APIMODELSAPIMODELS

20+ Kling 4.0 Dialogue & Lip Sync Prompts

20+ prompts. More than 270 Kling 4.0 video prompts that other people published: creators on X, the kling4.video prompt library, fal.ai's Kling 4 prompting guide and a few Civitai posts. Each one is quoted in full, word for word, credited to its author and linked to the original, and the card plays the clip it produced where the source has one. We did not write any of them.

← All 275 Kling 4.0 prompts

Last updated: · Kling 4.0 API — pricing & playground · API docs

TL;DR

Kling 4.0 is the newest video model in Kuaishou's Kling family, and every clip it makes comes with sound generated in the same pass. On apimodels.app one model id, kling-4.0, covers text-to-video; reference-to-video with up to 10 images, 5 videos, 7 named subjects and 3 voices that the prompt calls by @mention; and keyframe-to-video from a first frame, up to 8 middle frames and a last frame. Clips run 3 to 30 seconds at 720p or 1080p, prompts can be up to 10,000 characters, and it costs $0.157 per second at 720p and $0.235 at 1080p, with failed generations not charged. Kling 4.0 Flash (kling-4.0-flash) takes the same request at 720p only, 3 to 20 seconds, prompts up to 8,000 characters and a first frame as its only keyframe, for $0.094 per second. The API has no negative prompt, no multi-shot storyboard mode and no 4K. This page collects more than 270 Kling 4.0 prompts other people published, most of them on X.

Source: Kling AI (the model vendor’s official site)

Hover to preview · click for sound

Three Emotions Portrait Performance

Create an ultra-photorealistic cinematic portrait video featuring one woman experiencing three powerful emotions in a continuous, uninterrupted performance: genuine happiness, heartbreaking sadness with visible crying, and explosive anger. Her emotional changes must feel psychologically believable, with natural spoken dialogue, accurate lip synchronization, subtle facial microexpressions, realistic tears, and expressive vocal delivery. Environment: A minimalist portrait studio with a pure white background, soft diffused frontal lighting, delicate natural shadows, and no distracting objects. Character: A woman in her early thirties with expressive brown eyes, natural facial features, softly styled dark hair, minimal makeup, and a modest black high-neck top. Her identity, hairstyle, clothing, and facial proportions remain completely consistent. Visual Style: Ultra-photorealistic facial performance, visible skin pores, fine facial hairs, realistic muscle contractions, natural eye moisture, detailed tear formation, subtle lip trembling, authentic breathing, and physically accurate facial movement. Camera Language: One continuous intimate close-up framing her face and shoulders. The camera performs an extremely slow forward push throughout the entire sequence, gradually moving closer to emphasize the emotional intensity. No cuts, no angle changes, no sudden camera movements. Audio: Clear natural female dialogue with precise lip synchronization, emotional vocal changes, audible breathing, soft laughter, trembling speech, sobbing, and increasingly forceful angry delivery. No background music. [00:00-00:06] HAPPINESS | Genuine Joy Begin with the woman looking directly into the camera, her face relaxed and her eyes bright. A small, spontaneous smile appears at the corners of her lips, gradually spreading into a beautiful, genuine expression of happiness. Her cheeks lift, delicate smile lines develop around her eyes, and she releases a quiet, breathy laugh. Her shoulders relax as she leans almost imperceptibly toward the camera, appearing excited and emotionally overwhelmed by wonderful news. She speaks in a warm, joyful voice, smiling naturally between words: Dialogue: "I can't believe it... I'm so happy. This is everything I ever wanted!" Her eyes sparkle with excitement, and she finishes the sentence with a soft laugh. Toward the end of the moment, her smile begins to weaken as an unexpected realization crosses her face. [00:06-00:13] CRYING | Heartbreak Her happiness gradually collapses into sadness. The smile disappears, her eyebrows lift toward the center, and her eyes begin filling with tears. She tries to maintain composure, pressing her trembling lips together while taking a shaky breath. Moisture gathers along her lower eyelids before the first tear spills over and slowly travels down her cheek. Her breathing becomes uneven, her chin trembles, and she attempts to speak through the emotion. Her voice cracks naturally, interrupted by a small involuntary sob. Dialogue: "But... you promised me. You said you'd never leave me..." She struggles to finish the sentence, briefly lowering her gaze as another tear begins rolling down her opposite cheek. Her mouth trembles, her nostrils flare with a shaky inhale, and she closes her eyes momentarily as the pain becomes overwhelming. Her crying must feel authentic and restrained, with visible emotional effort rather than exaggerated theatrical sobbing. [00:13-00:20] ANGER | Emotional Explosion Her sadness gradually transforms into anger while the tears remain visible on her cheeks. She inhales sharply, raises her head, and fixes her eyes directly on the camera. Her eyebrows lower, her jaw tightens, and the trembling in her lips gradually becomes a firm, controlled expression. Her breathing changes from broken sobs into deeper, more forceful breaths. She begins speaking through clenched teeth, her voice initially low and shaking with suppressed anger. Dialogue: "You lied to me..." She pauses briefly, swallowing her emotions as her eyes narrow and her facial muscles tense. Her voice suddenly rises with genuine fury. Dialogue: "HOW COULD YOU DO THIS TO ME?!" Her eyebrows pull together sharply, her nostrils flare, and her mouth opens naturally with the force of the final words. Her voice breaks slightly because she is still crying, creating a believable mixture of heartbreak and rage. She finishes the sentence breathing heavily, her jaw clenched, tears still visible, and her eyes locked intensely on the camera. The final frame holds on her furious, tear-streaked face as she struggles to regain control. Emotional Continuity: The performance must feel like one uninterrupted emotional experience. Happiness gradually gives way to heartbreak, and heartbreak intensifies into anger. Preserve overlapping emotional cues, particularly the transition from crying into rage, where tears continue flowing even as her facial expression becomes increasingly aggressive. Facial Performance: Prioritize realistic facial anatomy, natural asymmetry, detailed eyebrow movement, subtle cheek tension, lower-lip trembling, involuntary blinking, eye moisture, visible tear accumulation, realistic tear trails, and physically accurate jaw movement during speech. Dialogue and Lip Synchronization: Every spoken word must align precisely with her mouth movements. Her voice should evolve naturally from light, joyful warmth to fragile, trembling sadness and finally intense, emotionally strained anger. Include realistic pauses, breaths, vocal cracks, and changes in volume without making the dialogue sound theatrical or artificially generated. Camera and Lighting: Maintain a single continuous close-up with a very slow push-in. Preserve identical facial proportions, hairstyle, clothing, white background, lighting direction, and skin texture throughout. Negative Guidance: No identity changes, sudden emotional switching, exaggerated facial acting, cartoon expressions, artificial tears, frozen eyes, unnatural mouth movements, inaccurate lip synchronization, inconsistent tear positions, plastic skin, beauty filters, facial morphing, camera cuts, subtitles, text, logos, background music, or additional characters.

