回ランダムに変更する。昔ながらの商店街、住宅街の細い路地、大型ショッピングモール、スーパーマーケット、コンビニ前、駅前広場、地下街、飲食店や店舗の店内、ホームセンター、観光地の参道など、日本国内の日常的な場所を選ぶ。必要に応じて通行人、買い物客、店員、学生、会社員、観光客などが自然に存在する。背景人物は主役にせず、戦闘が始まると驚いて振り返る、立ち止まる、距離を取る、道を開ける程度の自然な反応にする。 格闘技の内容も毎回ランダムに組み合わせる。高速前蹴り、高速回し蹴り、ローキック、足払い、膝蹴り、掌底、肘打ち、中国拳法風の連続掌打、八極拳風の短距離突進、太極拳風の受け流し、柔道の崩し、体落とし、小外刈り風の足技、腕を取って体勢を崩す動き、高速ステップ、高速フェイントなどを複数組み合わせる。同じ技だけを連打しない。ババアは腰が曲がった姿勢を基本的に維持しながら、人間離れした速度で戦う。 映像全体の最重要構造は固定する。 「高速移動 → 一瞬だけ実体化 → 格闘技 → 即離脱 → 別方向から再接近 → 突然急停止 → 高速キッス → 即離脱 → 再び高速格闘」 この反復を15秒間、高密度で繰り返す。 高速キッスは絶対に省略しない。キッスは最低5回程度入れる。各キッスのたびに顔の超接近アップを0.2〜0.4秒程度だけ短く差し込む。キッスの直前まで激しく高速移動しているのに、唇が接触する瞬間だけ突然時間が止まったように人物が鮮明になり、接触を明確に見せる。直後には即座に高速で離脱し、そのまま格闘へ復帰する。 キッスの前に長く見つめ合わない。恋愛的な間を作らない。キッス後に照れない。笑い合わない。色気を強調しない。キッスそのものも本気の格闘の中に組み込まれた異様な接触技として扱う。男は毎回驚くが、コミカルな顔芸にはしない。驚愕と困惑を短く見せた直後に本気で反撃しようとする。 この戦いは同じ場所に固定しない。対峙した開始地点から、戦いながら少しずつ位置を移動していく。攻防のたびに2人の立ち位置がずれ、前進、後退、横移動、回り込み、押し込み、回避によって、画面内の背景が少しずつ変化していく。商店街なら店先から通路中央へ、通路中央から別の店の前へ、ショッピングモールなら柱やベンチやエスカレーター付近へ、スーパーなら通路沿いに移動しながら、路地なら奥へ流れながら戦う。戦闘全体を通して、2人は周囲の環境の中を移動し続け、ひとつの定位置で格闘し続けない。高速移動するババアだけでなく、男も押し返し、踏み込み、かわし、よろけ、追いながら位置を変える。結果として15秒の間に戦場の重心が少しずつ移動していく。 カメラワークも固定しない。カメラは1か所に置いた固定撮影ではなく、戦いに合わせて常に位置と向きを変える。前進、後退、横移動、斜め移動、回り込み、追従、遅れて追うリフレームを自然に組み合わせる。ワイドで全体を捉えた直後に少し寄り、別の角度へずれ、また追いかける。2人の移動に合わせてカメラも数歩分動いてついていく。時には男の肩越し、時にはババア寄り、時には2人の進行方向に合わせて並走する。カメラ自体を無意味に高速回転させたり、同じ構図を固定し続けたりしない。戦いながらロケーションの別の部分が見えてくる、空間の中を一緒に移動している感覚を出す。 0.0〜1.5秒。ババアと男が至近距離で対峙している。両者とも本気の構え。ババアは腰の曲がった姿勢のまま低く重心を落とし、鋭く男を見据える。男も警戒しながら構える。場所に通行人や客がいる場合、まだ周囲は日常の状態。緊張感のある静かな導入。カメラはミディアム〜ややワイドで2人を捉えつつ、完全固定ではなく、じわりと寄るか、わずかに横へ動いて緊張感を高める。 1.5〜2.1秒。男が先に踏み込む。腕を伸ばす、掴みにいく、蹴りを出す、打撃を仕掛けるなど、毎回違う攻撃を開始する。その瞬間、ババアが突然異常な速度で加速。身体に強いモーションブラーと残像が生じ、男の攻撃線を紙一重で外しながら一瞬で顔面付近へ入り込む。ここで2人の位置は開始地点から少しずれる。カメラも遅れて追い、横へ流れる。 2.1〜2.4秒。第1高速キッス。突然、顔の超接近アップ。高速移動が完全に止まり、ババアが男へ一瞬だけキッスする。唇の接触が明確に見える。男は目を見開く。0.2〜0.4秒だけ鮮明に見せる。 2.4〜3.0秒。キッスを離した瞬間、ババアはすでに高速離脱。男だけが一瞬その場に残され、驚愕したまま次の方向を探す。ババアの残像が別方向へ走る。男はそれに引っ張られるように数歩動き、戦場の位置がさらにずれる。カメラもその移動に合わせてリフレームする。 3.0〜3.3秒。第2高速キッス。別方向からババアが突然真正面へ実体化。顔の超接近アップへ瞬時に切り替わり、再び短いキッス。すぐ離れる。 3.3〜4.5秒。ワイドまたはミディアムへ戻り、高速格闘。ババアが男の周囲を猛烈な速度で移動しながら、高速蹴り、足払い、掌打、中国拳法風の連撃、柔道の崩しなどからランダムな技を連続で差し込む。1つの動作を長く見せず、0.2〜0.4秒程度の短いアクションを連続させる。男も本気で防御し反撃する。2人は攻防しながら少しずつ移動し、開始地点とは違う背景が見えてくる。カメラも並走、斜め追従、回り込みを混ぜて追う。 4.5〜4.8秒。第3高速キッス。激しい高速移動の途中で突然ババアが男の顔の目前へ停止。顔の超接近アップ。短く明確なキッス。直後すぐ高速離脱。 4.8〜5.4秒。高速格闘再開。男が反撃しようとするが、ババアは側面、背後、正面へ高速で位置を変え、攻撃をかわしながら技を差し込む。強い残像、風圧、衣服の揺れ。男もそれに合わせて踏み替え、向きを変え、押し戻され、2人はさらに別の場所へ移る。カメラも止まらず一緒に動く。 5.4〜5.7秒。第4高速キッス。再び超接近アップ。キッスだけ一瞬完全に止まり、すぐ高速離脱。 5.7〜8.4秒。ここは高速格闘の密度を最大化する。ババアが男の周囲を高速で回り込み、0.2〜0.4秒単位で攻撃方向を変える。高速前蹴り、回し蹴り、足払い、掌底、肘、受け流し、崩し、投げへの入り、短距離突進などをランダムに組み合わせる。男も本気で攻撃を返すが、ババアは直前で回避し、別方向へ抜ける。ババアが複数人に増殖したようには見せず、1人の人物が超高速で位置を変えているように描く。この区間では攻防の流れで2人が通路、路地、フロアなどをさらに移動し、背景が段階的に変化する。通行人や客がいる場合は、戦いを避けるように自然に脇へ下がり、進路が開く。カメラも後退しながら受けたり、横へ動いたり、回り込んだりして空間の変化を見せる。 8.4〜8.7秒。第5高速キッス。激しいラッシュの途中で突然真正面へ実体化。顔の超接近アップ。キッス。その瞬間だけ背景と人物の速度感が止まり、唇の接触が鮮明に見える。即離脱。 8.7〜10.5秒。高速格闘へ即復帰。男が大きく反撃し、ババアが紙一重でかわす。さらに中国拳法、柔道、キック系などから別の技を高速で組み合わせる。この区間にテンポを壊さない範囲で第6高速キッスを短く1回追加してもよい。その場合も必ず「顔の超接近アップ → 短い接触 → 即離脱」で処理する。この区間でも2人はその場にとどまらず、押し引きしながら戦いの位置が少しずつ移動し続ける。カメラも追い続ける。 10.5〜12.5秒。一度だけ両者の距離が開く。男は体勢を整え、本気で最後の攻撃に備える。ババアも腰の曲がった姿勢のまま静かに構える。2人とも相手から視線を外さない。ここだけ短い緊張の間を作る。ただし長く止まりすぎない。この時点ですでに開始地点とは違う位置まで戦いが移動していることが背景から分かる。カメラは少し回り込みながら2人の距離感を見せる。 12.5〜13.4秒。ババアが突然真正面から猛烈な速度で突進。強い残像を引きながら一気に距離を詰める。男も迎撃しようとするが、その攻撃をかわしながら顔の目前まで到達。直前で完全急停止。ここでも2人はさらに数歩分位置を移し、カメラも一緒に踏み込む。 13.4〜13.9秒。フィニッシュ高速キッス。顔の超接近アップ。最後のキッスはそれまでよりわずかに長く、最も明確に見せる。直前まで超高速だった映像が、この瞬間だけ完全に静止したように見える。恋愛的な演出は一切入れない。真剣な必殺技として扱う。 13.9〜15.0秒。キッス直後、男が強い衝撃を受けて後方へ大きく吹き飛ぶ、転倒する、床を滑る、壁や什器の方向へ弾かれるなど、ロケーションに合わせた真剣な決着。過剰なギャグ落ちは不要。ババアはその場付近に残り、腰の曲がった姿勢のまま静かに男を見る。笑顔、勝利ポーズ、指差し、コミカルな仕草はしない。カメラは決着の勢いに合わせてわずかに流れ、最後に止まる。 高速移動の表現は「急加速 → モーションブラーと残像 → 一瞬だけ実体化 → 鮮明な技またはキッス → 即再加速」を繰り返す。高速中ずっと人物をぼかし続けず、停止した瞬間だけ身体と顔を鮮明にする。 カメラは実写映画の格闘シーンとして撮影する。基本はミディアム〜ワイドで、2人の位置関係と技の動線を明確にする。