Realistic Gym Comedy Short Film Prompt
Detailed prompt for generating a 15-second vertical comedy video focusing on a woman in a gym, emphasizing realistic mobile phone cinematography and natural lighting.
تجمع هذه الصفحة أمثلة مطالبات فيديو المصنفة ضمن «Social Lifestyle». قارن النتيجة والتكوين أو اللقطات والصياغة الأصلية قبل تكييف المثال لمشروعك.
1,241 prompts
الاستخدامات
Detailed prompt for generating a 15-second vertical comedy video focusing on a woman in a gym, emphasizing realistic mobile phone cinematography and natural lighting.
15秒超写实搞笑短视频,9:16竖屏,手机原相机纪实质感,真实健身房环境,柔和室内顶光,全程像朋友在旁边随手跟着拍,轻微自然晃动,生活化非常强。 【人物设定】 高颜值年轻亚洲女生,自然淡妆,五官精致舒展,身材匀称,气质温柔清冷,真实路人感,皮肤保留自然纹理和细微汗珠,不网红磨皮,不夸张整容脸,身体比例自然。面部和身材完全保持与参考图一致 镜头1|0-4秒 假象自律 明亮干净的健身房,背景有少量正在训练的人影和器械。女生在自由训练区认真做标准深蹲,动作流畅稳定。镜头从画面右后方手持跟拍,先轻缓后退保持人物全身入镜,再随着她起身微微上抬,像朋友边走边拍,画面有轻微呼吸感和自然晃动,营造她非常自律刻苦的错觉。 镜头2|4-8秒 误导继续训练 硬切到侧面跟拍,女生站立举小哑铃做弯举训练,微微出汗,认真发力,表情冷静专注。镜头贴近她身体侧前方跟随,先轻微横移,再缓慢推近到上半身,背景器械自然掠过,观众以为这是一条自律健身视频。 镜头3|8-12秒 第一层反转 女生突然放下哑铃,表情从专注变成松弛,长舒一口气。镜头继续手持跟随她走到训练凳旁。她坐下,从随身健身包里掏出炸鸡和冰奶茶,动作自然熟练,撕开包装袋。镜头在她掏东西时快速但轻微地推近,形成抓拍式喜剧效果。 镜头4|12-15秒 终极反转 镜头直接推到近距离人脸和炸鸡奶茶同框。女生坦然自然地咬一口炸鸡,再喝一口奶茶,看向镜头,用轻松随意的语气说:“吃饱了才有力气减肥。”说完表情淡定,像在说一件很正常的事。结尾停留在她淡定干饭的反差脸上,手持镜头有极轻微的前后晃动感,强化朋友偷拍感。 【画面质感】 超写实真人实拍,原相机高清画质,真实皮肤纹理、毛孔、汗珠和自然肤色,健身房轻微环境噪点,室内顶光自然,不要电影级精致布光。镜头运动以手持跟拍、轻推近、轻横移为主,节奏随性,不做稳定器丝滑运镜。场景之间直接硬切,不做花哨转场。 【音效】 健身房远处器械碰撞声、轻微脚步声、女生训练呼吸声、包装袋撕开声、炸鸡咀嚼声、奶茶吸管声。台词清晰自然,不要夸张配音感。台词说完后加入短促轻松搞笑音乐点。 【负面提示词】 畸形手指,扭曲肢体,多指,少指,脸部崩坏,五官错位,AI假脸,塑料皮肤,过度美颜,硅胶脸,夸张美瞳,变形身体,比例失调,头身比例异常,悬浮物体,物品穿模,画面闪烁,物体漂移,卡通渲染,3D动画,手绘,插画,屏幕字幕,文字,花字,水印,logo,边框,强烈滤镜,柔光磨皮,稳定器顺滑运镜,固定机位,僵硬摆拍,舞台打光,惨白假光,过度布光,多余人物,杂乱抢镜杂物,夸张表演,尬演,做作表情
A prompt featuring a woman leaning against a wrapped Cybertruck saying "I'm a bad girl."
A lady whose thick frame leans on her pink wrapped cybertruck in Scottdale Az smiling as she says” I’m a baaad chick”
A prompt for generating a nostalgic 2003-style video of a Korean couple on a shopping date, emphasizing authentic camcorder aesthetics and natural interaction.
Create a 30-second ultra-realistic Korean home video from around 2003, casually recorded by a friend using an early-2000s consumer MiniDV camcorder. Capture a sweet, spontaneous shopping date between a young Korean couple at a busy Seoul shopping mall, with imperfect framing, natural interactions, and authentic everyday behavior. CHARACTERS: A young adult Korean woman in her early 20s with long black hair, natural makeup, a fitted pastel-pink top, low-rise blue jeans, sneakers, and a small shoulder bag. Her boyfriend is a young Korean man in his early 20s with slightly messy black hair, a casual striped T-shirt, loose jeans, and sneakers. Maintain consistent faces, outfits, and body proportions throughout. STORY: The couple walks through a crowded Seoul shopping mall, playfully teasing each other while the camera follows them from behind. They enter a toy store filled with colorful plushies. The woman excitedly picks up an oversized teddy bear, hugs it tightly, and makes her boyfriend take a picture of her with it. He jokingly holds a tiny stuffed rabbit beside his face, making her burst into laughter. They choose two soft toys, carry them around the mall, and stop in front of a large store mirror. She pulls him close and takes a mirror selfie with a small early-2000s digital camera while he makes a funny expression behind her. Later, they buy one large ice cream and share it while walking through the mall. She takes a bite, offers it to him, and laughs when he accidentally gets a little ice cream on his lip. She gently wipes it away with her finger as he smiles shyly. They enter an old-fashioned mall elevator, still holding their plush toys. Just before the doors close, he leans toward her and gives her a brief, sweet kiss. She smiles bashfully at the camera as the elevator doors slide shut, ending the recording abruptly. CAMERA & FOOTAGE: Authentic 4-3 early-2000s MiniDV footage, handheld shake, imperfect framing, accidental zooms, autofocus hunting, exposure fluctuations, faded colors, soft digital detail, mild compression noise, and natural motion blur. The camera behaves like a friend casually filming them, sometimes reacting late or briefly losing the action. No polished cinematography or smooth tracking shots. SETTING: A busy Seoul shopping mall circa 2003, crowded walkways, toy stores, colorful plushies, clothing shops, large mirrors, old-fashioned elevators, fluorescent lighting, and shoppers passing naturally in the background. AUDIO: Natural mall chatter, footsteps, shop announcements, toy-store ambience, camera shutter clicks, plastic shopping bags, laughter, ice cream wrapper sounds, elevator chimes, and quiet spontaneous conversation. Casual natural English dialogue. No background music or narration. REALISM & CONTINUITY: Natural couple chemistry, shy smiles, playful teasing, believable hand movements, realistic ice cream interaction, consistent character id
A DIY renovation video generated by Seedance 2.0 showing seashells embedded in epoxy resin flooring.
Vertical 9:16 photorealistic DIY renovation video, satisfying ASMR style. Bright empty room: white walls, grey concrete floor, large white-trimmed window on the left, soft natural daylight. SCENE 1 — A bearded man in a grey t-shirt and blue denim overalls rakes a large pile of colorful seashells (scallops, clams, cone shells) with a landscape rake, spreading them evenly across the entire floor. Fast time-lapse motion. SCENE 2 — A woman with brown hair in red overalls, white t-shirt and rubber boots pours thick creamy white self-leveling epoxy resin from a large grey bucket. The milky liquid flows over the shells, spreading and gradually covering them completely into a glossy white surface. SCENE 3 — A worker in a neon-yellow safety vest and black cap pushes a floor polishing machine back and forth, grinding and buffing the surface, revealing seashells embedded inside a glossy white terrazzo resin floor. SCENE 4 — The man in denim overalls assembles a light oak wooden bed frame, attaches the headboard and slats, places a white mattress, spreads a white duvet and beige pillows. Final static beauty shot: cozy finished bedroom with an oak bed, white bedding and a designer seashell-terrazzo floor glowing in soft daylight. Style: photorealistic, smooth cuts, time-lapse pacing during work phases, natural soft lighting, high detail, no text.