Hover to preview · click for sound

Girl Skateboarding in Dark Forest

Nighttime medium shot of a girl skateboarding swiftly through a dark, cold forest, her breath visible in the frosty air. The camera follows close behind, capturing her focused expression as she sings softly and sorrowfully, "Am I dead? Am I dreaming? I can't feel anything—I can't feel a thing." Pale moonlight filters through bare branches, casting cool blue shadows. She comes to a gentle stop on a leaf-strewn path, picks up her skateboard, and steps deeper into the dense woods. She whispers, "I must remain unseen," as the camera slowly dollies forward, enhancing the eerie, quiet ambiance. Audio: raw on-set sound only — natural dialogue, ambient room tone, and diegetic sound effects.

Hover to preview · click for sound

Crime Boss Confronts Courier

SCENE CONTEXT EXACTLY 4 HUMAN CHARACTERS — NO DUPLICATES, NO EXTRAS: the boss, the courier and two silent bodyguards, all Mexican. Interior, the back room of a closed cantina in Guadalajara, Mexico, late at night. A courier nicknamed Flaco reports to his boss that the merchandise is gone: a rival family, the Mendozas, ambushed his team on the highway to Tepic and took the whole load. The boss starts completely calm while he eats; the tension rises with every line; he explodes, then drops to a cold, lethal whisper. Crime drama, real time. Only the boss and the courier speak. CHARACTERS ERNESTO (the boss): heavyset Mexican man, slicked-back grey hair, thick grey moustache, a thin old scar cutting through his left eyebrow, heavy-lidded eyes. Black button-up shirt with subtle dark embroidery on the yoke, sleeves rolled to the forearm, a small sauce stain on the cuff, a thick gold chain at the neck. A worn gold signet ring on his right hand. 178 cm. FLACO (the courier): very thin, wiry Mexican man, short black hair neatly cut, thin moustache, a small fresh bruise on his left cheekbone, a faded tattoo of a small cross on the back of his right hand. Clean, pressed white short-sleeved shirt, dark jeans, worn brown leather boots, a gold wristwatch with a freshly cracked face. He looks put-together, but his nerves betray him. 182 cm. THE BODYGUARDS: two broad, silent men in plain dark short-sleeved shirts, one with a shaved head and a thick black beard, the other with a grey buzz cut and a crooked nose. They stand against the back wall in the half-dark, arms crossed, never speaking. LOCATION MAP A small square table with a worn green oilcloth sits at the center under a single hanging lamp, with a slow ceiling fan above it. Ernesto sits on the right side of the table (screen-right), facing left, with a plate of carne asada, a stack of warm corn tortillas in a cloth, a small clay bowl of salsa, a fork and a full shot glass of tequila. A box of dominoes rests at the edge of the table. An empty wooden chair waits on the left side of the table (screen-left). The two bodyguards stand against the back wall behind the table, one at the left third and one at the right third of the frame, partly in shadow. In the dark background: stacked beer crates without labels, a closed swinging kitchen door, a wall of painted talavera tiles, an old calendar, closed window blinds. The eyeline axis runs left–right across the table; the camera always stays on the same side of it. FORMAT One scene, 11 shots joined by clean hard cuts, classic shot–reverse-shot coverage. Cuts follow the dialogue and also land on the listener's reaction. The framing gets tighter and the silences longer as the tension rises, until the explosion in Shot 9. No fades, no dissolves, no split screens. SHOTS Shot 1 — Wide shot, locked-off, from the far corner of the room, 63° FOV. Ernesto eats in the pool of light while the ceiling fan turns slowly above him; the two bodyguards stand motionless against the back wall. Flaco walks in from screen-left and stops beside the empty chair, standing, hands at his sides. He does not sit. Ernesto keeps eating and ignores him. Shot 2 — Medium close-up on Ernesto, 47° FOV, eye level, static. He tears a tortilla, keeps chewing, eyes on his plate. Without looking up, he points his fork at the empty chair. Relaxed, unhurried: "Siéntate, Flaco." Shot 3 — Medium shot on Flaco, 47° FOV, static. Only now does Flaco pull out the chair and sit down slowly, on the front edge of the seat, back straight, hands resting stiffly on his knees. Shot 4 — Medium close-up on Ernesto, 47° FOV, static. Still eating, still not looking at him. Casual, almost friendly, mouth half full: "¿Y? ¿Cómo salió lo de Tepic?" Shot 5 — Reverse: medium close-up on Flaco over Ernesto's out-of-focus right shoulder, 47° FOV; one bodyguard is visible out of focus in the background. Flaco rubs his palms slowly along his thighs, swallows, his eyes flick from the plate to Ernesto's face. Fast and nervous, words tumbling out: "Los Mendoza nos cayeron en la carretera, patrón. Tres camionetas. Se llevaron la mercancía. Toda." Shot 6 — Close-up on Ernesto, 29° FOV, static. His chewing slows… and stops. A long silence. For the first time he lifts his eyes to Flaco. No expression at all. Flat, quiet, slowly, as a statement: "Toda." Shot 7 — Reverse close-up on Flaco, 29° FOV, handheld with an extremely subtle breath-like float. He cannot hold Ernesto's gaze; his eyes drop, then come back. His jaw tightens, his breathing becomes shallow, his fingers grip his knees. Voice cracking, pleading: "Nos agarraron por sorpresa. No pude hacer nada, patrón. Se lo juro." Shot 8 — Extreme close-up insert on the table, 29° FOV, static. Ernesto sets his fork down beside the plate with a soft click. His hand rests flat on the oilcloth; his fingers slowly curl into a fist. Silence; only the creak of the ceiling fan. Shot 9 — Medium shot on Ernesto, 47° FOV, handheld, the camera jolting once with the impact. He slams his open palm onto the table; the shot glass jumps and spills a little tequila, the dominoes box rattles. He leans over the table toward Flaco, veins visible on his neck, face red, shouting hard: "¡La quiero de vuelta! ¡Haz lo que tengas que hacer!" Behind him, both bodyguards uncross their arms and take one step forward. Shot 10 — Close-up on Ernesto, 29° FOV, slow push-in ending on his eyes. Still leaning in, his breathing heavy, his face half in shadow under the lamp. His voice suddenly drops to a cold, quiet whisper, each word deliberate: "O no vuelves a ver salir el sol." Shot 11 — Two-shot in profile across the table, 47° FOV, slow lateral drift of less than half a meter to the right, ending with both faces and the table between them in frame, the bodyguards out of focus behind. Ernesto slowly sits back, smooths his shirt, picks up the shot glass and drinks the tequila in one swallow. Flaco stays frozen in his chair, breathing hard, staring at him. Hold in silence. CHARACTER ACTING Naturalistic film acting with a steady, rising tension. Ernesto: total, unhurried calm in Shots 1–4 (he ignores Flaco, eats, never looks at him); the first eye contact in Shot 6 is the turning point; quiet tension in Shot 8; a sudden, real explosion of rage in Shot 9 (jaw clenched, eyes wide, neck tendons tight); then an instant return to icy control in Shot 10, which is the most frightening moment. Flaco: tension held inside the body — stiff posture, hands on his knees, rubbing his thighs, swallowing, quick eye movements, shallow breathing; he flinches back in his chair at the slam. His skin stays dry. The bodyguards stay expressionless and silent throughout. Faces show living micro-expressions and natural irregular blinks. LIGHTING One warm 3000K hanging lamp over the table is the key source: hard top light, fast falloff, deep shadows filling the room, eye sockets partly in shadow; the bodyguards are mostly in shadow, lit only on their shoulders and the edges of their faces. The slowly turning ceiling fan above the lamp casts soft rhythmic shadows across the table and faces; the lamp swings slightly after the slam in Shot 9. A faint red neon glow from the cantina sign outside leaks through the slats of the closed blinds in the background. Light color stays identical after every cut. AUDIO All dialogue in natural, clear Mexican Spanish with an authentic Mexican accent and intonation. Ernesto: deep voice, casual and slow at first, flat and quiet, then a loud raw shout in Shot 9, then a cold whisper in Shot 10. Flaco: tense tenor voice, fast and breathy, cracking when he pleads. The bodyguards never speak. Each speaker has a distinct voice. Only one person speaks at a time, no interruptions or overlapping, natural pauses between lines. Lip movements synchronized with the Spanish dialogue. Ambience: creaking ceiling fan, distant refrigerator hum, faint street traffic and a dog barking far away outside, fork against the plate, chewing, the chair scraping on the floor tiles in Shot 3, Flaco's breathing, a heavy palm slam on the table, the shot glass knocking on the wood. Ambience stays below the dialogue. No background music. SUBTITLES Burned-in English subtitles, bottom-center inside the title-safe area, positioned 8% above the bottom edge of the frame. White sans-serif text with a thin black outline, maximum two lines, stable position and size in every shot. Each subtitle appears and disappears exactly in sync with its spoken line: Shot 2: "Sit down, Flaco." Shot 4: "So? How did the Tepic job go?" Shot 5: "The Mendozas hit us on the highway, boss. Three trucks. They took the merchandise. All of it." Shot 6: "All of it." Shot 7: "They caught us by surprise. I couldn't do anything, boss. I swear." Shot 9: "I want it back! Do whatever you have to do!" Shot 10: "Or you'll never see the sun rise again." Subtitle spelling must match exactly. No other text on screen. STYLE Gritty Mexican crime drama. 35mm film texture with organic grain, light haze in the air, shallow depth of field, crushed blacks, soft halation around the lamp, no digital sharpening. Palette: 55% deep black and shadow, 30% warm amber and worn green, 15% red neon accent. POSITIVE CONSTRAINTS Exactly four people for the entire scene: Ernesto, Flaco and two bodyguards. Same faces, hair, clothing, bruise, gold chain, watch and signet ring in every shot. Ernesto always screen-right looking left; Flaco always screen-left looking right; the bodyguards always against the back wall. Flaco stands in Shots 1 and 2 and sits down only in Shot 3, after Ernesto tells him to; from Shot 3 onward he stays seated. Exactly 7 spoken lines: 5 by Ernesto, 2 by Flaco. Ernesto stays seated; the bodyguards take only one step forward in Shot 9. Hands and fingers anatomically correct. Faces stable. The scene ends in silence with Ernesto drinking his tequila and Flaco frozen.