高速移動中は短いパン、急なリフレーム、わずかに遅れる追従、自然な手持ち感、前進、後退、横移動、回り込みを使う。カメラそのものを無意味に高速回転させない。 キッスの瞬間だけ必ず顔の超接近アップへ切り替える。「ワイドで高速格闘 → 突然顔の超アップ → 0.2〜0.4秒のキッス → 即ワイドへ戻って高速格闘」という映像テンポを何度も繰り返す。このアップとワイドの高速な切り替えが映像の重要なリズム。さらに各ワイド、ミディアム、アップの撮影位置や背景は少しずつ変化し、同じ場所、同じ画角、同じ背景で繰り返さない。 登場人物は最後まで真剣。ふざけない。笑わない。キッスだけをギャグとして強調しない。全体としては緊迫した本格高速格闘映画であり、その中に説明不能な高速キッス技が何度も自然に組み込まれている状態を維持する。 毎回ランダムに変更するのは、ババアのタイプ、男の人物設定、ロケーション、背景人物、格闘技、技の順番、男の反撃、戦いながら移動する方向と経路、カメラが追従する方向と角度、最後の決着方法。 毎回必ず維持するのは、腰の曲がった日本のババア、35mm映画フィルム調のシネマティックな映像、本気の高速格闘、0.2〜0.4秒単位の高速アクション、最低5回程度の高速キッス、キッスごとの顔の超接近アップ、キッスだけ一瞬完全停止、キッス直後の即高速離脱、即格闘復帰、最後の高速キッスによるフィニッシュ、戦いながら少しずつ空間を移動していくこと
A prompt for creating hyper-realistic cinematic action scenes in a high school basketball gym, featuring supernatural energy effects and dramatic confrontation.
Ultra-realistic cinematic action scene inside a high-school basketball gym, a fierce young woman in a stylish school-uniform-inspired outfit unleashes powerful glowing red and purple supernatural energy from her hands, intense confrontation with another girl, dramatic energy trails and particles, dynamic movement, wooden basketball court, bleachers in the background, cinematic lighting, realistic facial details, dramatic atmosphere, motion blur, volumetric light, shallow depth of field, high contrast, photorealistic VFX, 8K detail, vertical 9:16 composition, epic supernatural action movie aesthetic.
An action-packed video prompt depicting a knight fighting bats and a fire-breathing dragon.
Knight fighting many black bats dragon lands standing over knight blasts black bats with fire
A highly detailed cinematic prompt for a 30-second special forces night raid video with strict consistency rules.
16:9 横屏,30秒,电影级现代夜间特种作战短片,超写实真人摄影,高预算军事惊悚片质感。整体色调为冷蓝黑色,低饱和、低照度、高反差,空气中有轻微雾气、灰尘和冷凝水汽。场景为深夜城市高层建筑内部及相连的工业走廊,包含狭窄通道、金属门、混凝土墙面、低亮度应急灯和窗外模糊城市灯光。全片保持同一夜间环境、同一人物、同一服装、同一枪械、同一冷蓝光线,不改变时间、地点和视觉风格。 主角高度参考上传图片中的同一名特种兵。深色夜战作战服,宽松深色战术外套,深色贴头帽或头套,黑色战术手套,胸前有软管式呼吸或通信装置,肩背黑色战术装备包。主角手持同一把现代突击步枪,枪械安装消音器、瞄准镜、战术灯和前握把。人物始终保持冷静、克制、专业、专注。面部、服装、装备和枪械在整段视频中保持一致,不换脸、不换装、不换武器。 0至5秒: 以接近上传图片气质的中近景开始。摄影机位于主角正前方略低位置,35mm镜头,轻微仰拍。主角单膝或低姿停在黑暗走廊边缘,低头快速确认武器状态,然后缓慢抬头观察前方。冷蓝色侧光打在脸部、帽子和武器边缘,背景大部分沉入黑暗。窗外只有模糊蓝白城市灯点。摄影机缓慢向前推进,不做快速切换。声音只保留沉重呼吸、衣料摩擦、远处风声和轻微无线电杂音。 5至10秒: 主角起身,以低姿贴着右侧墙面向前推进。枪口始终朝向前方,动作安静、缓慢、明确。摄影机保持在主角左后方肩后位置,以35mm镜头稳定跟随。主角经过一个转角时短暂停顿,身体贴墙,先观察,再继续移动。前方远处出现一名守卫的模糊身影。守卫缓慢转身巡视,不要突然出现。空间关系保持清晰,主角在近景,守卫在走廊远端。 10至15秒: 主角接近守卫所在区域,停在门框阴影内。守卫开始察觉异常,头部轻微转向主角方向。主角立即抬枪,用消音武器完成一次极短促点射。守卫产生自然受击反应并倒入墙边或地面,不出现夸张血腥。主角不原地停留,立刻跨过守卫位置继续前进。摄影机仍保持肩后跟拍,不切成太多角度。重点表现“发现、反应、压制、继续推进”的清晰动作链。 15至20秒: 主角来到目标房间门外。房门关闭或半掩,门缝中透出微弱蓝白光。主角靠墙站位,短暂停顿,调整握枪姿势,侧头确认室内动静。摄影机从肩后缓慢移动到主角侧前方,保持同一空间连续性。主角迅速推门进入,不使用复杂爆破,不增加多人协同。房间内只有一名高价值目标和一名贴身护卫。护卫位于目标侧后方,目标靠近桌面、设备或窗边。 20至25秒: 主角进入房间后立即控制射界。护卫首先发现主角,试图抬起武器。主角迅速进行一次短点射压制护卫,然后立即将枪口转向高价值目标。高价值目标后退一步,试图躲向桌边或墙角。主角保持稳定站姿和精准持枪动作,迅速完成目标清除。整个过程只安排两次明确动作:先压制护卫,再锁定目标。避免同时多人乱动,避免复杂枪战。不要血浆特写,不要慢动作,不要大规模爆炸。 25至30秒: 主角快速扫视房间确认安全,低头看一眼胸前通讯装置,短暂停顿,随后转身撤离。摄影机跟随主角从房门退出,再次回到冷蓝色走廊。最后3秒使用与开头相似的低机位中近景。主角持枪向前进入更深的黑暗,冷蓝色雾气和远处城市灯光出现在背景。主角轮廓逐渐被黑暗吞没,画面在沉重呼吸声和微弱无线电杂音中切黑。 Seedance 2.5 稳定执行规则: 人物一致性为最高优先级。主角全程保持同一张脸、同一深色头套、同一作战服、同一战术外套、同一胸前软管装置、同一背包和同一把步枪。不要生成额外队员,不要生成大量敌人。全片最多出现主角、一名走廊守卫、一名贴身护卫和一名高价值目标。 镜头数量控制在少量长镜头和清晰过渡。避免连续快速剪辑,避免360度绕拍,避免突然切到完全不同空间。摄影机以35mm为主,必要时使用50mm近景。主要采用肩后跟拍、侧前方中近景和轻微低机位。摄影机运动平稳,保留轻微手持呼吸感。 动作必须简洁明确。每个时间段只执行一个主要动作目标。不要同时安排大量奔跑、多人交火、爆炸、直升机、烟雾和快速切镜。优先保证人物、武器、动作和空间连续性。 所有枪械保持相同结构、长度和附件位置。枪托始终贴合肩部,双手持枪姿态符合真实人体结构。禁止枪管弯曲、弹匣变形、瞄具漂移、武器忽然变长或变短。 夜间光线全程保持冷蓝黑色调。禁止突然出现暖色日光、明亮白天、红色霓虹或赛博朋克环境。暗部保留细节,皮肤、衣料、金属和墙体要有真实纹理。 负面约束: 人物换脸,人物变装,突然换枪,武器变形,枪管弯曲,瞄具漂移,弹匣消失,手指穿模,多余手指,多余肢体,人物瞬移,场景跳变,大量群演,复杂多人混战,敌人突然生成,科幻感,赛博朋克感,游戏CG感,卡通感,塑料质感,夸张血腥,血浆特写,爆炸过多,镜头剧烈乱晃,快速无逻辑切镜,过曝,过饱和,白天场景,暖色阳光。
A detailed prompt for a 30-second cinematic Wuxia video featuring a female warrior in Hanfu fighting in an ancient Chinese village at night with magical sword effects.