A detailed prompt for Seedance 2.0 to generate a realistic 15-second video of a person jumping from a helicopter onto a trampoline on the sea.
【優先参照画像&名称固定】 @ image1 =記述名称:主人公 主人公の人物同一性、顔、髪型、体型、衣装、装飾、装備、靴の外観基準。 以降の本文では、上記で名称固定した名称のみを使用する。 15秒、3:4、実写フォトリアル、明るい昼の青い海上を舞台にした、音声付きの一続きの映像。全編を通して画面の切替なし。人物参照は主人公の外見だけに用い、三面図の並列表現や文字・見本レイアウトは映像へ取り込まない。人物の同一性、衣装、装飾、体格は全編で維持する。BGM・字幕・テロップ・ロゴなし。 登場人物は主人公、クルーA、クルーB、クルーCの計4名。白い機体に青いラインが入った民間の中型撮影用ヘリコプター。黒いスキッド式着陸脚、開いた幅広の側面スライドドア、乗降用の外側ステップ、ダークグレーの機内。ヘリコプターは最初から最後まで海面から一定の高度を維持する。遠景には海岸線が見え、はるか下の海面上には円形トランポリンが設置されている。主人公は開いたドアの外側ステップに立ち、遠く下のトランポリンを見ている。クルーAはドア寄りに立ち、青いウインドブレーカーと黒い救命ベスト、航空用通信ヘッドセットを着用。クルーBは機内のドア近くに立ち、オレンジ色のウインドブレーカーと黒い救命ベスト、航空用通信ヘッドセットを着用。クルーCは機内の奥にいて、緑色のウインドブレーカーと黒い救命ベスト、航空用通信ヘッドセットを着用する。クルー3名の顔が見える。カメラはヘリコプターのドア付近の同じ撮影位置から、やや広角で主人公とクルー3名、ドアの向こうの海を捉えて開始する。カメラの設置位置は変えず、落下と上昇に応じて上下に向きを変える。風切り音とヘリコプターのローター音が全編に自然に続く。 0.0〜3.0秒:クルーAは主人公の方を見て笑顔で「じゅんびいい?」と問いかける。主人公はクルーAへ顔を向けてうなずき、それからカメラのレンズを直接見つめ、笑顔に緊張と高揚をにじませて「よし、いってきます!」と自然な日本語で勢いよく言う。両者の見えている口元はそれぞれのセリフ全文と一致する。クルーBは笑顔で拳を軽く上げ、クルーCは嬉しそうに笑い、身を少し乗り出してうなずく。主人公は発話後に大きく息を吸い、眼下の円形トランポリンへ目を向け、外側ステップを蹴って飛び出す。 3.0〜6.2秒:主人公がヘリコプターから飛び出した瞬間、クルーBが主人公に向けて「いけー!」と声を上げる。カメラはドア付近の撮影位置を保ったまま素早く下へ向きを変え、海へ落下する主人公を画面の中央付近で追う。主人公は身体を伸ばして落下し、距離が開くにつれて画面内で小さくなる。下方の円形トランポリンが見え、主人公はその中央を目指して近づいていく。カメラを下に向けた間、クルー3名は画面外となるが、機内側から楽しげな歓声が聞こえる。ローター音と風の音が続く。 6.2〜7.7秒:主人公が海面上の円形トランポリンの中央付近へ着地する。張った跳躍面が主人公の重みで大きく沈み、下降が止まった直後に強く押し返す。カメラは下を向いたまま、主人公の着地、跳躍面の沈み込み、反発による上昇への反転を一続きで見せる。着地の衝撃音と反発音が聞こえる。 7.7〜11.6秒:主人公は反発の勢いでヘリコプターへ向かって高く跳ね上がり、膝を胸へ引き寄せて小さく身体を折りたたみ、空中で勢いよく回転する。カメラは同じ撮影位置で上昇する主人公に合わせて上へ向き直る。主人公は近づくほど画面内で大きくなり、開いたドアと外側ステップが再び見えてくる。主人公はヘリコプターの外側ステップの直前まで勢いよく一気に上昇し、ステップに届く瞬間に素早く回転をほどいて脚を伸ばし、飛び出したのと同じ外側ステップへ間髪入れず両足を接地する。着地の瞬間に膝で衝撃を吸収して直ちに上体を起こし、冒頭と同じ位置・身体の向き・立ち姿に戻る。ヘリへの接近、回転解除、両足の接地、姿勢の復帰を通常速度で途切れなく続く、鋭く素早い一連の動きとして撮影する。ヘリコプターの海面からの高度は変わらない。 11.6〜15.0秒:カメラは冒頭と同じドア周辺の向きへ戻る。クルーAは主人公に向かって笑顔で拍手する。クルーBは喜んで拳を突き上げ、「やったーー!」と短く声を上げる。クルーCは主人公を見て笑顔で手をたたく。主人公は弾む呼吸のままカメラのレンズへ顔を向け、目を輝かせ、無事に戻れた興奮と喜びを込めて「やばい!やばい、さいこうだったよ!」と明るく自然な声で話す。クルーBと主人公の発話時には口元の動きをそれぞれのセリフ全文と一致させる。最後のフレームは、主人公が最初と同じ外側ステップに立ち、カメラへ話し終えて興奮した表情を見せ、背後でクルーAとクルーCが拍手し、クルーBが喜んでいる状態。クルーの拍手とローター音が続いたまま15秒で終わる。
A simple prompt for using Grok Imagine to generate a funny video of Elon Musk driving a Tesla through the streets of New York.
Funny video. Elon Musk and I are driving Teslas through the streets of New York.
A nostalgic first-person perspective video simulating a 2000s home camcorder recording of a child's day.
STYLE RULE: First-person POV throughout, shot like a 2000 home camcorder (MiniDV): soft focus, slight color bleed, warm grain, 4:3 feel, orange timestamp "OCT 21 2000" in the corner. Our hands are always visible: a kid's hands, baggy hoodie sleeves, a cheap digital watch. Same hands and clothes in every shot. No celebrities, no logos, no brand names. [0-5s] SHOT 1, MORNING AT HOME: POV waking up in a small bedroom with posters on the wall and a CRT TV in the corner. Hand slaps a wind-up alarm clock. Walk down the hallway past a wall-mounted landline phone with a curly cord. Sit at the kitchen table with a bowl of cereal while cartoons play on a small TV. Dad reads a newspaper, Mom calls "Hurry up, the bus is coming!" Camera: handheld, slightly shaky, warm morning window light. [5-10s] SHOT 2, WALK AND SCHOOL BUS: POV grabbing a heavy backpack and running out the door. A friend waves from across the street and joins the walk. Board a yellow school bus, sit by the window, friends trade stickers and a folded note. Outside: quiet suburban street, soft sun flare. Camera: handheld, glancing between friend and window. [10-15s] SHOT 3, CLASSROOM: POV at a wooden desk with gel pens and a pencil case. Teacher writes on a green chalkboard, an overhead projector hums. Secretly pass a note folded into a triangle to a friend, who passes one back. Beige computer in the corner of the room. Camera: slow pan across the class, then close on the note. [15-20s] SHOT 4, LUNCH AND PLAYGROUND: POV in the loud cafeteria with a tray, pizza and chocolate milk, friends laughing. Cut to the playground: trade cards and stickers on the ground, chase friends, hopscotch and tag. Camera: wide, turning left and right, bright overcast daylight. [20-25s] SHOT 5, AFTER SCHOOL: POV riding a bike down the street with friends, scooters and rollerblades beside us, golden hour light. Stop at a corner shop, buy candy with coins. Later at a friend's house: sit on carpet in front of a CRT TV playing a 90s console game, controllers in hand, snacks everywhere, friends shouting and bumping shoulders. Camera: handheld, intimate, tilting to the screen. [25-30s] SHOT 6, EVENING: POV at the family dinner table, parents and siblings passing plates. Sit on the couch, family sitcom on the one living-room TV. Then at the shared family computer: dial-up screeches, a chat window pops up with a friend. Mom calls "Time for bed!" Fade to a dark room lit only by the monitor glow. Camera: slow push-in to the screen. CAMERA RULE: Handheld first-person only, no third-person angles, shallow depth, warm lens flare, subtle VHS tracking glitch at each cut. SOUND RULE: Layered ambient audio: alarm bell, cartoon TV, bus chatter, chalkboard scratch, cafeteria roar, bike wheels, console sounds, dial-up modem screech. Soft nostalgic instrumental music in the background. Only short kid voices and parents calling, no narrati
A prompt for a 15-second video of a cosplayer at Comiket changing poses every 3 seconds with character consistency.