by @MayorKingAISource
Hover to preview · click for sound

Night Street Breakup Talk

リアルな実写の日本のショートドラマ。男性目線のPOV映像。 日本の大学近くの夜の帰り道。20代前半の日本人女子大学生と男性大学生が、肩を並べて同じ方向へ歩いている。 男性本人は映らず、カメラそのものが男性の視点。男性は女性より少し背が高い。女性は男性のすぐ隣を歩き、カメラとの距離は近め。 30秒間すべてワンショット。 二人は最後まで横並びのまま歩き続ける。カメラは女性の真横の位置を維持し、前後へ回り込まない。ズーム、寄り引き、構図変更なし。 女性は基本的に前を見て歩き、男性に話しかけるときだけ自然に隣を見る。男性を見るときは、少し見上げるようにカメラレンズを見る。 スマートフォンで歩きながら撮影したようなリアルな質感。軽い手ブレ、自然な上下動、小さなピントの迷い、わずかな露出変化。映画的に作り込みすぎない。 BGMなし。足音、風、遠くの車など自然な夜の環境音のみ。 女性は失恋した直後だが、大げさに悲しまず、仲のいい男友達に愚痴っている自然なテンション。 0〜30秒 二人は横並びのまま夜道を歩いている。 女「三年付き合って、別れるの五分だったんだけど!」 言い終わるあたりで、女性が隣の男性を少し見上げる。 男「五分?」 女「うん。こっちは昨日、全然寝れなかったのに」 女性は自然に前を見る。 男「……ほぉ」 少し間を置いて、 女「しかも最後に言われたの、『袋いる?』だよ。スーパーかよ」 「スーパーかよ」は、少し呆れながら自分でも笑ってしまうような自然な言い方。 男「袋もらった?」 女性が「そこ聞く?」というような表情で男性を見る。 女「もらった」 男「もらったんだ」 女性が少し笑う。 女「だって荷物あったし」 言い終わったあと、二人で小さく笑う。 女性はまた前を向き、そのまま二人で歩き続ける。 字幕、テロップ、ロゴ、ウォーターマークなし。 男性の姿、腕、手は映さない。 女性は手に何も持たない。 セリフ以外の不自然な口パクなし。 (extend) 前の映像からそのまま連続して始まる。30秒間ワンショット。男性と女性は最後まで完全に横並びで、同じ方向へ同じペースで歩き続ける。カメラの高さ、女性との距離、画角、位置関係は前半から変えない。男性は女性より少し背が高く、カメラは女性の真横からわずかに見下ろしている。女性の体は進行方向を向いたまま、男性を見るときだけ顔を向けて少し見上げるようにカメラレンズを見る。 女性が「だって荷物あったし」と言ったあとの小さな笑いが残っている。二人で少し笑い、そのまま数歩歩く。笑いが収まり、少し静かな空気になる。 女性は前を向いたまま、少し小さな声で、 女「……もっと何か言うと思ってた」 ぽろっと本音が出たような自然な言い方。 男「引き止めてほしかった?」 女性は少し考えながら前を向いたまま、 女「いや、別れるのは決めてたけど」 言い終わるあたりで少し男性を見る。 男「うん」 女性はまた前を見る。少し間を置いて、 女「……でも、なんかなぁ。なんかモヤるわぁ」 深刻に言いすぎず、自分でもうまく説明できない気持ちをそのまま話すような自然なトーン。 男「うむ」 女性は一瞬だけ男性を見て、少し「何その返事」という表情をするが何も言わず、また前を見る。 2〜3秒ほど会話が途切れる。足音、夜の風、遠くの車の音だけ。少し風が吹き、女性が肩をほんの少しすくめる。 女「なんか寒いな〜。 ひとりになったからかな〜?」 冗談っぽく、少し大げさに言う。「ひとりになったからかな〜?」と言いながら男性へ顔を向け、少し見上げるようにカメラレンズを見る。 男「あたためますか?」 男性は何でもないような自然な声で言う。ふざけた言い方にはしない。 このセリフは、前半の「袋いる?」→「スーパーかよ」という会話を男性が覚えていて、その流れを拾って女性を少し笑わせようとしているボケ。 女性はすぐには意図に気づかず、男性を見上げたまま一瞬だけ表情が止まる。約1秒〜1.5秒ほど間を置き、前半の「スーパーかよ」の流れを拾ったボケだと気づく。同時に、男性が自分の話をちゃんと聞いていて、重く慰めるのではなく笑わせようとしてくれていることにも自然に気づく。 その瞬間、女性の表情が少し柔らかくなる。大げさに感動せず、小さな嬉しさが表情ににじむ程度。 女「……コンビニかよ!」 怒ったツッコミではなく、「そこ拾ってくるんだ(笑)」という嬉しさと親しさが混じった言い方。最初の「……」はボケに気づくまでの一拍。「コンビニかよ!」と言うときには少し笑っている。 言い終わったあと、女性が少し下を向いて小さく笑う。男性もカメラの後ろから自然に少し笑う。女性はもう一度だけ男性をちらっと見上げ、少し嬉しそうな笑顔を残したまま前を向く。 「……コンビニかよ!」以降、新しいセリフは追加しない。そのまま二人で横並びに歩き続け、足音と夜の環境音だけを残して終了する。 演技は全体的に大げさにしない。「温めますか?」を恋愛的な意味に受け取る演技にはしない。すぐには意味が分からない → 前半のボケを拾ったことに気づく → 自分を笑わせようとしてくれた優しさにも気づく → 少し嬉しくなる → 「……コンビニかよ!」と笑って返す、という小さな感情変化で見せる。 恋愛感情を明確に出しすぎず、「この人、ちゃんと話聞いてくれてたんだ」「この人といると少し楽になるな」くらいの感情に留める。 カメラは最後まで女性の真横。女性が男性より前へ出ない。男性が女性より後ろへ下がらない。女性の正面へ回り込まない。振り返っているような構図にしない。カットなし、ズームなし、寄り引きなし、構図変更なし、カメラ位置変更なし。BGMなし。字幕、テロップ、ロゴ、ウォーターマーク、画面内文字なし。