Create a 30-second cinematic, ultra-realistic wuxia-style video set at night in an ancient Chinese village, with traditional wooden buildings, a stone-paved street, a small arched bridge, misty mountains in the background, and many glowing red lanterns hanging along the street. A beautiful young woman in an elegant flowing red traditional Chinese Hanfu walks calmly toward the camera, with long dark hair styled traditionally and a serious, confident expression. As she moves closer, the camera slowly pushes in and follows her naturally, capturing the lantern light, fabric movement, atmospheric mist, and realistic footsteps. Around the middle of the scene, she suddenly stops and confidently draws a glowing red magical sword, holding it horizontally in front of her while her expression becomes focused and powerful. The camera moves into a dramatic close-up of her face and sword, showing realistic skin texture, detailed hair, glowing reflections, and cinematic depth of field. Several mysterious black-clothed attackers appear around her, rushing toward her from different directions, creating a tense martial-arts atmosphere. She swiftly turns and performs powerful choreographed sword movements, blocking and striking the attackers with fast but believable movements while the glowing sword leaves subtle red light trails. The attackers are knocked down onto the stone street around her, while she remains standing confidently in the center with her sword raised, surrounded by red lanterns and light mist. End with a wide cinematic shot slowly pulling back to reveal the woman standing alone among the fallen attackers, ancient village buildings and mountains behind her, maintaining consistent character appearance, realistic motion, cinematic lighting, detailed textures, dramatic atmosphere, smooth camera movement, 16:9 aspect ratio, 30 seconds, no text, no watermark.
A prompt for creating a 15-second cinematic fantasy action sequence using Seedance 2.5, depicting an anthropomorphic samurai cat fighting ninjas in a moonlit bamboo forest.
Create a 15-second photorealistic cinematic fantasy action sequence featuring a small anthropomorphic warrior cat battling masked ninjas in a mysterious moonlit bamboo forest. Begin with a wide low-angle establishing shot moving slowly through tall dark bamboo stalks, mist-covered ground, glowing warm Japanese lanterns hanging between the trees, and a huge full moon illuminating the fog → reveal the small warrior cat standing confidently on a curved bamboo arch, wearing detailed dark-blue samurai armor, a flowing dark cape, leather accessories, and a wide traditional straw hat, with a katana at his side → transition into a dynamic tracking shot as multiple masked black-clad ninjas emerge from the surrounding mist, forming a threatening circle around the tiny warrior → cut to a dramatic close-up of the cat as his eyes become intensely focused and he draws his sword, a brilliant electric-blue magical energy beginning to glow along the blade → suddenly transition into a fast cinematic action shot as the warrior cat leaps high into the air above the ninjas, cape and clothing reacting naturally to the movement, swinging his glowing blue sword in a powerful arc → follow with a low-angle tracking shot through the bamboo as the cat rapidly moves between attacking ninjas, leaving elegant blue energy trails through the mist → cut to a wide shot showing multiple ninjas being knocked backward while the warrior remains centered and controlled → transition into a slow-motion heroic landing as the cat lands on a moss-covered rock, glowing sword held low at his side while the surrounding enemies stagger behind him → final shot becomes a heroic low-angle wide shot of the tiny warrior standing proudly beneath the enormous full moon, bamboo trees towering around him, mist drifting across the forest floor, cape gently moving in the wind, and the brilliant blue sword glowing against the dark night. Visual style: ultra-photorealistic fantasy film, realistic fur and facial details, detailed samurai armor, believable fabric and fur movement, realistic sword physics, atmospheric volumetric moonlight, natural fog, cinematic depth of field, dramatic composition, high-detail bamboo forest, realistic shadows, premium VFX, smooth character animation, dynamic camera movement, epic fantasy adventure atmosphere, 4K detail. Negative prompt: cartoon, anime, low resolution, plastic fur, deformed face, extra limbs, extra weapons, duplicate characters, distorted hands or paws, inconsistent armor, changing character design, identity drift, floating objects, unrealistic sword movement, excessive motion blur, oversaturated colors, text, subtitles, watermark, logo, frame glitches, unnatural physics.
An intense action video prompt for a single-shot samurai battle sequence, including specific camera movements and character consistency locks.
KAZEMIRU: THE JADE-WIND BLADE: ONE-TAKE CASTLE ASSAULT Duration: 30 seconds | Aspect Ratio: 16:9 | No music ONE-TAKE LOCK: This is ONE SINGLE UNBROKEN CONTINUOUS SHOT lasting the full 30 seconds. ZERO cuts. ZERO dissolves. ZERO fades. ZERO match-cuts. ZERO time jumps. ZERO scene resets. The camera never leaves the action and every location change happens physically inside the shot: the camera passes through torn doors, over railings and up the roof with Kazemiru. Time runs in real time. STYLE: Ultra-photorealistic live-action Japanese dark-action cinema with restrained subtle VFX. Impossible anime-inspired dual-sword choreography performed by real human bodies. Large-format cinema look, natural daylight, muted earthy color palette, soft realistic shadows, no oversaturated colors. @Image1 is KAZEMIRU. Preserve her exact face, silver-white ponytail, torn ivory kimono, charcoal split hakama, wind-swirl forearm tattoo and gold hoop earrings in every frame. @Image2 shows the five elite guards. @Image3 shows Captain Tetsugan. POSITIVE LOCKS (true for all 30 seconds): - Exactly ONE Kazemiru with exactly TWO real steel katanas, one in each hand, both always visible and independently controlled. - Her face always matches @Image1. - Every enemy comes from @Image2 or @Image3 and stays visually consistent. - Her body physically crosses every distance, with no teleportation. - It is always daytime with bright natural light. PERSONALITY: Cold, calm, battle-hungry. Minimal expression, steady breathing, focused eyes. Her hunger shows through relentless speed and escalating ferocity, never through grinning or shouting. JADE-WIND EFFECT: Every fast movement leaves a thin, soft jade-green wind trace that follows her exact physical path and fades almost instantly: sword arcs leave fine blade trails, spins bend the air, footsteps kick tiny wakes, supersonic bursts add a brief compressed-air ripple. Always thin, subtle and realistic. No aura, no smoke, no glowing body, no effects moving on their own. CAMERA (one continuous handheld-style pursuit): Constant dutch angle of 25–35°. Wide field of view around 75° in the interior and courtyard, tightening to about 50° for the rooftop duel. Kazemiru moves first and the camera follows 0.1–0.3 seconds late: whip-pan, overshoot, correct, reacquire at the moment of contact. The camera flows through rear over-the-shoulder, low-angle pursuit, side tracking, ground-level chase and front three-quarter retreat, always in one connected movement. Never static, never perfectly smooth. ══ 0:00–0:10: THE GRAND AUDIENCE HALL ══ Setting: bright daylight through large shoji panels, gold folding screens, tall dark timber pillars, tatami sections, raised platform, armor displays, low lacquer tables, silk curtains. 