🎬 Gemini監督への指示 アップロードした3枚の画像(全身、アップ、ミディアム)を上手く使って5シーンの切り替えて「コミケ会場でコスプレイヤーが撮影会に決めポーズや映えるポージングを3秒毎(1シーン内で2ポージング)に変える」、15秒の動画の日本語プロンプトを作ってください。最後はクローズアップして決めポーズで片目でウインクさせてください。 BGM「(画像の雰囲気に合ったBGMを考えて)」 人物の顔や髪型は一貫性を維持させてください。画像生成や動画生成は不要。 プロンプト中の画像1(全身)は@Image1、画像2(アップ)は@Image2、画像3(ミディアム)は@Image3 に置き換えてください。 🎥 動画生成プロンプト(Grok Imagine) 【基本設定・一貫性】 * 人物・衣装の参照: @Image1(全身)、@Image2(アップ)、@Image3(ミディアム)の女性コスプレイヤー。銀髪の三つ編みヘアー、エルフ耳、青と白のファンタジー衣装、顔立ちおよび髪型の一貫性を維持。 * ロケーション: 賑わうコミケ会場(背景にカメラマンや展示ブースのボケ感)。 * BGM提案: 爽やかで明るいアップテンポなEDM/アニソン風ポップス(ファンタジー感のあるキラキラしたシンセ音入り)。 【タイムライン・構成(全15秒)】 * シーン1(0:00 - 0:03)/ 参照: @Image1 * 画角: フルショット(全身) * ポーズ1(0〜1.5秒): 衣装のスカートを軽く持ち上げて優雅におじぎをするようなポーズ。 * ポーズ2(1.5〜3秒): 両手を広げて華やかに微笑み、全身の衣装を見せるポーズ。 * シーン2(0:03 - 0:06)/ 参照: @Image3 * 画角: ミディアムショット(腰上) * ポーズ1(3〜4.5秒): 胸の前で両手でハートマークを作り、首を少し傾けて微笑む。 * ポーズ2(4.5〜6秒): 片手を顎に当て、カメラを目線で追いかけながらクールな表情を作る。 * シーン3(0:06 - 0:09)/ 参照: @Image1 * 画角: アングルを変えたフルショット(斜め全身) * ポーズ1(6〜7.5秒): 身体を斜めにひねり、髪に軽く手を添えて振り返るポーズ。 * ポーズ2(7.5〜9秒): 片足を一歩前に出し、ファンタジー作品のヒロイン風に手をカメラへ差し出すポーズ。 * シーン4(0:09 - 0:12)/ 参照: @Image3 * 画角: ミディアムショット * ポーズ1(9〜10.5秒): 両手を頬に添えて、驚いたような可愛らしいポーズ。 * ポーズ2(10.5〜12秒): カメラに向かって爽やかに手を振るポーズ。 * シーン5(0:12 - 0:15)/ 参照: @Image2 * 画角: クローズアップ(顔〜肩上) * ポーズ1(12〜13.5秒): カメラをじっと見つめ、優しく微笑む。 * ポーズ2(13.5〜15秒): カメラに向かって決めポーズを取り、片目で可愛らしくウインクして笑顔で静止。
A prompt for generating a realistic, handheld-style video of a young Korean woman running errands in Seoul, capturing authentic life details and natural light.
Create a 30-second, 1080p ultra-realistic personal home video of a young Korean woman running a small summer errand in an old Seoul residential neighborhood. It should feel like an unplanned recording by a friend using an early-2000s DV camcorder. SUBJECT: A naturally pretty Korean woman in her early 20s, realistic skin texture, minimal makeup, long black hair in a loose low ponytail with wispy strands. She wears a white sleeveless knit top, faded-blue denim shorts, white ankle socks, black canvas sneakers, and a thin silver bracelet. Maintain identical face, hairstyle, outfit, and proportions throughout. SETTING & STYLE: Quiet, lived-in Seoul streets with narrow concrete lanes, modest houses, weathered walls, potted flowers, parked bicycles, overhead wires, hanging laundry, and a tiny local shop. Warm summer afternoon, ordinary neighborhood life, no recognizable brands or tourist attractions. Use shaky handheld footage, imperfect framing, occasional autofocus hunting, exposure shifts, faded colors, soft digital detail, mild noise, motion blur, and subtle camcorder handling sounds. No stabilization, cinematic camera moves, dramatic lighting, or commercial polish. 30-SECOND SEQUENCE: - 0–5s: She exits her house with a cloth tote, checks the door, notices the camera, smiles, and says, “I'm just going to the shop.” - 5–11s: She greets an elderly neighbor with a polite bow, then steps aside as a little girl rides past on a bicycle, its bell ringing. The camera briefly follows the bicycle. - 11–18s: Wind shakes a flowering pot, scattering small flowers. She picks one up, gently returns it to the planter's edge, smiles at the camera, and continues. - 18–25s: At a tiny neighborhood shop, she takes a reusable container from her tote, receives a small paper-wrapped item from the shopkeeper, thanks them, and puts it away. - 25–30s: She walks back past the same houses and bicycles. Her ponytail moves in the breeze as she waves playfully at the camera, reaches her doorway, turns back with a smile, and the footage abruptly cuts to black. AUDIO: Natural location sound only—footsteps, bicycle bell, distant scooters, birds, summer insects, rustling leaves, faint neighborhood chatter, shop door, and subtle camcorder noise. No music, narration, added sound effects, or other dialogue. IMPORTANT: Prioritize authentic everyday behavior, natural expressions, realistic timing, consistent identity, and the imperfect charm of an old personal home video. Avoid staged acting, exaggerated gestures, artificial skin, visual glitches, or an AI-generated appearance.
A satisfying renovation video showing gummy bears embedded in an epoxy resin floor, generated by Seedance 2.0.