Reference prompts (1)

This clip was made by generating reference images with the prompts below, then driving the video with the prompt above.

Extension prompt

前の映像からそのまま連続して始まる。30秒間ワンショット。男性と女性は最後まで完全に横並びで、同じ方向へ同じペースで歩き続ける。カメラの高さ、女性との距離、画角、位置関係は前半から変えない。男性は女性より少し背が高く、カメラは女性の真横からわずかに見下ろしている。女性の体は進行方向を向いたまま、男性を見るときだけ顔を向けて少し見上げるようにカメラレンズを見る。 女性が「だって荷物あったし」と言ったあとの小さな笑いが残っている。二人で少し笑い、そのまま数歩歩く。笑いが収まり、少し静かな空気になる。 女性は前を向いたまま、少し小さな声で、 女「……もっと何か言うと思ってた」 ぽろっと本音が出たような自然な言い方。 男「引き止めてほしかった?」 女性は少し考えながら前を向いたまま、 女「いや、別れるのは決めてたけど」 言い終わるあたりで少し男性を見る。 男「うん」 女性はまた前を見る。少し間を置いて、 女「……でも、なんかなぁ。なんかモヤるわぁ」 深刻に言いすぎず、自分でもうまく説明できない気持ちをそのまま話すような自然なトーン。 男「うむ」 女性は一瞬だけ男性を見て、少し「何その返事」という表情をするが何も言わず、また前を見る。 2〜3秒ほど会話が途切れる。足音、夜の風、遠くの車の音だけ。少し風が吹き、女性が肩をほんの少しすくめる。 女「なんか寒いな〜。 ひとりになったからかな〜?」 冗談っぽく、少し大げさに言う。「ひとりになったからかな〜?」と言いながら男性へ顔を向け、少し見上げるようにカメラレンズを見る。 男「あたためますか?」 男性は何でもないような自然な声で言う。ふざけた言い方にはしない。 このセリフは、前半の「袋いる?」→「スーパーかよ」という会話を男性が覚えていて、その流れを拾って女性を少し笑わせようとしているボケ。 女性はすぐには意図に気づかず、男性を見上げたまま一瞬だけ表情が止まる。約1秒〜1.5秒ほど間を置き、前半の「スーパーかよ」の流れを拾ったボケだと気づく。同時に、男性が自分の話をちゃんと聞いていて、重く慰めるのではなく笑わせようとしてくれていることにも自然に気づく。 その瞬間、女性の表情が少し柔らかくなる。大げさに感動せず、小さな嬉しさが表情ににじむ程度。 女「……コンビニかよ!」 怒ったツッコミではなく、「そこ拾ってくるんだ(笑)」という嬉しさと親しさが混じった言い方。最初の「……」はボケに気づくまでの一拍。「コンビニかよ!」と言うときには少し笑っている。 言い終わったあと、女性が少し下を向いて小さく笑う。男性もカメラの後ろから自然に少し笑う。女性はもう一度だけ男性をちらっと見上げ、少し嬉しそうな笑顔を残したまま前を向く。 「……コンビニかよ!」以降、新しいセリフは追加しない。そのまま二人で横並びに歩き続け、足音と夜の環境音だけを残して終了する。 演技は全体的に大げさにしない。「温めますか?」を恋愛的な意味に受け取る演技にはしない。すぐには意味が分からない → 前半のボケを拾ったことに気づく → 自分を笑わせようとしてくれた優しさにも気づく → 少し嬉しくなる → 「……コンビニかよ!」と笑って返す、という小さな感情変化で見せる。 恋愛感情を明確に出しすぎず、「この人、ちゃんと話聞いてくれてたんだ」「この人といると少し楽になるな」くらいの感情に留める。 カメラは最後まで女性の真横。女性が男性より前へ出ない。男性が女性より後ろへ下がらない。女性の正面へ回り込まない。振り返っているような構図にしない。カットなし、ズームなし、寄り引きなし、構図変更なし、カメラ位置変更なし。BGMなし。字幕、テロップ、ロゴ、ウォーターマーク、画面内文字なし。