0:00–0:03: Rear over-the-shoulder, five guards closing in. Her fingers tighten on both hilts. BURST: a thin jade streak snaps across the hall and the silk curtains whip. The camera loses her, whip-pans, and finds her inside Guard 1's reach. Left blade parries, right blade slashes diagonally, a pivot, a reverse cut. He drops. 0:03–0:06: Guards 2 and 3 converge. She ducks under a swing, plants a foot on a pillar and pushes off, dust bursting from the wood. Mid-air her left sword deflects Guard 2 and her right sword cuts down. She lands on the edge of a lacquer table, which slides back, and rebounds straight toward Guard 3. 0:06–0:10: Aerial right slash, left reverse slash, dual cross-slash with two separate jade trails. She lands low and bursts across the floor. Guard 4's spear thrusts: she runs two steps up a wall, flips off, and cuts him down through a folding screen. Guard 5 charges: she catches his blade with one sword, vaults the railing above him, and finishes with a cross-slash as she lands behind him. ══ 0:10–0:20: THE PALACE COURTYARD ══ Transition inside the same shot: she does not pose. Both swords still in hand, she drives straight through the paper doors in one burst. The torn paper flutters past the lens as the camera follows her through the doorway onto the wooden veranda and out into a stone courtyard with lanterns, a koi pond, a red lacquer arched bridge and pine trees. Eight new guards: swordsmen below and archers on the roofs. 0:10–0:13: A volley of arrows. She cuts two out of the air with a spinning double slash and a third grazes her sleeve. She sprints along the veranda, pivoting off each post, a jade ripple following her feet. 0:13–0:16: She kicks off a stone lantern, which tips over, and leaps onto the bridge railing. Three swordsmen charge. She runs along the rail, slashes the first, flips over the second, and lands in the koi pond with a huge splash. In the water she parries two blades and cuts both guards. Droplets scatter across the lens. 0:16–0:20: She bursts out of the pond and sprints up a pine trunk in three steps. The camera tilts up with her. She launches onto the roof among the archers: left sword disarms, right sword strikes, roof tiles scatter. Two archers fall. ══ 0:20–0:30: THE ROOFTOP DUEL ══ Transition inside the same shot: she keeps climbing over the roof ridge and the camera rises with her, tightening to a 50° field of view. The tiled castle rooftop opens up with wind in her ponytail and the town far below. Captain Tetsugan (@Image3) waits with his naginata, calm and unflinching. 0:20–0:23: Tetsugan sweeps the naginata in a wide arc. Kazemiru ducks, slides down the sloping tiles, and crosses both swords to stop the blade. Sharp metal sound as his strength pushes her back a step. Her expression stays cold. 0:23–0:27: Fast exchange: his thrust, her left parry, her right slash that cuts his armor cord. He spins the pole and sweeps for her feet: she jumps, kicks off the shaft, and flips over him. Mid-air she cuts both swords across his back armor. Tiles crack under their feet and a faint jade wake curves around her path. He staggers, strikes back, and she narrowly dodges as the blade cuts a roof beam. 0:27–0:30: Supersonic burst along the ridge line, the jade streak slightly brighter but still thin. She slides under the naginata, and as she rises both swords slice through the shaft in a clean cross-cut. Tetsugan drops to one knee, defeated but alive. Kazemiru stands, both swords still in hand, and the last jade filaments disappear. She turns her cold eyes toward the courtyard far below, where dozens more guards pour in. The camera slowly pulls back and up to a wide shot of the whole castle. She lowers her body for the next burst. THE FIGHT CONTINUES. AUDIO: Sword resonance, compressed-air whooshes, metal clashes, footsteps on wood and tiles, arrows, water splashes, fluttering silk and paper, enemy shouts, wind over the rooftops. No dialogue, no music. HUMAN-FIRST LOCK: Kazemiru is always a real human: natural skin pores, real eyes, individual hair strands, believable anatomy and cloth physics. Only her choreography is anime-level impossible. NEGATIVE: cuts, edits, dissolves, fades, scene transitions, time jumps, multiple shots, single-sword fighting, missing or duplicate sword, duplicate Kazemiru, clones, teleportation, thick aura, smoke, glowing body, neon or oversaturated colors, detached VFX, random flips, decorative acrobatics, idle pose, static camera, perfectly smooth tracking, slow combat, floating, broken anatomy, CGI or plastic skin, anime rendering, blood, gore, subtitles, logos, watermark.
A detailed prompt for a 30-second realistic fitness Vlog with 2000s home DV camera aesthetics, focusing on character consistency and natural lighting.
创建一段30秒、4:3横向画幅、高度写实的个人健身Vlog,呈现朋友用2000年代初家用DV随手记录一次日常锻炼的感觉。不是健身广告,也不是精致的电影短片。30秒是一次健身过程的剪辑摘要,通过自然跳剪串联出门、准备、训练和结束,不要让人物在30秒内匆忙完成所有事情,不要加速播放。 【人物与服装】 使用上传的这张灰色运动装全身人物图【@图片1】作为唯一角色参考。主角为参考图中的成年女性,严格保持她的五官长相、脸型、眼睛、鼻子、嘴唇、细框眼镜、发际线和整体年龄感一致。不同角度、运动状态、说话和笑起来时,依然必须是同一个人,不能变成另一张相似的脸。参考图只用于确定人物身份、服装和身体外观,不沿用白色摄影棚背景或原图的固定站姿。 人物具有自然、健康的健身力量感,肩臂、腰腹和腿部有适度肌肉线条,运动时能够看到真实的肌肉收缩和稳定的身体控制。保持参考图的整体身高和身材比例,不要夸张增肌、过度收腰或拉长双腿。皮肤保持白皙细腻,但保留自然皮肤质感,运动后可以出现轻微泛红,不能过度磨皮或呈现塑料感。 全程穿着参考图中的同一套运动服装:麻灰色宽领短袖T恤,领口自然倾斜,露出她的右肩,也就是正面面对镜头时画面左侧的肩膀;同侧腰部衣摆打结,形成露出腰腹的短款造型,保留胸前原有粉紫色印花;里面是粉紫色细肩带运动内衣,肩带和少量边缘自然露出;下身为麻灰色高腰贴身运动短裤,搭配白色罗纹中筒运动袜和参考图同款白色系带运动鞋。衣服随运动产生真实褶皱和轻微位移,但不能改变款式、颜色、材质、打结位置或露肩方向。不要换成黑色上衣、长款紧身裤、蓝色袜子或长靴。 出门时保留参考图中的披散黑色长发,进入健身房前亲手扎成马尾,此后始终保持同一条马尾,保留自然额前碎发和鬓发,不要突然换刘海或改变发量。眼镜全程佩戴,运动中保持合理位置。道具固定为一个小号黑色健身包、一只白色瓶盖的透明水瓶和一条小白毛巾,不要在不同镜头中改变外观。 【镜头流程】 0—3秒|去附近健身房。 安静的社区街道,自然日光。朋友在她侧前方边走边拍,她穿着上述灰色运动套装,单肩背着小号黑色健身包,向附近健身房走去。黑色长发随着脚步轻轻晃动。她短暂看向镜头,露出一个自然的小笑容,随后继续看路,不刻意摆拍。镜头有走路带来的轻微起伏,构图略偏,像随手记录。 3—6秒|扎好头发。 在健身房入口旁停下,侧面中近景。她抬起双手,将长发收拢,用黑色发圈扎成利落的马尾,随后扶一下眼镜、调整肩上的包带。可以用自然跳剪略过部分扎发过程,但必须让观众看到从披发到马尾的实际动作,不能让发型凭空变化。动作放松熟练,手指和头发之间的接触真实。 6—9秒|放下东西,简单热身。 切入普通社区健身房,黑色橡胶地面、哑铃架、训练凳和墙面镜子,环境真实、有人使用的生活痕迹,不要豪华空旷的商业摄影棚。她把黑色健身包放在靠墙训练凳旁,将水瓶和白毛巾放在凳子一端。自然跳剪到她轻轻活动肩膀、舒展手臂,调整呼吸。镜头像朋友站在旁边随手拍摄,不围绕身体刻意展示。 9—15秒|简单力量训练。 