Vertical 9:16 photorealistic satisfying renovation video, one continuous scene in a bright empty room with white walls, bare wooden floor and a large sunlit window on the right. Shot 1: A bearded man in a gray t-shirt and blue denim overalls vigorously rakes a huge conical pile of thousands of colorful jelly bean candies, spreading them into an even layer that covers the entire floor. Shot 2: A woman in red overalls and a gray t-shirt pours thick glossy white epoxy resin from a large white bucket; the creamy liquid flows over the candy layer and spreads outward, fully covering the colorful beans. Shot 3: A worker in a neon-yellow safety vest and black cap grinds the cured white floor with a professional floor polishing machine; the top layer is buffed away, revealing thousands of colorful jelly beans embedded under a crystal-clear, mirror-glossy epoxy surface, like candy terrazzo. Shot 4: Two men in black t-shirts and black caps quickly assemble a wooden bed frame, set a white mattress on it, and make the bed with crisp white bedding, all in fast-forward motion. Final shot: Slow beauty shot of the finished minimalist bedroom — a luxurious mirror-shiny floor filled with colorful candy under transparent epoxy, sunlight reflecting off the polished surface. No people. Style: viral satisfying DIY renovation timelapse, static wide-angle camera from the doorway, natural daylight, ultra-detailed, smooth realistic physics of pouring liquid and rolling candy.
A prompt for a 30-second video showing a Korean girl enjoying cherry blossoms and coffee in a dramatic setting.
Create a video of beautiful Korean girls in 16:9 landscape format, exactly 30 seconds long, featuring a beautiful young Korean woman with black hair tied in a ponytail with a burgundy ribbon, wearing an olive-green top, a camouflage jacket, matching trousers, and carrying a black shoulder bag. She walks along a modern Korean roadside on a beautiful spring day surrounded by blooming cherry blossom trees. Three stylish Korean female friends wait beside a pale-yellow SUV, smiling and waving at her. She approaches them, and they greet each other warmly while holding takeaway coffee cups. One friend opens the SUV's rear hatch as the girls gather around, laughing and chatting naturally. Another friend takes a selfie with the group using her smartphone. The main woman playfully poses while holding her coffee, surrounded by beautiful pink cherry blossoms. Finally, show a cinematic close-up of her holding the coffee cup, wearing a small white cherry blossom hair clip, gently sipping her drink and smiling peacefully in the sunlight. Use photorealistic Korean drama cinematography, natural skin texture, realistic facial expressions, soft daylight, smooth camera movements, detailed clothing, and consistent faces and outfits throughout the video. Add gentle birdsong, a spring breeze, friendly laughter, and soft background music. Maintain smooth transitions, natural body movements, and high-quality cinematic visuals throughout the entire 30-second video.
A complex video prompt depicting a playful scene of a girl riding a giant cat in a misty Japanese city at dawn, with strict audio and camera constraints.
SECONDS • ULTRA-REALISTIC LIVE ACTION • IMAX LARGE-FORMAT LOOK • CINEMATIC KOREAN-JAPANESE MORNING ATMOSPHERE • THICK NATURAL CITY FOG • SOFT EARLY-MORNING SUNLIGHT • FRESH CITY AIR • PLAYFUL • GEMAS • GOOFY • AGGRESSIVE HANDHELD • CANDID • IMPERFECT • EXTREME SPEED • SLICE OF SLICE • 16:9 A modern Japanese city neighborhood in the early morning, partially covered by thick natural fog. A clean Korean-Japanese minimalist home opens onto a quiet residential street. Compact modern houses, narrow asphalt roads, small gardens, utility poles, overhead wires, parked bicycles, roadside signs and distant apartment buildings gradually emerge through the mist. The city is already beginning to wake up, with faint traffic and pedestrians barely visible through the fog. MAIN SUBJECT @image1 exactly like the attached reference. Outfit exactly like the attached reference. Wearing simple PINK FLIP-FLOPS outdoors. Playful, cute, gemas, naturally expressive and energetic. Never posed. @image2 exactly like the attached reference. Preserve the exact appearance, fur pattern, face, colors, body proportions, amber eyes, large paws, fluffy white fur with orange-and-black patches and short bobbed tail throughout the entire scene. Gigantic scale with realistic feline anatomy, weight, balance, acceleration and momentum. No clothing, saddle, armor or accessories. @image1 naturally interacts with @image2. She searches for a small bench, uses it to climb onto the cat, then grips @image2’s thick fur with BOTH HANDS throughout the ride. Fingers visibly sink into the fluffy coat. Her body follows every movement naturally. CAMERA Aggressive reactive handheld. Candid, imperfect and physically operated. Natural camera sway, micro-jolts, slight focus corrections, imperfect framing, brief motion blur and delayed reactions. Camera movement reacts directly to the subjects and environment. NO gimbal. NO stabilized look. NO smooth tracking. NO locked shots. NO static camera. NO robotic movement. NO predictable camera movement. NO symmetrical composition. NO forced centering. NO polished commercial cinematography. AUDIO ABSOLUTELY NO MUSIC. NO BACKGROUND MUSIC. NO AMBIENT MUSIC. NO MUSICAL SCORE. NO SONG. NO MELODY. NATURAL LOCATION SOUND ONLY. Soft birds, distant traffic, faint motorcycles, light wind, leaves, footsteps, flip-flops against the ground, fabric movement, cat breathing, giant paws striking asphalt and natural feline sounds. @image1 says ONLY: “산책 가자!” @image2 responds naturally: “냐옹!” No other dialogue. SCENE 00:00–00:02.2 REAR FOLLOW — INSIDE HOUSE → FRONT DOOR → OUTSIDE. The camera begins INSIDE the modern minimalist house, directly behind @image1. @image1 walks naturally toward the closed front door. The camera follows closely behind, framing her back, shoulders and the back of her head. She opens the door FROM INSIDE. Soft early-morning sunlight and thick natural fog appear beyond the doorway. @image1 steps outside wearing simple PINK FLIP-FLOPS. The camera follows directly behind her through the doorway. She walks along the small front pathway. NO DIALOGUE. The foggy city neighborhood gradually appears ahead. @image2 is relaxing quietly in the front yard. @image1 notices the gigantic cat. CUT. 00:02.2–00:04.2 REAR HANDHELD FOLLOW — FINDING THE BENCH. @image1 walks toward @image2. She realizes the gigantic cat is too tall to climb onto directly. She notices a SMALL WOODEN BENCH. She moves the bench beside @image2. The camera follows naturally from behind. @image2 watches calmly. The cat understands what she wants and slowly lowers its entire body into a deep crouch, bringing its back to approximately bench height. @image1 reacts with a small delighted smile. CUT. 00:04.2–00:06.3 CLOSE REAR / SIDE-REAR HANDHELD — MOUNTING. @image1 steps onto the small bench and carefully climbs onto @image2’s enormous back. She immediately grips the thick fur with BOTH HANDS, fingers visibly sinking into the fluffy coat. She settles naturally and gently strokes @image2’s head. @image2 slightly lifts its head into her touch. @image1 leans forward playfully. She says: “산책 가자!” @image2 responds: “냐옹!” The cat’s ears point forward. Its body subtly tenses. CUT. 00:06.3–00:08.0 AGGRESSIVE HANDHELD — SUDDEN TAKEOFF. Without warning, @image2 EXPLODES FORWARD. The camera reacts slightly late. @image1 grips the thick fur with BOTH HANDS. Her PINK FLIP-FLOPS bounce naturally against the cat’s sides. @image2 races toward the front fence. @image1 leans forward with the acceleration. @image2 plants its enormous paws— HUGE JUMP OVER THE FENCE. The camera violently tilts upward. Beyond the fence, a modern Japanese city street is almost completely swallowed by thick morning fog. HARD CUT ON JUMP. 00:08.0–00:10.0 AGGRESSIVE REAR 3/4 CHASE — FOGGY CITY MORNING. @image2 lands heavily on the asphalt. THUD! It immediately accelerates deeper into the city. @image1 remains firmly gripping the thick fur with BOTH HANDS. The giant cat races through the fog-covered morning street, passing utility poles, parked bicycles, compact houses, roadside signs and faint early traffic. The camera struggles to keep up, bouncing and swinging naturally. Distant apartment buildings emerge through the mist. @image2 runs deeper into the fog. The cat and rider gradually disappear into the dense morning mist. Only the foggy city street remains. HARD CUT. NO BLACK. CUT DIRECTLY INTO SCENE 1. STYLE Ultra-realistic live action. IMAX large-format image quality. Modern Japanese city neighborhood at early morning. Thick natural city fog. Soft warm sunlight filtering through mist. Korean-Japanese minimalist home. Rear-follow opening from inside the house. @image1 opens the front door from inside and walks outside. She finds a small wooden bench, uses it to mount the gigantic Japanese Bobtail, gently strokes its head and says “산책 가자!” before the cat suddenly takes off. Playful. Cute. GEMAS. GOOFY. Energetic. Natural rider-cat interaction. Gigantic cat deliberately lowers its body so @image1 can mount. @image1 grips fur with BOTH HANDS throughout the ride. Pink flip-flops outdoors. Aggressive reactive handheld. Candid. Imperfect. Natural motion blur. Sudden acceleration. Huge fence jump. Foggy waking city. Cat and rider naturally disappear into the morning fog. NO BLASSSHH. NO LIGHT BURST. NO SPECIAL EFFECT TRANSITION. NO SUPERNATURAL TRANSITION. NO MUSIC. NO BACKGROUND MUSIC. NO AMBIENT MUSIC. NO MUSICAL SCORE. NATURAL LOCATION SOUND ONLY. HARD CUT directly into SCENE 1. SLICE OF SLICE. NO POLISHED COMMERCIAL LOOK. 4K.