Hover to preview · click for sound

Futuristic Talk Show With Android

A cinematic futuristic talk show filmed inside a polished science-fiction broadcast studio. A serious male interviewer dressed entirely in black speaks calmly while sitting in a modern chair. Opposite him sits a beautiful red-haired female android with intricate silver-black mechanical plating and highly realistic synthetic skin. Begin with a stable waist-up shot of the man speaking naturally and gesturing with both hands. Seamless cut to a close-up of the android answering him, moving her hands naturally while her mechanical fingers articulate precisely. Background screens display abstract futuristic imagery. Transition to a wide establishing shot showing the circular stage, overhead lights, glass architecture and both guests. Cut back to their faces during the conversation. At the end, the center of the stage suddenly detonates in a powerful explosion, sparks and fragments burst outward, both characters react instantly, thick smoke rapidly consumes the entire frame. Hyperrealistic live-action aesthetic, realistic explosion physics, subtle handheld reaction during blast, professional studio cameras, dramatic but believable

by @Alin_Reaper05Source
Hover to preview · click for sound

Café Two-Shot Dialogue Scene

A fixed, locked-off medium two-shot in a bright café at midday, horizontal 16:9 cinematic framing. Two young Japanese women in their early twenties sit facing each other across a small wooden table. The camera is at table height beside the table, so both women are seen in three-quarter view from the waist up — Misaki on the left of frame, Yui on the right — with their faces large and clearly lit. A large window runs along the background; soft natural daylight falls on their faces from the side, not from behind. Two iced lattes sit on the table between them. Photorealistic, natural skin texture, gentle background blur. Misaki (left): 22, cheerful and talkative, black chin-length bob, white knit sweater, expressive hand gestures. Yui (right): 23, gentle and easygoing, long brown hair, beige cardigan, laughs easily. The camera does not move or cut. Exactly four lines of dialogue, in natural Tokyo-standard Japanese, in this order. While one speaks, the other listens with her mouth closed, reacting only with nods and smiles. 0–4s: Misaki leans forward toward Yui, eyes bright, excited:「ねえ聞いて! 昨日ね、駅前のパン屋さん、やっと行けたの」 4–7s: Yui's eyes widen, surprised, quick:「え、まって、あの毎朝並んでるとこ?」 7–11s: Misaki nods hard, hands miming something crispy, delighted:「そうそう! メロンパン、ぱりっぱりで…もう最高だった」 11–15s: Yui bursts out laughing and speaks through the laugh, playfully envious:「ずるい! 今度ぜったい一緒に行こうね」 Precise lip sync: lips fully close on ま, ぱ, め, ば sounds; mouth shapes follow each vowel. No extra lines, no ad-libs, no narration. Audio is only the two voices and soft café ambience — no background music. No subtitles, no on-screen text. Single continuous horizontal shot, same framing from start to end.

Hover to preview · click for sound

Cat Vlogger Walks City Street

A 15-second continuous cinematic selfie-style video of an anthropomorphic tabby cat vlogger walking down a modern city street while holding a front-facing camera. The cat is wearing black headphones and a blue plaid shirt, speaking directly to the camera in a casual, confident tone like a daily street vlogger. Mouth movement synced to speech throughout. The camera remains in selfie mode the entire time with slight handheld shake for realism. Natural daylight lighting. Background includes passing cars, pedestrians, and tall buildings softly blurred with shallow depth of field. As the cat walks forward, it talks continuously, occasionally nodding, blinking, and slightly adjusting its headphones mid-sentence. Subtle fabric movement from wind. Natural whisker and ear motion. The cat briefly laughs near the end while still speaking, then gives a friendly wink at the camera. Ultra-realistic fur detail, natural lip sync, vlog aesthetic, cinematic color grading, 4K, 24fps, realistic motion blur.

Hover to preview · click for sound

Woman Speaks to Camera

Subject and Action A striking close-up portrait of a beautiful woman with vibrant blue eyes and blonde hair. She has full, expressive lips that move naturally as she speaks. Her facial expressions are dynamic and engaging, with subtle blinks and micro-movements that convey enthusiasm. She is wearing a unique blue cone hat that sits perfectly on her head. She speaks directly to the camera with a confident and energetic demeanor, her lips clearly articulating the phrase "Blue team, fuck yeah." Setting and Atmosphere The background is a soft, out-of-focus studio environment in neutral tones, ensuring the focus remains entirely on the subject. The atmosphere is vibrant and energetic, matching the high-energy tone of her dialogue. The scene is contained within a single continuous take, maintaining a steady focus on the subject's face and upper body. Camera and Perspective The shot is a tight close-up, framing the subject from the chest up. The camera remains steady with a slight, almost imperceptible handheld drift to add a sense of realism and immediacy. The perspective is direct and eye-level, creating an intimate connection with the viewer. The depth of field is shallow, keeping the subject's eyes and lips in sharp focus while blurring the background elements. Lighting and Style The lighting is cinematic and flattering, using soft key lights to illuminate the face evenly while gentle rim lighting highlights the edges of the blue cone hat and her blonde hair. The color palette is cool, emphasizing the blues of her eyes, hat, and the implied "blue team" theme, contrasted with the warm tones of her skin. The overall style is high-fidelity, realistic, and polished, suitable for a modern social media or promotional video aesthetic.

by 5XTzQSource
Hover to preview · click for sound

Last Ferry Rainy Love Scene

"A cinematic, aching love scene on the last ferry of the night, crossing a dark sea in the rain. [Jules], the red-haired woman in the rust-orange wool coat with a single gold hexagon earring in her left ear, and [Harry] , the clean-cut man in his late 20s with neat side-parted light-brown hair and an olive work jacket, sit side by side on a bench seat by a rain-streaked window in the quiet ferry café. Harbour lights shrink into the dark behind the glass. Intimate romantic drama, six shots. 0s–5s: Wide two-shot from across the empty café. Jules watches the harbour lights recede; Harry watches only her. [Jules: warm quick Glaswegian voice, quiet and wistful]: "This is the last ferry, you know." A beat. [Harry: slow Central Texas drawl, soft and low]: "I know." 5s–10s: Close-up on Jules in profile against the window, rain shadows sliding down her face. She keeps her eyes on the lights and forces a small smile that doesn't reach her eyes. [Jules, trying to sound light]: "Tomorrow you're on a plane, and I'm back to talking to the gulls." 10s–14s: Close-up on Harry. He turns fully toward her, earnest, his voice barely above the engine hum, and his hand finds hers on the bench. [Harry, tender, hopeful]: "Then come with me." 14s–19s: Close-up on Jules. Her composure cracks; her eyes fill, a small broken laugh escapes, and she shakes her head without looking at him. [Jules, voice trembling]: "Don't. Don't make it sound easy." 19s–25s: Tight two-shot. He lifts her hand and holds it against his chest; she finally turns to meet his eyes. [Harry, hoarse, full of feeling]: "Nothing about you's been easy, darlin'. That's why I keep coming back." 25s–30s: Extreme close-up of the two of them, foreheads touching, eyes closed, the harbour lights a soft blur behind them. [Jules, a whisper]: "Then keep coming back." [Harry, a whisper, smiling through it]: "Every time. Every single time." The ferry horn sounds low in the distance.Warm tungsten café lamps against cold blue storm light from the window, shallow depth of field, natural skin texture, glistening eyes, subtle film grain. Sound: rain on glass, the engine hum, the creak of the hull, a soft piano note under the final line."