两个正常速度的训练片段:先拍她进行轻哑铃弯举,完整呈现一次平稳抬起、短暂停顿、控制放下的过程,肩膀不乱晃,手掌真实握住哑铃,手臂随着发力出现自然肌肉线条;随后切到侧前方中全景,拍她完成一次自重深蹲,从站立到下蹲再稳定站起,双脚接触地面,膝盖和髋部运动合理,躯干稳定。她专注呼吸,发力时轻轻呼气,不对镜头摆健身造型。运动服出现自然拉伸和褶皱,马尾随着动作轻微摆动。 15—20秒|跑步机慢跑。 侧前方手持中景,她在跑步机上轻松慢跑,步幅适中,左右脚交替接触跑带,手臂自然摆动,马尾随步伐有节奏地晃动。呼吸稍微变重,额头、鼻翼和颈侧逐渐出现少量汗水,不是突然全身湿透。她看了镜头一眼,带着一点累又觉得好笑的表情轻轻笑一下。随后自然剪切到跑步机已经减速、停止,她确认站稳后再走下来,不跳下运行中的跑带。 20—25秒|喝水、擦汗。 回到同一张训练凳旁,她拧开同一只水瓶,喝两小口水,再用小白毛巾轻按额头和颈侧。毛巾与皮肤有真实接触和遮挡,不穿过眼镜,不直接擦掉全部汗水。她偶然看到镜子里有些出汗的自己,轻轻笑起来,是运动后放松的真实反应,不是夸张表演。镜中倒影的动作、服装和位置必须与本人准确对应。 25—30秒|练完收工。 她坐在训练凳上,呼吸仍稍微急促,肩膀随着呼吸轻轻起伏,手里拿着毛巾。朋友把镜头稍微凑近,她抬眼看向镜头,用自然的中文口吻笑着说:“今天练得还挺爽!”声音略带运动后的气息,嘴型准确,说完轻笑一声。最后自然切到她背上同一个黑色健身包走向出口,马尾轻晃,镜头稍慢半拍跟上,在生活化的动作中结束,不做广告式定格。 【摄影与画面质感】 整段呈现2000年代初消费级MiniDV录像质感:轻微手持抖动、不完美构图、偶尔跟拍不及时、轻微自动对焦搜索、室外进入室内时短暂曝光和白平衡变化、柔和的数字细节、轻微暗部噪点、正常运动模糊,以及一次不太熟练的小幅变焦。这些瑕疵应克制、随机,不要每个镜头都故意失焦或剧烈晃动。人物脸部始终足够清楚,可以辨认出参考图中的同一个人。以平视中景、中全景和自然面部近景为主,训练镜头保留必要的身体和器械信息,不刻意对胸部、臀部或其他局部进行特写。不要稳定器式丝滑运镜、大片调色、慢动作、炫光、胶片烧灼、夸张颗粒或伪造的磁带故障。画面中不出现DV机本体。 【音频】 仅保留同期环境音:社区脚步声、轻微街道声、推门声、包带与衣料摩擦、健身房空调嗡鸣、远处模糊交谈、哑铃轻放声、鞋底接触地面的声音、跑步机马达声、逐渐变重的呼吸、水瓶开盖和喝水声、毛巾摩擦声、自然笑声,以及结尾的一句人物同期对白。音质带有家用DV内置麦克风的轻微底噪和空间感,不要录音棚式人声。没有背景音乐,没有解说旁白,没有字幕。 【负面约束】 禁止身份漂移、变脸、眼镜消失或变形、发型无故切换、衣服换色换款、露肩方向左右翻转、身体比例变化、夸张肌肉、塑料皮肤、美颜滤镜、异常皮肤纹理、不合理汗水、扭曲手掌、多余手指、器械变形、哑铃穿手、脚底滑动、跑步动作失真、物品漂浮或瞬移、错误镜面倒影、重复主角、突然出现的道具。除参考服装已有印花和标记外,不新增品牌标志、水印、日期时间戳、界面文字或其他画面文字。
A prompt for creating realistic cinematic superhero super-speed scenes on busy downtown streets, featuring dynamic camera tracking and visual effects.
Create a realistic cinematic superhero speed sequence in a busy downtown city street during autumn, with natural daylight, pedestrians, cars, crosswalks and detailed buildings. Scene 1 — Wide street-level shot: pedestrians cross a busy intersection while cars wait in the background. Camera tracks smoothly from left to right. Scene 2 — A female superhero in a sleek fitted red superhero suit suddenly appears and accelerates across the crosswalk at extreme speed, powerful running posture, flowing hair. Scene 3 — Side-tracking close shot: she races past outdoor café tables and pedestrians, surrounded by intense glowing red energy trails and realistic motion blur. Scene 4 — Low-angle tracking shot: she rapidly approaches a small white dog in the crosswalk, crouches down while still moving at super speed and safely grabs the dog. Scene 5 — Close dynamic shot: she carries the dog securely while sprinting forward, red energy streaks wrapping around her body, strong cinematic motion blur. Scene 6 — Wide establishing shot: she races across the entire intersection at incredible speed, leaving long red light trails behind her as pedestrians react naturally. Scene 7 — Fast lateral camera pan: she blasts past people sitting on a city bench reading newspapers, red energy trails sweeping through the frame. Scene 8 — Final wide-to-medium tracking shot: she continues running rapidly down the street and toward the camera, then passes close to the camera with powerful speed, realistic cinematic lighting and motion blur. Photorealistic, cinematic superhero VFX, realistic human movement, natural city environment, dynamic camera tracking, shallow depth of field, realistic red energy trails, high detail, smooth motion, dramatic speed-ramp feeling, no text, no logos, no watermark.
A detailed video prompt for Seedance 2.0 depicting a comedic scene of a bride fleeing her wedding in a red vintage sports car, including specific camera movements.
Use the character sheet as the visual reference. Preserve the bride’s exact face, hairstyle, dress, body proportions, and accessories throughout the entire video. 16:9 landscape. 0–3 sec — THE ESCAPE A church wedding is happening when the bride suddenly bursts through the giant church doors and sprints down the steps, still holding her bouquet. Her expression is determined but hilariously excited. Her veil and dress fly wildly behind her. Camera rapidly tracks backward in front of her as she runs. A few confused wedding guests appear in the background, realizing what is happening. 3–5 sec — GET TO THE CAR She spots a bright red 1950s vintage car waiting at the curb. She kicks off one white bridal heel while running, then throws herself toward the driver's door. Fast whip-pan follows her movement. 5–8 sec — PEEL OUT She jumps into the car, slams the door, starts the engine and PEELS AWAY at ridiculous speed. Tires squeal, a tiny cloud of smoke appears, and her long white veil gets caught in the closing door and streams dramatically behind the car. The bouquet lands on the passenger seat. 8–11 sec — CHAOS Rapid comedic interior cuts: Bride gripping the steering wheel and laughing → her veil whipping around her face → bouquet bouncing around the passenger seat → her other bridal heel flying through the air → wedding guests running helplessly behind the disappearing car. 11–15 sec — SHE’S FREE Dynamic side tracking shot of the red car racing down a sunny vintage highway. The bride drives one-handed, completely carefree. She looks into the rearview mirror, sees the church disappearing in the distance, grins, then blows a huge pink bubblegum bubble. Final frame: The red car speeds toward the horizon, veil flying behind it. Style: fast-paced physical comedy, playful rebellious energy, 1950s Americana, saturated red vintage car, creamy white wedding dress, warm golden sunlight, cinematic vintage film grain, slightly painterly realism, realistic motion, energetic camera movement, whip pans, quick cuts, exaggerated but believable comedy. Important: No slow motion, no sad mood, no dramatic romance, no dialogue, no text, no extra brides, no face changes, no outfit changes, no distorted hands, no morphing.
A cinematic action prompt where a villain leaps from the screen, transforming the theater into an ancient ruin for a magical duel.
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.
A prompt for generating nostalgic, hyper-realistic videos of children playing street soccer at golden hour, featuring dynamic camera work and slow-motion celebrations.
Create a cinematic, ultra-realistic live-action sequence set in a warm, dusty neighborhood at golden hour. Start with an aerial view of a lively residential area → close-up of a child placing a worn football on the dusty ground → kids begin playing an intense street football match → dynamic low-angle shots of quick dribbles, footwork and the ball flying through the air → end with a cinematic slow-motion shot of the kids celebrating after scoring. Warm golden sunlight, realistic dust particles, natural movement, handheld camera feel, shallow depth of field, detailed environments, authentic emotions, smooth cinematic transitions, photorealistic live-action, nostalgic coming-of-age atmosphere. No text, subtitles, logos or watermark.
A detailed prompt for a 30-second realistic martial arts fight between a hero and villain in a Japanese temple courtyard at dusk.