A detailed prompt for generating a realistic video of a combine harvester in an autumn rice field, focusing on camera and character movement.
秋の田んぼ。稲をかき分けて迫るコンバインの刈り取り部。運転席で目を丸くするさくら。畦のおじさんが腕を前へまっすぐ伸ばす。レバーを倒すと機体が奥へよれ、今度は手前へよれすぎる。土手の上から見下ろすと、刈り跡はへびのようにくねっていた。おじさんがしゃがんで、稲の株の列を手のひらでなぞる。 あごひもを結び直して、レバーを握る。分草板の先を株の列に合わせると、機体はぶれずにまっすぐ進む。最後の稲が吸い込まれる。見下ろすと、くねった跡の隣に一本だけまっすぐな刈り跡。軽トラの荷台に、金色のもみが滝のように流れ落ちる。運転席で両手を上げる。 一緒に来た友達が手持ちで撮った記録。1カット2秒前後、セリフ・字幕・BGMなし。画面に出るのは二人だけ。コンバイン1台、軽トラ1台。機体・服・帽子は文字なしの無地。コンバインの形と田んぼの配置は、人のいない参照画像で固定。
A retro-style Vlog prompt simulating early 2000s MiniDV quality, documenting a Korean woman preparing for her first job interview.
GETTING READY FOR HER FIRST JOB INTERVIEW Create an ultra-realistic personal vlog filmed by a friend using a consumer MiniDV camcorder in South Korea in 2003. A young Korean woman nervously prepares for her first job interview in her modest bedroom, from choosing her outfit to rushing out the door. CHARACTER & CONTINUITY A Korean woman in her early 20s with a soft oval face, natural skin texture, shoulder-length dark brown hair, and side-swept bangs. She starts in a T-shirt and home trousers, then changes into a white blouse, dark knee-length skirt, dark cardigan, and black shoes. Maintain consistent identity, hairstyle, outfit, and props. SCENE 1 — OUTFIT (0–5s) She compares two cardigans against her interview clothes, hesitates, chooses the darker one, and gives the camera a nervous smile. A wooden desk, paper calendar, and handwritten interview note establish the year. SCENE 2 — IRONING (5–10s) She carefully irons her blouse, struggles briefly with a sleeve, smooths it out, and checks the collar. A corded telephone and household calendar appear in the background. The iron stays safely on the board when not in use. SCENE 3 — PRACTICE (10–15s) Dressed for the interview, she practices her introduction in a mirror, forgets her words, checks handwritten notes, and tries again. She notices the camera and laughs shyly. SCENE 4 — DOCUMENTS (15–20s) She organizes her résumé and application papers into a folder. One page falls; she retrieves it and puts it back. Seeing the clock, she places the folder in her shoulder bag and checks for her purse and keys. SCENE 5 — FINAL CHECK (20–26s) She smooths her blouse, adjusts her cardigan, fixes her collar, and tucks back loose hair. After attempting a confident smile, she notices the time and grabs her bag in a hurry. SCENE 6 — DEPARTURE (26–30s) She hurries to the door, checks her keys, slips into her black shoes, and gives the camera one last nervous smile. The camera follows her into the hallway before an abrupt recording cut. VISUAL STYLE & SOUND Authentic early-2000s MiniDV footage: soft SD detail, mild video noise, imperfect handheld framing, autofocus hunting, accidental zooms, and brief exposure shifts. Use natural lighting, realistic colors, and period-appropriate Korean apartment interiors. Include fabric rustling, ironing, paper shuffling, faint clock ticking, footsteps, jingling keys, and the door opening. Dialogue is quiet, natural Korean speech. CONTINUITY RULES Keep facial identity, anatomy, lighting, and room layout consistent. Use a natural transition for the outfit change. Once dressed, her outfit stays unchanged. Documents remain in the folder and bag after packing; account for the keys before departure. Avoid modern technology, cinematic grading, fake VHS overlays, exaggerated acting, face morphing, duplicated fingers, teleportation, instant outfit changes, and background music
A detailed narrative prompt for generating a video of a child operating an excavator in an autumn setting, designed for Seedance 2.5 with technical parameters.
秋晴れの重機体験場。巨大なバケットが地面に突き刺さり、土が飛ぶ。運転席で目を丸くするさくら。指導係のおじさんが手のひらで「ゆっくり」。かくかく伸びるアーム。爪がタイヤの穴を通り過ぎ、そのまま土の山に突き刺さる。山が崩れ、土砂がタイヤを押し流す。固まるさくら、吹き出すおじさん。土煙が晴れると、タイヤは杭のすぐ横まで来ていた。 あごひもを締め直して、レバーを握る。今度はなめらかに下りるアーム。爪がタイヤの穴に引っかかる。持ち上がって、空にぶら下がる黒いタイヤ。じわじわ左へ、杭の真上。ゆっくり下ろすと、杭が穴を通って、どすん。運転席で両手を突き上げる。 一緒に来た友達が手持ちで撮った記録。1カット2秒前後、セリフ・字幕・BGMなし。画面に出るのは二人だけ。ショベルカー1台、杭1本、タイヤ1本、土の山1つ。機体・ヘルメット・服は文字なしの無地。体験場の配置は、人のいない引きの参照画像で固定。
A prompt for a hyper-realistic smartphone-style video showing a humpback whale floating over downtown Chicago streets.
A single continuous 30-second one-take filmed on a smartphone, vertical 9:16, handheld with slight natural shake. A busy downtown street at dusk after light rain, wet asphalt reflecting neon signs and car headlights. The camera operator is a pedestrian standing on the sidewalk, filming casually. 0-6s: The camera pans across the street. People walk past, a delivery rider waits at a red light. Ambient city sound, distant sirens. Then a few people stop and look up. The camera tilts up with a slight delay, as a real person's would. 6-14s: A huge humpback whale glides slowly out from behind the glass towers, floating about 40 meters above the street. Photoreal skin texture, barnacles, water droplets falling off its fins and onto the road. Its shadow passes over cars and crowds. People gasp, raise phones, and one person grabs a friend's arm. 14-24s: The whale drifts overhead and lets out a deep, low call that vibrates through the street. Windows reflect its body, puddles ripple from the sound, and a flag and trees sway in the air it pushes. The camera shakes slightly and refocuses. 24-30s: It continues down the avenue, tail sweeping gently, and fades into low clouds between the buildings. The shot ends with the crowd still looking up and the camera lowering. Realism: natural phone-camera behavior, mild auto-exposure shifts, slight lens flare from the neon, real-world scale and weight, no cartoon glow, no text or logos on screen. Ordinary, unposed pedestrians with natural reactions. Audio: @Audio1 or synchronized ambient city sound, crowd murmurs, wind, and a deep whale call. No music, no narration. Style: photorealistic, shot-on-iPhone look, natural color, light grain, realistic motion blur, sharp 4K.