Hover to preview · click for sound

Riverside Winter Night Breakup Talk

A vertical 9:16 Japanese short drama scene, cinematic and photorealistic, shot at night on a riverside walking path in early winter. Streetlights stand at even intervals along the path, their warm light reflected on the dark river. Cool night air, breath faintly visible. Shallow depth of field, soft bokeh from the streetlights, muted teal-and-amber color grade, subtle film grain. Haruka: Japanese woman, 24, shoulder-length black hair, long beige coat. Quiet voice, but firm. Souta: Japanese man, 25, short black hair, navy duffle coat. Usually gentle; now shaken. Four shots, in this order. Exactly four lines of dialogue in natural Tokyo-standard Japanese, spoken softly and slowly, with real pauses. No other lines. Shot 1 (0–4s) — Frontal tracking shot, the camera moving backward ahead of them, bust shot of both. Haruka and Souta walk side by side toward the camera, a small gap between their shoulders. Haruka keeps looking straight ahead and says quietly:「ねえ…来月から、大阪なんだ」 Shot 2 (4–7s) — Tracking from behind at waist height, focus on the space between their two hands. Their hands swing as they walk, almost touching but never touching. Souta's voice, after a pause, low:「…なんで、今言うの」 Shot 3 (7–11s) — Side tracking shot, moving alongside them. Haruka stops walking. The camera keeps moving with Souta for two more steps, then stops. Focus racks from Souta in the foreground to Haruka standing behind, now one streetlight's distance away. Haruka, still and steady:「言ったら…止められると思ったから」 Shot 4 (11–15s) — Souta turns back toward her. Slow push-in on his face; streetlight falls across only half of it. He starts to speak, swallows it, then says in a hoarse voice:「…止めたら、いてくれんの?」 Hold on his face to the end. Audio is only their voices, footsteps, the river, and distant traffic — no background music. No subtitles, no on-screen text. Same two people, same clothes, same night riverside path in every shot.

Hover to preview · click for sound

Three A.M. Sisters Kitchen Confession

20s, 16:9, 6 cuts, photoreal live-action, native audio with synced dialogue, British English accents. No on-screen text, subtitles, captions, watermarks or logos. STYLE: intimate chamber drama, 35mm grain, shallow focus, understated performances. CAST: NORA - woman, 45, auburn hair in a loose knot, black reading glasses pushed up on top of her head, grey cardigan over a faded T-shirt, tired eyes. ELLIE - her younger sister, 32, black curly shoulder-length hair soaked from rain, oversized denim jacket, jeans, silver hoop earrings. PROPS: two identical mustard mugs. Nora holds one. A second, empty mug stands clearly visible at the empty chair opposite her. PALETTE: amber pendant lamp vs cold teal under-cabinet light, deep shadows, natural skin. STORY: At 3 a.m. Ellie comes home to admit she sold their late mother's house. Nora already knows. BEATS: 0.0-3.5s | CUT 1, wide, static, eye level: heavy rain on the kitchen window. Ellie stands frozen in the doorway on the left, dripping. Nora sits at the table on the right, hands round her mug; the empty mug waits opposite. Stillness. 3.5-7.5s | CUT 2, clean medium close-up on Nora, nothing in the foreground, 50mm, slow push-in. Eyes down. NORA (flat, quiet, exhausted): "You sold it. Mum's house. Without asking me." 7.5-12.0s | CUT 3, close-up on Ellie in the doorway, 85mm, subtle handheld. Her eyes fill with tears; she swallows before speaking. ELLIE (defensive, voice cracking on the last word): "I was drowning, Nora. You weren't answering." 12.0-15.5s | CUT 4, same clean medium close-up on Nora, eyes dry at first. She looks up, pulls the glasses down off her head and sets them on the table. Only then does one tear run down her cheek. She says nothing. Only rain. 15.5-18.0s | CUT 5, low profile shot along the tabletop: Nora's hand slides the empty second mug across the wood to the empty chair. NORA (whisper, barely voiced): "Sit down." 18.0-20.0s | CUT 6, medium close-up on Ellie, already seated at the table, both hands round the second mug. One shaky breath, half laugh, half sob, then stillness. Hold. AUDIO: dialogue close and dry. Steady rain on glass audible from the first frame, fridge hum, room tone. Mug scrape on wood at 16s. Ellie's half-laugh sob at 18.5s. No music. NEGATIVE: no text, no extra people, no foreground shoulders in Nora's shots, no repeat of the CUT 1 wide, no props appearing or vanishing, no melodramatic sobbing, no face morphing, no lip-sync drift.

Hover to preview · click for sound

Medieval Tax Office Comedy

Text-to-video prompt: A SINGLE CONTINUOUS 20-SECOND SHOT. No cuts. SETTING: An extravagant medieval tax office, 1977 Eastern European live-action fantasy film aesthetic. Handmade brocade costumes, theatrical practical makeup, faded Eastmancolor photography, softly diffused sunlight, subtle 35mm grain. CHARACTERS: Lord Bartholomew, an enormously pompous, stout nobleman with an elaborate moustache and gold rings, seated behind an oak desk. Opposite him stands a very tall, thin, elderly tax clerk holding a leather ledger. Both speak English in understated British accents. 0:00–0:03 — KEYFRAME 1: Medium-wide two-shot. A brilliant shaft of morning sunlight falls across the nobleman's desk. He points at the light and declares triumphantly, "Tax that!" The clerk freezes, quill raised. 0:03–0:07 — KEYFRAME 2: Camera slowly tracks toward the clerk as he studies the sunlight. He asks cautiously, "The sunshine, my lord?" The nobleman nods with tremendous satisfaction. 0:07–0:11 — KEYFRAME 3: The clerk steps toward the window while the camera tracks sideways with him. The nobleman announces, "Every last ray!" He folds his hands, pleased with his genius. 0:11–0:16 — KEYFRAME 4: Without cutting, the clerk closes the heavy wooden shutters. The sunlight disappears, and the room becomes noticeably darker. He turns back and says, "It's gone, sir." 0:16–0:20 — KEYFRAME 5: The camera gently moves closer to the nobleman, now sitting in gloom. His smile collapses. He shouts, "OPEN IT! THAT'S MINE!" The clerk slowly looks at the camera with weary resignation. CAMERA: One uninterrupted, gently tracking camera movement at human eye height. Natural blocking and stable screen geography. PERFORMANCE: Underplayed British comedy, microexpressions, perfectly timed hesitations. Physically consistent sunlight and shadows. AUDIO: Realistic dialogue, creaking shutters, quill scratches, quiet room tone. No music, subtitles or artificial transitions.

by @airina_xyzSource
Hover to preview · click for sound

Gym Vlog Dumbbell Workout

CAMERA & STYLE: Handheld DV 16mm camcorder aesthetic, imperfect framing, natural camera shake, soft focus, tape noise, flickering exposure, and authentic gym-vlog energy. CHARACTER: MILA, a 20-year-old American brunette fitness creator with a high ponytail, natural skin texture, and an athletic figure. Wearing a cobalt-blue sports bra, matching gym shorts, and white ankle socks. SETTING: A gym dumbbell area in the evening, with weight racks, benches, mirrors, and a few people exercising in the background. 15-second storyboard 0–2.5s: Walking selfie. “Arm day. This should be quick.” 2.5–5s: Alternating dumbbell curls. “These felt lighter yesterday.” 5–7.5s: Lateral raises. “I picked the light ones!” 7.5–9.5s: Close-up of her hand gripping a dumbbell. Natural movement and gym sounds. 9.5–12s: She walks toward the rack, laughing. “Yep — my arms just quit.” 12–15s: Final selfie after the workout. “Same time tomorrow? No promises.” The goal: Make it feel like a real, spontaneous gym vlog — not a polished AI commercial. https://x.com/RDV1113/status/2115020582161142147?a=7kkqBUaXc6gsV1GUMHo&s=20

Hover to preview · click for sound

Rainy Cafe Dialogue Scene

The man on the left leans in and says, in a calm British accent, "You already know what I'm going to say." The other man lowers his cup and gives a small nod. Slow push-in on the two of them, rain running down the window, warm lamps steady. One continuous take, natural dialogue, cafe room tone.