SEEDANCE 2.5 | 30s | 16:9 Photorealistic live-action martial arts action in a ruined Japanese temple courtyard at dusk. Large-format cinema look, drifting mist, wet flagstones, crumbling stone torii, mossy lanterns, broken pillars and collapsed halls. Desaturated moss green, stone grey and cedar brown, warm lantern accents, natural skin texture, subtle film grain. Soft grey light from camera-right, warm lantern light from camera-left. HERO: Use Image1 with EXACT same face, hairstyle, body build and outfit in every shot. Calm, controlled and extremely fast. Natural dust and fabric wear increase during the fight. VILLAIN: Tall broad-shouldered warrior, charcoal-black layered kimono, dark indigo sash, half-face iron mask, long tied-back black hair, worn hardwood bo staff. Outfit remains unchanged. SHOT FLOW: 00:00–02: Hero stands beneath torii, mist drifting; 24mm extreme-wide slow dolly-in. 02–04: Villain emerges dragging staff; 35mm low-angle tracking shot. 04–06: Hero drops into low fighting stance; 85mm quick push-in. 06–08: Villain swings staff; hero ducks and palm-strikes ribs; 28mm handheld action. 08–10: Rapid staff attacks; hero blocks twice and punches mask; 40mm handheld. 10–12: Overhead staff strike; hero sidesteps and lands elbow; 35mm arc. 12–14: Villain lands heavy blow, throwing hero across wet stone; 24mm ground tracking. 14–16: Hero rises, parries staff thrust and lands knee; 50mm push-in. 16–18: Hero jumps low sweep, pushes off pillar and kicks staff away; 35mm crane rise. 18–20: Unarmed villain throws rapid punches; hero slips, blocks and ducks; 40mm handheld. 20–22: Hero traps arm, elbows villain and flips him onto stone; 28mm orbit. 22–24: FINAL COMBO 1 — rising palm strike + low kick. 24–26: FINAL COMBO 2 — powerful rotating back kick to chest. 26–28: FINAL COMBO 3 — two-handed palm strike sends villain crashing onto wet stone. 28–30: Hero calmly walks toward torii as mist closes in; slow 24mm pull-back, fade to black. AUDIO: No dialogue. Wind, footsteps, cloth movement, staff whooshes, impacts, stone cracks and water splashes. Music builds from low drone → cello → fast taiko → orchestral climax at 00:24 → near silence → sustained cello note. Maintain exact identity, costumes, environment, lighting direction and realistic physics throughout. No face changes, outfit changes, extra characters, random weapons or inconsistent backgrounds.
A CGI animated action scene prompt depicting a female ninja fighting samurais in a moonlit Japanese temple corridor.
A CGI-animated action sequence set at night in a traditional wooden Japanese temple corridor illuminated by a bright full moon. A female anime-style kunoichi ninja with long dark hair tied in a high ponytail, glowing red eyes, a red scarf, and ornate armored martial arts attire fights off multiple samurai attackers. She uses fluid, high-speed martial arts kicks and striking punches that produce red energy impact sparks upon hit. Dynamic cinematic camera work follows her fast movements, featuring dramatic close-ups, wide action shots, and slow-motion impact pauses under dramatic night lighting.
A complex prompt for a viral vertical video of a miniature athletic woman performing parkour moves in a giant arcade.
STYLE: Miniature Tiny-Person FX, photorealistic live-action, cinematic macro photography, ultra-shallow depth of field, realistic amusement-park lighting, ultra-detailed 8K, vertical 9:16, high-energy viral short-video style. DURATION: 30 seconds. SETTING: A gigantic indoor arcade filled with oversized claw machines, racing simulators, basketball games, air-hockey tables, giant plush toys, neon signs, glowing buttons, prize shelves, and colorful arcade machines. Everything feels enormous from the perspective of a palm-sized woman. CHARACTER: One athletic miniature woman (1:15 scale), consistent throughout: cropped bomber jacket, cargo pants, sneakers, compact utility backpack, same face, hairstyle, proportions, and size. She sprints across enormous glowing arcade buttons, jumping between them before launching herself from a giant joystick. She grabs a hanging cable, swings between massive arcade machines, and lands on a racing-game cabinet. She jumps onto the steering wheel of a giant racing simulator as it suddenly accelerates, holding on through the shaking motion before jumping away at the last moment. She lands on a huge air-hockey table as a massive puck races toward her. She jumps onto it, rides across the table, leaps over the goal, and lands on a pile of oversized plush toys. Inside a giant claw machine, she climbs across stuffed animals as the mechanical claw descends toward her. She jumps onto a plush bear, uses it as a trampoline, grabs the claw, and swings out of the machine. She lands on a towering prize shelf, races across giant stuffed toys, and leaps onto a glowing neon sign above the arcade entrance. The camera pulls far back to reveal her tiny scale against the enormous arcade. Large glowing text appears: “BUILT FOR THE BIG MOMENTS” She raises both arms as colorful arcade lights flash around her. SFX: Arcade beeps, button clicks, footsteps, mechanical sounds, engine roar, tire screech, air-hockey hiss, plush impacts, rushing air, electronic chimes, crowd ambience, energetic victory sound. VISUAL REQUIREMENTS: Consistent 1:15 scale, realistic physics, seamless action, photorealistic materials, authentic reflections and shadows, cinematic macro DOF, consistent character identity. No cartoon look, animation style, scale changes, duplicate character, outfit changes, distorted anatomy, floating objects, subtitles, narration, or watermark.
A detailed prompt for Seedance 2.5 depicting a cinematic fantasy battle between a female warrior and a dragon during the golden hour.
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.
A creative prompt for a dance video featuring Marcus Aurelius, Cleopatra, and Rumi performing Sufi whirling and splits.
Make a dance video of Marcus Aurelius with Cleopatra and Rumi doing spins like Durvishes then breakdown and into the splits
A detailed prompt for a 15-second cinematic samurai action sequence in Edo-period Japan, featuring specific instructions for camera lag and wind effects.
KAZEMIRU — WILD-WIND NIGHT HUNT — 5 SAMURAI Duration: 15s | 16:9 | No Music STYLE: Ultra-photorealistic REAL LIVE-ACTION, AAA Japanese dark-action cinema, restrained semi-CGI VFX. ARRI ALEXA 65, IMAX, Panavision anamorphic. Nighttime Edo Japan, cold moonlight, warm lanterns, deep shadows, mist, realistic atmosphere. @Image1 — STRICT IDENTITY LOCK: Preserve exact male face, facial geometry, white hairstyle, body proportions, torn-white outfit, tattoo, accessories and identity. Exactly ONE male Kazemiru, TWO real metal swords, FIVE adult samurai. Kazemiru ALWAYS remains a photorealistic real human male. COMBAT: Wild, aggressive, acrobatic anime-inspired dual-sword choreography translated into live action. BURST → CROSS-SLASH → PIVOT → REVERSE CUT → WEAVE → DOUBLE SLASH → RE-BURST. Both swords remain physical and clearly visible. ZERO idle, posing, waiting or neutral resets. SUPERSONIC WIND: Kazemiru physically crosses every distance; NO teleportation. Each short-range burst creates restrained emerald-green wind trails, subtle particles, air distortion, dust, leaves, bending lantern flames and realistic clothing reaction. LOCATION: Edo castle district at night: broad dirt road, wooden houses, stone walls, gates, tiled roofs, lanterns and trees. Five samurai surround Kazemiru. CAMERA: Strong 25–35° Dutch angle. Camera is always moving and intentionally slower than Kazemiru. Kazemiru moves first → camera reacts 0.1–0.3s late → whip-pan → overshoots → corrects → reacquires at contact. Use rear OTS, 3/4 tracking, aggressive side tracking and low-angle pursuit. NEVER static, floating or robotic. 00:00–00:03 — #1: Five samurai rush from different directions. Kazemiru bursts forward, air blast throws dust and leaves. Camera loses him, whip-pans, reacquires. He reaches #1 and delivers a brutal dual-sword CROSS-SLASH. Clear contact. #1 collapses. No blood/gore. 00:03–00:06 — #2: #2 attacks. Kazemiru weaves beneath the blade, redirects it with one sword and reverse-slashes with the second. Clear contact. He plants one foot on a stone wall and explosively pushes off. Wind and dust erupt. Camera overshoots toward #3. 00:06–00:09 — #3: Kazemiru flies into frame. Camera catches him mid-air. Real human body twists through a descending dual-blade attack. Both swords remain readable. Clear contact. He lands low and instantly bursts again. 00:09–00:12 — #4: Low Dutch tracking above dirt. #4 charges. Kazemiru weaves past by centimeters, pivots and performs two distinct reverse-slashes. Clear contact. Pressure wave throws dirt outward. Camera loses him and violently reacquires. 00:12–00:15 — #5: #5 searches desperately. Emerald wind crosses background. Kazemiru bursts from the side. He ducks the sword, rotate
A detailed prompt for generating a 30-second live-action supernatural martial arts sequence featuring So-Yeon and specific visual effects.