A detailed prompt for Seedance 2.5 to generate a haunted house prank scene featuring a girl named Sakura in a Japanese house corridor.
日本家屋のお化け屋敷、ハロウィン期間。カボチャのランタンが並ぶ廊下で、押し入れからおばけが飛び出して両袖を上げる。カップルはくすっと笑って、横をすり抜けていく。肩を落として押し入れへ。めくり布を持ち上げると、さくらの素顔。口を結ぶ。今度は待ちすぎて、通り過ぎた主婦二人の背中に両袖を上げる。二人はおしゃべりしたまま去っていく。インカムの先輩が肩をたたき、懐中電灯を二回点滅させて「これが合図」。 押し入れの中で、息を整えてうなずく。隙間の向こうから、悪魔の角とマントの男子二人がこわごわ近づいてくる。障子の陰で、先輩のライトがぱっ、ぱっ。二人が飛び上がって絶叫し、抱き合う。逃げていく二人。残されたおばけは、その悲鳴にびっくりして尻もち。めくり布がめくれて、目を丸くした素顔。先輩の手につかまって立ち上がり、照れ笑い。押し入れへ戻る。 スタッフ仲間が手持ちで撮った記録。1カット2秒前後、セリフ・字幕・BGMなし。おばけはさくら一人だけ。押し入れは画面の左、先輩の障子は右、客はいつも奥から手前へ一方向。着ぐるみは顔のないマネキンに着せた参照画像どおり。
A detailed prompt for generating a 30-second hyper-realistic 2003 Korean home video using MiniDV aesthetics, showing a young woman's evening routine.
Create a 30-second ultra-realistic Korean home video from around 2003, casually recorded by a friend using an early-2000s consumer MiniDV camcorder. Capture an ordinary, slightly lazy evening with spontaneous moments, imperfect framing, and authentic everyday behavior. **CHARACTER:** A young adult Korean woman in her early 20s with natural beauty, realistic skin texture, minimal makeup, and long black hair loosely tied in a messy side ponytail. She wears a fitted pastel-blue short top, loose cream pajama-style pants, black sneakers, and a simple silver necklace. Maintain consistent facial identity, outfit, and body proportions throughout. **STORY:** She wakes up from an evening nap in her modest Seoul apartment, looking sleepy and confused. She sits on the bed, rubs her eyes, stretches lazily, and checks the time on an old bedside clock. Her messy ponytail is half undone, and she yawns at the camera before saying, “Wait… is it evening already?” She slips on her sneakers, grabs a little shopping bag, and leaves the apartment. The camera follows her down the stairs and through a narrow residential street filled with parked bicycles, overhead wires, small shops, and warm evening sunlight. She visits a tiny neighborhood convenience shop, picks up potato chips, chocolate, instant noodles, and a bottled drink, then examines a snack packet suspiciously before laughing at the camera. She pays at the counter and walks outside with her purchases. Feeling thirsty, she stops at an outdoor public water tap beside a small neighborhood park. She unties her ponytail, lets her long black hair fall naturally around her shoulders, splashes a little water onto her face, and drinks directly from the running tap with her hands cupped beneath it. Water drips from her fingers, and she laughs when a little splashes onto her top. She wipes her face with her hand and shakes her loose hair back casually. She sits on a low concrete wall beneath the trees, opens her chips, takes a crunchy bite, and watches children playing and neighbors walking past. She offers a snack toward the camera as if sharing it with her friend filming. Finally, she walks back home along the quiet street, carrying her snacks. At the apartment entrance, she turns toward the camera with a sleepy but happy smile and says, “Okay, now I'm ready for the evening!” The footage ends abruptly as her friend laughs and the camera tilts toward the ground. **CAMERA & FOOTAGE:** Authentic 4 3 early-2000s MiniDV footage, handheld shake, imperfect framing, delayed camera reactions, accidental zooms, autofocus hunting, exposure fluctuations, faded colors, soft digital detail, mild compression noise, and natural motion blur. No polished cinematography or smooth tracking shots. **SETTING:** A modest Seoul apartment and an older Korean residential neighborhood circa 2003, narrow lanes, small convenience shops, public outdoor water taps, concrete w
A detailed prompt for a 1-minute selfie-style video inside a Tesla Model 3 discussing the EV lifestyle.
She sitting inside of her model 3 selfie style drinking in n out soft drink talking about how she choose EV life because she hates getting oil changes from jiffy line or Midas 1080p video 1 min
A prompt for generating a 20-second realistic cinematic travel Vlog featuring a young woman exploring a charming European old town.
Create a realistic 20-second cinematic travel vlog featuring a young woman exploring a charming European old town. She walks through narrow cobblestone streets lined with colorful historic buildings, smiles naturally at the camera, stops at a traditional bakery to taste a fresh pastry, and enjoys the lively outdoor market with colorful umbrellas. End with her standing at a beautiful hilltop viewpoint overlooking red rooftops and the city skyline. Keep the same woman's face, hairstyle, and outfit consistent throughout the video. Natural expressions, realistic walking movements, authentic hand gestures, soft daylight, cinematic camera movement, detailed textures, natural colors, and a premium travel influencer aesthetic. Smooth transitions between scenes, realistic physics, subtle background activity, vertical 9:16 format, ultra-realistic 4K quality. No text, no subtitles, no logos, no watermarks.
A prompt for a 20-second cinematic city walk video in Seoul featuring a couple, rhythm control, and title overlays.
Seoul, South Korea 20-Second Cinematic City Tour | Seedance 2.5 | 16:9 Use the supplied image as the exact opening frame. Preserve both characters' faces, hairstyles, outfits, and natural proportions throughout. Ultra-realistic cinematic photography, natural skin texture, authentic Seoul locations, lively crowds, and realistic lighting. Dynamic tracking cameras, smooth lateral pans, instantaneous hard cuts, natural movement. No slow motion, no morphing. No subtitles except the specified opening location title. Opening Title — Scene 1 Only Display "Seoul, South Korea" during Scene 1 only. Poppins Semi-Bold (600), 42px at 1080p, white #FFFFFF text on a deep charcoal-slate #17212B background at 60% opacity. Softly rounded rectangle, consistent padding, bottom-center in the lower-third video-safe area. Keep visible approximately 2 seconds. Never render floating white text or position it at the top. Scene 1 — Seoul Street (0–2.5s) Begin with the exact supplied image. The couple briefly holds eye contact with the camera, then turns and walks into the busy evening street. Neon signs and pedestrians surround them. Display the specified opening title. Scene 2 — Seongsu Design District (2.5–4s) Diagonal tracking shot as the couple walks past a fashionable industrial-style concept store. Contemporary displays, stylish shoppers, and active street life. Scene 3 — Hannam-dong Portrait (4–7.5s) Beautiful close-up of both faces, looking directly into the camera with confident, natural model-like expressions. Smooth right-to-left camera pan across their faces. Soft city lights and passing pedestrians behind them. Scene 4 — Euljiro After Dark (7.5–9s) Quick lateral tracking shot of the couple moving through a narrow, lively alley filled with Korean neon signs, intimate bars, and nighttime crowds. Scene 5 — Modern Korean Restaurant (9–12.5s) The couple sits together at a stylish restaurant counter. A server places Korean dishes before them. They share a bite, exchange a playful look, and laugh naturally. Warm lighting, lively restaurant atmosphere. Scene 6 — Vinyl Listening Bar (12.5–14s) Inside a dimly lit listening bar, the man flips through vinyl records while the woman leans beside him. Warm lamps, record shelves, and turntables. Scene 7 — Haebangchon Night Street (14–16.5s) Handheld tracking alongside the couple walking downhill past independent cafés, creative bars, and lively outdoor gatherings. Colorful nighttime street activity. Scene 8 — Seoul Rooftop (16.5–20s) At a stylish rooftop bar overlooking Seoul, Namsan Seoul Tower glows in the distance. The couple shares a quiet conversation, then turns toward the camera as it drifts smoothly past them. End on a beautiful, intimate portrait of both characters. Production Direction Maintain exact character identity and wardrobe throughout. Both characters remain prominent in every shot. Authentic Korean architecture, signage, food, and street culture. Natural interactions, expressive faces, varied camera angles, and continuous background activity. Follow the specified shot durations, alternating quick editorial cuts with longer character-focused moments. Clean instantaneous hard cuts only. No artificial transitions, no slow motion, no plastic skin, no visual distortions. No generated music; preserve natural environmental sounds and brief conversational ambience.