Hover to preview · click for sound

Rap Performance Studio Close-Up

Begin from the supplied studio portrait and preserve the performer’s face, curly light-brown hair, light mustache and goatee, white ribbed tank top, tattoos, silver pendant, and black over-ear headphones. Create one continuous medium close-up of him delivering a focused rap performance. Keep the silver condenser microphone and black pop filter beside his face, without letting either drift across his mouth.

by fal.aiSource

Fox and Owl Library Chat

A photorealistic cinematic scene in a grand walnut-panelled library, late afternoon. An anthropomorphic red fox aristocrat wears a forest-green frock coat, a cream waistcoat and a carefully tied silk cravat. An elderly barn owl scholar stands beside a writing desk in a dark plum velvet jacket, with tiny spectacles resting above his beak. Warm window light catches individual strands of fur and delicate facial feathers. Begin in a medium two-shot as the fox confidently straightens his cuffs. He asks, “Would you describe me as a man of considerable intellect?” Cut to the owl’s close-up. After a thoughtful pause, the owl replies, “I would describe you as considerably well dressed.” The fox’s proud smile slowly fades in the blurred background. Understated British delivery, subtle expressions, believable animal anatomy, polished period-drama cinematography, gentle clock ticking, no subtitles.

Watch on X

Kitchen Confession of Job Loss

SCENE CONTEXT EXACTLY 2 HUMAN CHARACTERS — NO DUPLICATES, NO EXTRAS. Interior, a small lived-in apartment kitchen, late at night. A husband confesses to his wife that he was fired in June and has been pretending to go to work every day. She did not know; her disbelief turns to hurt, then to unconditional support. Intimate two-person drama, real time. The emotion lives equally in their faces, their words and their voices. CHARACTERS DANIEL: lean man, short dark hair greying at the temples, two days of stubble, deep shadows under the eyes, a small healed nick on his chin. Pale blue cotton office shirt, top button undone, sleeves rolled to the forearm, a loosened dark navy tie, a faint coffee stain on the left cuff. Plain gold wedding ring on his left hand. 180 cm. LUCÍA: shoulder-length chestnut hair loosely tied, strands falling over her face, natural skin with faint freckles and slight redness around the nose, no makeup. Oversized oatmeal wool cardigan with a pulled thread at one cuff, over a grey cotton t-shirt. Plain gold wedding ring on her left hand. 165 cm. LOCATION MAP A small square kitchen table with a worn wooden top sits at the center. Daniel sits on the right side of the table (screen-right), facing left. The doorway to a dark hallway is screen-left. On the table: a half-full glass of water between Daniel's hands and a folded, unopened envelope. His laptop bag rests on the chair beside him. The window blind is fully closed. Behind Daniel: a kitchen counter and an old wall clock. The eyeline axis runs left–right across the table; the camera always stays on the same side of it. FORMAT One scene, 8 shots joined by clean hard cuts, classic shot–reverse-shot coverage. Cuts follow the dialogue and also land on the listener's reaction. No fades, no dissolves, no split screens. SHOTS Shot 1 — Wide shot, locked-off, from the corner behind the counter, 63° FOV. Daniel sits alone in the pool of lamplight, both hands around the glass, not drinking, staring at nothing. Lucía walks in through the dark doorway, relaxed and unaware, about to cross the kitchen. Shot 2 — Medium close-up on Daniel, 47° FOV, eye level, very slow push-in ending on his face. He lifts his eyes to her; his jaw tightens, his nostrils flare with one deep breath, his lips part twice before any sound comes out. Low, slow and hesitant, with a heavy pause before the last three words: "Lucía… I need to tell you something. I got fired. In June." Shot 3 — Reverse: medium shot of Lucía over Daniel's out-of-focus right shoulder, 47° FOV. She freezes mid-step. Her brow furrows, her mouth falls slightly open, a short incredulous breath escapes her. Quick and confused, almost a half-laugh of disbelief: "What? What do you mean, you got fired?" She walks to the table and grips the back of the chair opposite him, standing, looking down at him, knuckles whitening. Her voice rises with hurt, sharp but never shouting, stressing "hiding" and "nothing": "And you've been hiding it from me this whole time, like nothing happened?" Shot 4 — Close-up on Daniel, 29° FOV, slightly high angle matching her standing eyeline, handheld with an extremely subtle breath-like float. He looks up at her, then his eyes drop to the glass; his thumb rubs its rim; his eyes turn glassy. Quiet, ashamed, his voice thinning, with a long pause in the middle and a crack on the last word: "I wasn't trying to hide it. Every morning I pretended I was going to work… and I spent the whole day looking for a job." Shot 5 — Reverse close-up on Lucía, 29° FOV, slightly low angle. No words. Her grip on the chair loosens; her furrowed brow slowly relaxes; her lips press together and tremble; her eyes fill with water. The anger drains from her face and becomes pain. The clock ticks. Shot 6 — Medium shot of Lucía, 47° FOV. She pulls out the chair and sits down opposite him, now at his eye level, leaning slightly toward him. Softer and wounded, her voice breaking on "trust": "Why didn't you tell me? Don't you trust me?" Shot 7 — Close-up on Daniel, static, eye level. He opens his mouth to answer but no words come. His chin trembles, his eyes go red, a tear gathers on his lower lid, he swallows hard and gives one small shake of the head. Silence. Shot 8 — Two-shot in profile across the table, 47° FOV, slow lateral drift of less than half a meter to the right, ending with both faces and the table between them in frame. Lucía reaches across and places her hand over his. A single tear runs down her cheek; she does not wipe it. Quiet, warm and absolutely firm, each word deliberate, stressing "always": "I'm always going to be there for you." Daniel turns his hand over and holds hers tightly, closes his eyes, and lets out a long, shaking exhale. Hold on the two of them in silence. CHARACTER ACTING Restrained, naturalistic film acting; every emotion is visible on the face in close-up. Daniel: guilt and shame — avoids her eyes, then forces himself to hold them; jaw clenched, breath short through the nose, hands restless on the glass; relief only arrives in the final exhale. Lucía: disbelief (frozen, brow furrowed, mouth open) → hurt (knuckles white on the chair, voice rising) → softening (grip loosens, eyes fill) → steady support (still, firm gaze, gentle half-smile through tears in the final shot). Faces show living micro-expressions: trembling chins, glistening eyes, swallowing, natural irregular blinks. LIGHTING One warm 3200K pendant lamp hanging low over the table is the key source: light from above-front, fast falloff, deep shadows in the corners of the room, catchlights visible in both characters' eyes. A faint cold 5600K spill from the hallway behind Lucía outlines her hair. Light direction and color stay identical after every cut. AUDIO All dialogue in natural, clear English with a neutral American accent. Daniel: low, tired baritone, slow, hesitant, with long pauses and an audible tremor when emotion rises. Lucía: warm mid-range voice that moves from confused and fast, to sharp and hurt, to soft and breaking, to quiet and firm. Each has a distinct voice. Only one person speaks at a time, no interruptions or overlapping, about one second of silence between lines. Breaths, swallows and small catches in the voice are audible. Lip movements synchronized with the English dialogue. Ambience: wall clock ticking, refrigerator hum, chair legs scraping on floor tiles, glass touching wood, cardigan rustle. Ambience stays below the dialogue. No background music. No subtitles. STYLE Intimate auteur drama. 35mm film texture with organic grain, shallow depth of field, soft halation around the lamp, no digital sharpening. Palette: 60% warm amber and wood brown, 30% deep shadow, 10% cold blue spill from the hallway. POSITIVE CONSTRAINTS Exactly two people for the entire scene. Same faces, hair, clothing and wedding rings in every shot. Daniel always screen-right looking left; Lucía always screen-left looking right. Exactly 4 dialogue turns: 2 by Daniel, 2 by Lucía. Lucía stands in Shots 3–5 and sits from Shot 6 onward. Hands and fingers anatomically correct when they hold hands. Faces stable. The scene ends in silence with their hands joined on the table; they stay seated.