EMBER FRACTURE — AWAKENING Image SO-YEON | 30s | 16:9 | one continuous generation. LIVE-ACTION ONLY: Ultra-photorealistic AAA supernatural martial arts. <<<image_1>>> locks SO-YEON's exact identity; same single woman throughout. Small 160cm build, messy black hair, black hoodie/pants/Converse. Real skin, pores, hair, eyes and biomechanics. Never CGI/digital double. ALLEY: Wet narrow convenience-store alley at night, red/pink/teal neon, puddles, crates, dumpster, vending machine, steam. 5 unarmed male delinquents attack aggressively, never taking turns. AUDIO: Korean dialogue, diegetic impacts/traffic/ambience only. No BGM/subtitles. AWAKENED COMBAT: Her body takes over automatically; unarmed Taekwondo × Karate × Pencak Silat, extremely fast, fluid chained movement with no reset poses. VFX LOCK: Acceleration = physical movement + subtle heat-shimmer/refractive distortion only. No fire, flames, embers, orange particles, beams, plasma or teleportation. Every strong physical impact creates a brief glass-like spiderweb fracture in the air, splitting neon light, then silently disappearing; realistic steam/dust/debris from impact. IMPACT → FRACTURE WEB → NEON REFRACTION → DISSIPATION. 00–03: So-Yeon cowers against wall. Leader smacks her head. She slowly glares through bangs. {어쭈? 이 년 봐라? 많이 컸다?} 03–06: Fear returns; she flinches: {아…! 미안…}. Leader swings again. 06–09: 0.3s slow-mo: automatic head-slip → Silat parry → pivot → body punch. Fracture flash. Leader crashes into crates. 09–12: She stares at trembling hand in disbelief. {저 년이?!} Four rush simultaneously. 12–17: Heat-shimmer dash through two: parry → redirect → elbow → sweep → side kick. Impact fracture + steam. Continue instantly. 17–22: Two attack together: diagonal dash → duck → shoulder redirect → roundhouse. Wide fracture-web splits pink/teal neon. 22–27: Final attacker from behind. Maximum physical dash; camera lags/whip-pans. Evade → parry → jab → body punch → low kick → spinning back kick. 0.25s slow-mo; dense fracture-web across wall. 27–30: Largest fracture lattice spreads across alley, neon reflections split, debris/crates fly, enemy slides away. Fracture hits lens → brief refracted distortion. So-Yeon studies her hands, then calmly walks through steam, half frightened/half amazed, hair falling over eyes. Never looks back. CUT. CAMERA: Close, kinetic handheld pursuit; tracking, whip-pans, low angles, OTS, facial impacts, rapid focus. Camera reacts slightly late to acceleration. Impact shake only on physical contact. Readable action > chaos. HARD LOCK: Real human + real environment + VFX in same frame. No duplicate So-Yeon. No teleportation. Every VFX effect must originate from visible physical contact.
A prompt for a cinematic live-action superhuman subway fight with specific martial arts combinations and camera movements.
Generate a cinematic live-action superhuman fight scene. MAIN CHARACTER: Use image1 as the only main character. A superhuman fighter with extreme speed, strength, and reflexes. Calm expression. Precise martial artist. Every movement is controlled and powerful. OPPONENTS: Use image2 and image3 as main enemies. Add multiple opponents surrounding the main character. Aggressive street fighters. LOCATION: Modern subway station underground. Large platform. Concrete pillars. Subway signs. Metal structures. Train tracks in background. Bright artificial lighting. Passengers watching from a safe distance. FIGHT STYLE: Superhuman close combat. Fast boxing combinations mixed with Taekwondo. Continuous flow. No pause between attacks. Every move transitions naturally. 0–2 seconds: Opponents rush from different directions. Image1 instantly moves forward. Fast combo: left jab → right cross → body punch → spinning back fist. Before the opponent reacts: low kick → side kick → jumping knee strike. Camera follows every impact. 2–5 seconds: The fight becomes extremely fast. Image1 chains: double punch combination, elbow movement, hook punch, roundhouse kick, spinning heel kick, flying kick. Every hit creates powerful cinematic impact. Opponents are pushed backward by the force. Dust and small debris fall from damaged pillars. 5–8 seconds: Multiple enemies attack together. Image1 uses superhuman reflexes: dodges, counters, redirects attacks. Combination: block → counter punch → sweep kick → aerial kick → instant landing. The camera rotates around the action. Motion blur from extreme speed. 8–10 seconds: FINAL MOVE: Image1 charges energy through movement. Explosive combo: rapid punches followed by a powerful spinning kick. A shockwave pushes opponents away. They crash into the environment. Walls crack. Dust fills the subway platform. Final shot: Image1 stands alone in the center. Damaged station. Dust floating. Enemies scattered. Calm expression. CAMERA: Dynamic blockbuster camera. Handheld action style. Fast tracking. Low angles. 360° movement. Slow motion on strongest impacts. STYLE: Ultra realistic live action. High budget action movie. Superhero cinematic quality. Realistic physics. SOUND: Punch impacts. Kick impacts. Footsteps echoing in subway. Air whoosh. Metal vibrations. Crowd reactions. NEGATIVE: cartoon, anime, CGI look, plastic skin, fake physics, static camera, blood, gore, graphic injury, weapons, comedy, low quality,
A four-shot slapstick comedy prompt involving bamboo laundry poles and two people at a Korean villa.
Create a hyper-realistic cinematic slapstick comedy in four seamless shots outside a modest two-story Korean villa on a bright afternoon, using natural handheld smartphone cinematography. Use Image Reference 1 as the woman and Image Reference 2 as the man; preserve their identities, faces, hairstyles, clothing, and proportions consistently. Shot 1: The woman stands at an open second-floor window, struggling to straighten a large white bedsheet with an unusually long bamboo laundry pole. The pole suddenly slips from her hands and falls vertically toward the narrow walkway as the camera instinctively tilts down and follows it. Shot 2: The scruffy man casually walks beneath the building, completely unaware, when the bamboo pole crashes onto his head with a loud THUNK, sending him dramatically onto the pavement. He sits up rubbing his head as the woman leans out apologetically; she says, “I’m sorry! I really didn’t mean to!” and he replies flirtatiously, “It’s okay... but you’re really beautiful.” Shot 3: The man grabs the bamboo pole, sprints toward the building, plants it like a pole vaulter, and launches himself upward toward the second-floor window. The bamboo bends dramatically under his weight as the camera cranes upward and tracks his ascent, with the man leaning forward as if attempting to kiss the woman. Shot 4: The woman recoils and shouts, “Eww... you’re so ugly! Go away!” before delivering a perfectly timed front kick into his torso. The bamboo snaps back like a giant slingshot, launching him violently into the sky as the camera whip-pans and continuously tracks his spinning body until he becomes a tiny silhouette disappearing into the clouds. Cut back to the window as the woman calmly dusts off her hands, picks up another bamboo pole, and resumes fixing the bedsheet as if nothing happened.
A detailed prompt for Seedance 2.5 to generate a high-quality cinematic video of a futuristic warrior fighting monsters in an industrial port on a rainy night.
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.
A complex action prompt for Seedance 2.0 focusing on spatial geometry and tactical combat between a female swordsman and two enemies.