A detailed video generation prompt for Seedance 2.5 to create a realistic early 2000s Korean home video style short film of a woman preparing for a date.
GETTING READY FOR A BLIND DATE SOUTH KOREA, 2003 Ultra-realistic early-2000s home-video footage of the same young Korean woman (reference image) preparing nervously for her first blind date in a modest Korean bedroom. Scene 1 (0–5s): She compares outfits on her bed, reads a handwritten meeting note, checks the clock, and smiles nervously at the camera. Scene 2 (5–10s): She brushes her shoulder-length hair, struggles with stubborn bangs while using a curling iron, then smiles with relief. Scene 3 (10–15s): She applies subtle makeup and rosy lipstick, accidentally smudges the corner, giggles, and fixes it with a tissue. Scene 4 (15–20s): She chooses a pastel cardigan, changes naturally, adjusts her knee-length skirt, puts on small earrings, and grabs her shoulder bag. Scene 5 (20–26s): She checks herself in a full-length mirror, fixes her hair and bag strap, attempts a confident smile, then laughs awkwardly at herself. Scene 6 (26–30s): She heads out, remembers her forgotten purse, rushes back, grabs it, and hurries through the apartment hallway toward daylight. End with a shaky, abrupt camcorder cut. Visual style: Genuine 2003 South Korean consumer MiniDV footage, standard-definition softness, mild video noise, imperfect autofocus, shaky handheld framing, natural exposure shifts, and unpolished colors. Modest period-authentic bedroom with wooden furniture, printed photos, magazines, a CD player, and a corded landline. Natural daylight, realistic ambient sounds, minimal spontaneous laughter. Continuity: Preserve the exact reference face, age, proportions, room layout, and realistic movements. Maintain identical final outfit, hairstyle, makeup, and accessories from Scene 4 onward. Every change must occur physically and naturally. Avoid: Modern electronics, cinematic grading, 4K sharpness, beauty filters, glamorous posing, VHS overlays, face morphing, duplicated fingers, teleportation, and unexplained outfit changes. Mood: Charming, intimate, slightly clumsy, and genuinely human—like a real memory recorded by a friend in 2003.
A detailed prompt for generating a realistic, handheld-style video of a sudden crocodile attack in a safari park, including specific character references and camera movements.
【视频规格与整体风格】 9:16竖屏,15秒,一镜到底。中国野生动物园内,游客用普通手机偶然拍到的惊险现场。起初平静,巨鳄突袭后摄影者晚半拍受惊,镜头抖动、拍偏,再慌忙找回人物。保留业余手机录像的真实感。 【角色与参考锁定】 女主使用预设成年中国女性角色#1@598c0e35-7c27-4b7c-8bac-19bb206ff1c3,穿着预设服装#2@d57ec59a-c0a5-4eae-84f4-4f02ef21a92d,严格保持参考中的面貌、长发、服装款式、颜色和材质。#1是人物,#2是服装,编号不出现在画面中。 管理员是一名四十岁左右的中国男性,短黑发,穿卡其色短袖工作服、深色长裤,胸前佩戴工作证,站在女主侧后方。 后方有少量成年中国游客,穿夏季便服,自然错落站在栈道上。 【场景与机位】 热带鳄鱼观赏区,旧木栈道沿深绿水池延伸,对岸是竹子、棕榈和灌木。粗木栏杆从画面右下方斜向背景延伸。 外部摄影者站在女主侧后方约一米,略高于她手中手机的位置,竖屏向下拍摄。画面右侧是女主、管理员和栈道,左侧及下方是水池。 潮湿白天,自然日光穿过植被,水面反射轻微绿色。普通手机1倍主摄,轻微手抖、歪斜、压缩涂抹、暗部噪点,急转时短暂模糊。无电影调色、无人机机位或人像虚化。 【女主手机朝向——必须准确】 女主是在使用手机后置摄像头拍摄水里的鳄鱼,不是自拍,也不是把手机展示给外部摄影者。 女主双手横握手机两端,手指避开后置摄像头。手机位于她胸口以下、栏杆外沿附近,机身明显向下俯倾,后置镜头的拍摄方向准确落在左下方的水下巨大暗影上。 手机屏幕朝上,并略微朝向女主的脸;手机背面及后置镜头朝下,面对水面。女主低头看屏幕,通过屏幕观察水中的目标。 从外部摄影者略高的侧后方角度,应主要看到手机屏幕和机身侧边,不应正面清楚看到整个手机背部及摄像头模组朝着外部摄影者。 屏幕取景内容与真实水面一致:能看见同一片水面及同一条模糊暗影,不出现女主自拍脸、无关风景或错误方向的画面。 女主轻微调整手腕时,手机后置镜头始终追随水下暗影。直到巨鳄突袭,她才因受惊而收回手机、打乱朝向。 【巨鳄与首帧状态】 只有一只异常庞大的深灰黑色鳄鱼。跃起时,头部接近成人上半身大小,张开的嘴占据画面左侧近半幅,尺寸参照原视频,不生成普通小鳄鱼。 首帧中巨鳄完全潜在水下,只呈现一条巨大、模糊的长形暗影,像沉木。水体反光和浑浊遮住细节,不能清楚辨认头部、眼睛、鼻孔、鳞片或牙齿,没有任何部位露出水面。 巨鳄从始至终保持相同体积,不在跃起瞬间突然膨胀。 【0—2秒:对准水下暗影拍摄】 女主站在栏杆内侧,身体微微前倾,双手横握手机,将手机后置镜头朝下对准左下方水中的巨大暗影。 她低头看朝向自己的屏幕,屏幕内的暗影与水池里的暗影位置对应。外部摄影者从她侧后方拍到手机屏幕、女主侧脸和下方水面。 管理员严肃提醒: “女士,退后一点,别靠栏杆!” 水面只有轻微波纹,鳄鱼仍未露头。 【2—4秒:目标靠近,手机跟随】 水下巨大轮廓缓慢朝女主所在位置接近。女主小幅转动手腕,让手机后置镜头继续对准正在移动的暗影,屏幕朝向自己,不把手机背面转向外部摄影者。 管理员靠近一步,伸手准备扶她,语气变急: “那不是木头,是活的!别探身!” 女主开始收回身体,但手机仍在拍水面。本段末尾,鳄鱼鼻端和眼睛才刚刚破水。 【4—6秒:巨鳄突袭】 巨鳄猛然顶开水面,巨大头部沿栏杆外侧升起,张开的嘴瞬间占据画面左侧近半幅,带起大片水花。 女主尖叫,急忙往回收手机和手臂。手机朝向因惊吓而失去稳定,此前必须一直正确对准鳄鱼。 巨鳄短暂咬住她伸在栏杆外的一侧前臂及附近衣料。管理员立即扶住她的上臂和肩背,稳住她在栏杆内侧的重心。 外部摄影者受惊后退半步,镜头短暂上抖,没有切镜或伤口特写。 【6—9秒:挣脱与落水】 巨鳄短暂松口、头部回落,女主趁机收回受伤前臂,管理员顺势将她拉到栈道内侧。动作必须有明确松口,不能让手臂穿过闭合牙齿。 手机从女主手中滑落,翻转后掉进水池,只掉落一次。 巨鳄砸回水面,激起白色水花。女主捂住前臂,伤处有少量红色液体渗出,形成短而细的流痕,沾到接触位置的衣料,并有一两滴落向木栈道。 不展示深层伤口,不喷射,不大量涌血。 管理员喊: “退后!别伸手!别捡手机!” 【9—11秒:游客慌乱】 女主退到栈道中间,护住受伤前臂,肩膀发紧,呼吸急促。 近处游客先缩肩后退,拉住同伴;后方游客听到尖叫才转身,有人收手机,有人侧身让路,先后惊呼: “快退!” “别靠栏杆!” 