箭夺一步,剑夺一线 Prompt: 电影级写实质感,纯古风中国仙侠硬派战斗美学。 这一次彻底跳出“再换一种兵器单挑”的模式,核心改成真正的前后景交叉火力几何关系: 前景一名短刀高手负责不断贴身逼位 远景一名弓手并不疯狂乱射,而是专门控制师姐“下一步准备去哪里” 一近一远形成真正有战术意义的双重压力 镜头语言吸收经典武侠对空间关系和高速动作切片的重视,但不能直接复制任何具体电影。 弓手动作底层吸收宋代《射经》中关于以下原则的思想: 身体稳定 目视目标 引弓至满 发射节奏不能过急过缓 只转译成电影化射术逻辑,绝不能声称逐招复原历史射法。 参考与环境 将 @图片 1 和 @图片 2 严格作为人物身份锚点。 本轮新上传的全部背景与地点参考图,共同决定同一套环境 DNA。 正式构图之前,先无声分析并重新整合彼此兼容的: 真实地形 建筑语言 物理尺度 材质年代 植被 水体 天气 山雾 主光方向 倒影关系 空气纵深 前景 / 中景 / 远景空间层次 真实可行走路线 再重新规划成本轮独有、但与全部参考图统一可信的新空间。 从参考图已经存在或自然暗示的空间中,选择一条适合建立纵深攻击关系的战斗轴线,例如: 院落纵深 桥头 山道 廊间 平台 门前通道 或等价空间 但绝不能强行创造和参考图矛盾的新建筑。 背景原则 背景必须始终持续鲜活,但在叙事上绝对中立。 以下元素按照自己的物理规律独立运行: 风 水体 山雾 植被 真丝衣摆 倒影 远处人物 环境声 只有角色或者兵器真正踩踏、撞击、掠过环境时,局部才产生符合真实材质的: 扬尘 水纹 碎屑 布料位移 枝叶晃动 严禁 桥突然断裂 山雾突然帮助隐藏 建筑自行倒塌 树木主动挡箭 任何背景自动创造胜负机会 角色设定 角色 ID A|剑仙师姐 始终是同一个 @图片 1: 25–30 岁成年东亚女性 椭圆脸 白皙自然肤色 深色杏眼 黑色长发半挽,以白玉簪固定 高挑纤细比例 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 角色 ID B|青衣小师妹 始终是同一个 @图片 2: 20–25 岁成年东亚女性 圆润灵动面孔 黑发编辫 娇小比例 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 与同一个年长师父站在真正战斗轴线之外,只作为被动见证者。 年长师父 站在战斗轴线之外 只作为被动见证者 不加入战斗 敌人 敌人严格只有两名: 前景短刀高手 深色古风武服 负责持续近身逼位 远景弓手 位置稳定 不乱射 专门控制师姐的下一步落点 分段结构 0–5s|全景或远景 0.0–0.9s 使用 24mm 固定大全景。 必须一眼看清: 前景刀手 中景师姐 远景弓手 侧后方小师妹 侧后方师父 全场完全静止。 远处弓手先完成稳定开弓,弓弦拉满后突然放箭。 第一箭绝不能直接瞄师姐身体,而是精准射向她最合理的后撤落脚位置。 箭矢钉入该位置真实存在的地面或参考图材质表面,以纯粹攻击线路封住她的安全退路。 几乎同一瞬间,前景刀手从相反角度毫无预警爆发冲入。 立刻硬切 低机位 28mm 侧向高速跟拍: 短刀锋刃贴着摄影机前景猛烈撕过画框。 师姐因为后退线路已经被第一箭封住,只能主动向内改变角度,在最后瞬间转腰避开刀锋,并用银剑进行一次极短的线路碰撞,绝不和敌人站桩互砍。 刀手完全不给喘息,肩部立刻撞入她的防守结构,把她整个身体真实逼偏一个完整身位。 双方瞬间急停。 画面后方必须仍然清楚看见刚才那支箭固定在她原本准备后撤的位置,让观众立刻理解: 远处弓手不是乱射,他是在“封步”。 5–10s|中景或牛仔景 保持: 同一个白衣剑仙 同一个短刀高手 同一个远处弓手 第一支箭 完全连续的地理关系 使用 35mm 摄影机 沿战斗方向快速后退,但尽量保持一整段连续动作,而不是疯狂碎切。 前景敌人连续完成三段逼位: 上路重斩 反向低位切入 身体高度横向压迫 每一次攻击都真正把师姐向另一个看似可以撤退的位置赶过去。 远处同一个弓手绝不能连续机关枪式射箭。 他极其冷静地重新取出 第二支箭,搭箭、开弓、逐渐达到满引,并始终把箭锋瞄准师姐下一步即将落下的位置。 师姐第一次真正察觉:对方不是在射自己,而是在射自己的**“未来位置”**。 她故意做出一个准备后撤的明显起步动作,却在脚步真正落下之前突然主动刹停自身惯性。 远处第二箭就在这一瞬间离弦。 撞击点硬切: 箭矢高速穿过她原本应该进入的位置并命中后方真实表面,而她已经停在原地。 近身刀手判断她无法继续后撤,立刻进一步强攻。 师姐却突然反向暴抢近身,只短暂控制他的短刀线路,并利用两个人高速旋转的位置关系,把这个刀手带到远程弓箭攻击轴线附近。 绝不能静止拿敌人当人肉盾牌,而必须保持双方持续移动。 远处弓手已经准备 第三箭,却因为自己队友的身体短暂污染了射线,只能主动压低弓臂停止发射。 同一个小师妹眼神骤然改变,终于理解师姐正在主动操纵: “人和箭之间的几何关系” 师父始终不动。 10–15s|特写或极近特写 同一个短刀高手立刻意识到自己被带入远程射击轴线,证明敌人拥有真实战术判断。 他迅速旋身离开弓箭线路,同时发动一次凶狠反手刀,为后方弓手重新清出攻击通道。 远处同一个弓手几乎同步重新抬弓,第三支箭达到满引。 此刻师姐短暂陷入真正死局: 近处反手刀已经逼近 远处第三箭也获得干净射线 禁止任何瞬移和无逻辑剑气。 同一个白衣剑仙突然以爆发式斜向抢步切入短刀手持刀手臂外侧,用同一柄银色直剑的剑身平面短促改变刀锋攻击方向,而不是正面对撞力量。 借这一次真实碰撞,她和刀手的身体轴线同时旋转约九十度。 短刀在摄影机前方瞬间横扫满整个画框,形成一次天然兵器遮挡硬切。 下一镜 使用 50mm 新轴线冲击镜头: 远处第三支箭已经真正离弦,但因为师姐刚才主动改变了整个近身搏斗方向,箭矢从两人后方安全高速穿过,并钉入另一侧参考图真实表面。 绝不能靠突然出现的树、雾或者建筑挡箭。 短刀手听到箭矢擦过后的声音和撞击,本能出现不足半拍的视觉注意变化。 这不是变笨,只是高速复杂战斗中真实存在的一瞬间信息反应。 同一个白衣剑仙只利用这一瞬间,用空剑鞘迅速把他的持刀线路向外带离,贴着前肩旋身越过。 银剑不做任何花哨旋转,直接完成一次极短前送。 硬切 85mm 极近特写—— 同一柄银色剑锋高速进入画面,却在距离刀手下颌一指的位置骤然完全刹死。 所有战斗声音在这一瞬间突然坍缩。 只剩: 两个人急促但真实的呼吸 远处第三箭命中后的余震 弓弦轻微震动 白色真丝衣摆逐渐停止运动的声音 镜头迅速将焦点拉向纵深: 远处同一个弓手已经本能伸手准备取第四支箭,但看见近身胜负已经结束后,手停在箭囊边缘,没有继续发射。 同一个年长师父只平静说一句: “箭夺一步,剑夺一线。” 同一个小师妹不说话,只让目光依次扫过: 三支箭的落点 敌人 师姐 终于完全看懂这场战斗真正发生了什么。 立即切黑。
Hedefinize uyan bir örnekle başlayın. Konuyu ve sonucu açıklayın; Video üretimi için kompozisyon, kamera, ışık, ses, hareket veya düzen ayrıntılarını ekleyin. Üretmeden önce ürün, marka, referans ve diyalog değişkenlerini değiştirin.
Kartı açın, önizlemeyi kaynak metinle karşılaştırın ve özgün Promptu Topview AI’a veya uyumlu bir üreticiye kopyalayın. Referansları, kısıtları ve stil notlarını uyarlayın.
Her promptu sonuç garantisi değil, gösterilmiş örnek veya başlangıç noktası olarak kullanın. Marka doğruluğunu, hakları, güvenliği ve model özelliklerini kontrol edin.
Evet. Medya sayfaları ayrı facet sayfalarına bağlanır. Kapsam ve arama amacı açık kalsın diye her sayfada tek sınıflandırma etkindir.
Kitaplık şu anda Seedance 2.5, Seedance 2.0, Wan 3.0, GPT Image 2, Nano Banana Pro, Gemini Omni, Grok Imagine için örnekler içerir. Kullanılabilirlik medya türüne ve filtrelere bağlıdır.
konu olarak sınıflandırılan “Sports Action” koleksiyonundaki Video promptlarını görüntülüyorsunuz.