人群反应有时间差,不整齐同步,不穿模,不跌入水池。巨鳄留在水下,不再进行第二次攻击。 【11—13秒:管理员疏散】 管理员站在女主与栏杆之间,护着她继续退开,伸手示意游客让路: “往后退!大家别挤!” 一名附近游客递来纸巾,女主接过按住同一处伤处,纸巾接触位置逐渐染上少量红色。 摄影者小幅后退并修正构图,同时拍到女主、管理员和正在慌乱退让的游客。 【13—15秒:惊魂余波】 女主捂住前臂,喘着气、声音发颤地说: “吓死我了……它真咬啊!” 管理员仍护着她,警惕地看向水池。背景游客低声提醒: “离远点,别拍了!” 结束在女主惊魂未定、人群退开、水面余波尚未平息的现场。 【现场声音】 全部为手机现场收音,中文对白,无配乐、旁白和字幕。 开头有游客低声交谈、竹叶摩擦和轻微水声。管理员声音近而清楚,随危险发生从严肃提醒变为急促制止。 巨鳄出水时有沉重水声、女主尖叫、近处吸气声;随后是手机落水、水花砸落、急促喘气和凌乱脚步。最大水花与尖叫使麦克风短暂削波,随后自动增益恢复。 远处游客声音更散、更轻,不添加怪兽咆哮。 【连续性与重点约束】 开头女主手机必须正确拍摄水下目标:屏幕朝上并朝向女主,后置镜头朝下对准鳄鱼所在位置;外部摄影者主要看到屏幕与侧边。禁止手机背部镜头朝外部摄影者,却表现成正在拍摄水下目标。 首帧只有水下模糊巨影,不出现清楚鳄鱼头、眼睛、鳞片或牙齿。红色液体只在咬伤之后出现。 保持人物#1、服装#2、管理员、巨鳄和栈道连续。受伤始终是同一侧前臂,红色流痕、衣料损伤与纸巾按压位置对应。 只有一部手机,落水后不回到手中。女主与管理员始终在栏杆内,鳄鱼@d57ec59a-c0a5-4eae-84f4-4f02ef21a92d始终在池内。全过程保持接触、重量、咬合、松口和后退动作的因果关系。 无伤口特写、无断肢、无深层组织展示。全片一镜到底,无慢动作、回放、摄影棚揭底、界面覆盖或水印。
Detailed storyboard prompts for a cozy nature care Vlog featuring butterfly release and ASMR, emphasizing authentic MiniDV camera aesthetics.
CAMERA / LOOK: Handheld mini DV camcorder footage filmed by the subject herself. Slight hand shake, occasional focus hunting, imperfect framing, natural zoom adjustments, soft tape-like image quality, subtle grain, realistic auto-exposure shifts from soft bright garden daylight. Natural skin tones, mild motion blur, authentic consumer camcorder aesthetic rather than polished cinematic footage. STYLE: Cozy nature-care vlog with gentle ASMR elements. Relaxed pacing, minimal dialogue, candid moments, natural pauses. Focus on satisfying everyday sounds: mesh enclosure unzipping, soft rustling of leaves, gentle breathing, light footsteps on grass, faint birdsong. SUBJECT: Young woman in her mid-20s, plain linen dress, hair loose, minimal jewelry, no visible logos or branded items. Calm, quietly emotional energy during a small meaningful moment. SETTING: Small backyard garden on a bright calm morning. Natural daylight, flowering plants, a plain mesh butterfly enclosure resting on a table, no visible signage or brand names in frame. STORYBOARD: → (3s, propped medium shot) Places camera on a low table, gently unzips the mesh enclosure. "Finally ready to let this one go." → (3s, close-up) Reaches in carefully, lets the butterfly climb onto her finger. → (3s, handheld shot) Holds her hand up toward a nearby flower. "Take your time, no rush." → (3s, detail shot) The butterfly rests briefly on a petal before opening its wings. No dialogue. → (3s, medium shot) Watches quietly as it flutters a short distance away. "There you go." → (3s, macro shot) Wings catching the morning light as it lifts off. → (3s, propped shot) Follows it with her eyes until it disappears over the fence. → (3s, warm ending shot) Wipes a small tear, genuinely moved smile. "Didn't think I'd get emotional over this." → (6s, final shot) Turns toward camera. "See you next release." Hand covers lens as recording ends. AUDIO NOTES: Natural garden ambience — mesh unzipping, soft rustling, faint birdsong should be clearly audible. Dialogue quiet and casual, as if speaking to a small personal audience. REALISM NOTES: Authentic body language, natural blinking, genuine emotional smiles, occasional quiet pauses, imperfect framing, focus breathing, soft bright morning light shifts. No copyrighted characters, logos, brand names, or recognizable public figures anywhere in frame. Fully original personal vlog content, not AI-generated or commercial in style.
ابدأ بمثال يطابق هدفك. صف الموضوع والنتيجة بوضوح، ثم أضف التكوين والكاميرا والإضاءة والصوت والحركة أو التخطيط اللازم لإنشاء فيديو. استبدل متغيرات المنتج والعلامة والمراجع والحوار قبل الإنشاء.
افتح بطاقة وقارن المعاينة بالنص المصدر، ثم انسخ الـ Prompt الأصلي إلى Topview AI أو مولّد متوافق. عدّل المراجع والقيود وملاحظات النمط لمشروعك.
تعامل مع كل مطالبة كمثال معروض أو نقطة بداية لا كضمان للنتيجة. راجع دقة العلامة والحقوق والسلامة وقدرات النموذج المختار.
نعم. تربط صفحات الوسائط بصفحات تصنيف مخصصة، وتُبقي كل صفحة تصنيفًا واحدًا نشطًا ليظل النطاق وقصد البحث واضحين.
تتضمن المكتبة حاليًا أمثلة لـ Seedance 2.5, Seedance 2.0, Wan 3.0, GPT Image 2, Nano Banana Pro, Gemini Omni, Grok Imagine. يختلف التوفر حسب نوع الوسائط والفلاتر.
أنت تعرض مطالبات فيديو من مجموعة «Social Lifestyle» المصنفة حسب الاستخدام.