Watch on X

Alien Transit Terminal Warning

First-person cinematic POV inside a living extraterrestrial transit terminal grown from pale coral and translucent membranes. An original humanoid alien with opalescent skin, narrow amber eyes, and delicate crystalline ridges sits beside a basin of luminous drinking water. Its anatomy remains consistent throughout. As the viewer approaches, it covers the basin with one trembling hand. In a soft, precise English voice, it says: “Don't drink the water. It carries the colony's memories. Drink enough... and there won't be any room left for yours.” Moving shadows inside the water briefly resemble thousands of crowded faces. The alien struggles to recall a word, then falls silent. One continuous take, intimate framing, photoreal creature effects, organic architecture, cold bioluminescent lighting, subtle breathing and distant biological pulses, clear lip sync, no captions. 😉

Watch on X

Demon Eve Living Room Dialogue

26-second continuous cinematic sequence, photoreal, film grain, dynamic camera, seamless magical transitions between worlds. Dialogue in English, lip-synced. CHARACTERS: Eve @Image1, dark brown shoulder-length hair, mustard cable-knit jumper, blue jeans, brown Chelsea boots. Demon Eve @Image2, red-skinned demon with black curved horns, leathery wings folded behind her, spiked tail, black leather armour. Eve's voice: low, dry, deadpan female voice with a natural British accent. Demon Eve's voice: husky, gravelly, slightly resonant female voice, unimpressed. 0-6s: LIVING ROOM @Image3, cosy late-afternoon lamplight, Halloween pumpkin glowing on the windowsill. Medium-wide shot facing the sofa. Eve sits on the left of the sofa with a silver MacBook Pro on her lap, typing. Demon Eve sits on the right, wings tucked, tail curled over the armrest, staring blankly ahead at a TV just off camera, its flicker on her face. Eve suddenly stops typing, gasps, eyes wide at the screen, and says: "Eve, Kling 4.0 just came out." Demon Eve slowly turns her head towards her, deadpan, and says: "Do it." 6-8s: Close on Eve's hands typing fast and hitting enter. The laptop screen erupts with bright light, a swirling vortex pulls Eve forward, her hair whipping, and she is sucked headfirst into the screen. Camera pushes through the screen after her. 8-13s: DARK FANTASY BATTLEFIELD, ash and embers, stormy sky. Eve is now the necromancer @Image4: black hooded cloak, dark plate armour with bone details and skulls, holding a staff topped with a skull with glowing blue eyes. Horned demon monsters charge in. She slams the staff into the ground, releasing a huge circular shockwave of blue spectral energy that blasts the demons off their feet. Beside her, her skeleton minion @Image5, bronze skeleton in a tattered coat and boots, swings a rusty sword and cuts down demons one after another. The last demon collapses into ash. 13-18s: A beam of light yanks Eve straight up into the sky; mid-air she transforms in a burst of light into the caped hero suit from @Image6, long blonde hair, blue suit, red cape, red skirt, red boots. She flies fast above a modern high-rise city at golden hour, banking left and right between glass skyscrapers, cape snapping, camera chasing behind her. She pitches downward and dives towards the ground. 18-22s: She slams down in a ruined war zone, dust and debris blasting outward, and in the impact flash transforms into the futuristic soldier @Image7: white-silver ponytail, dark tactical armour, cargo trousers, combat boots. She raises a futuristic rifle and fires bright bursts at armoured enemy soldiers advancing through smoke, dropping them one by one. Behind her, on a crumbling window ledge, a tiny potted cactus sits untouched in the chaos. 22-23s: The last enemy falls. The light vortex grabs her again and pulls her up and away, blur of colour. 23-26s: BACK IN THE LIVING ROOM @Image3. Eve @Image1, back in her mustard jumper, is shot out of the laptop screen and thumps back onto the sofa, hair messy, laptop on her lap. She stares straight ahead, completely stunned, eyes wide, mouth slightly open. Demon Eve looks at her with a raised eyebrow and says: "So?" Eve slowly turns her head to Demon Eve and says: "That was fucking awesome." Hold on the two of them. NEGATIVE: extra limbs, morphing faces, identity drift between characters, Demon Eve losing horns or wings, logos or text on screen, subtitles, watermark, blurry faces, duplicate characters, laptop disappearing, cartoon style

Watch on X

Cafe Barista Order Dialogue

Medium shot in a small, busy café. A nervous young barista with a short bob looks toward a customer just off-screen left and says in English: "Sorry, was that oat milk or almond?" The customer laughs off-screen: "Surprise me." She smiles with relief and reaches for a carton. Sound: espresso machine hiss and café chatter. Natural window light, lips in sync with the speech.

Watch on the original post
by kling4.videoSource

How to write great Kling 4.0 prompts

  1. 1Call every input by its @name. On the API, references are numbered by their position in the request: @image_1 and @image_2 for image_urls, @video_1 for video_urls, @first_frame, @keyframe_1 and @last_frame for frames, and @Name for a subject in elements or a voice in voices. Every mention has to match an input in the same request, or the request is rejected before anything is charged.
  2. 2Turn "the supplied image" into a mention. Many prompts from fal.ai's guide say things like "Use Video 1 for the camera movement and the supplied images for the scene", and they only work with those files attached. On the API, pass the video in video_urls and the images in image_urls, then rewrite the references as @video_1 and @image_1 in the same order.
  3. 3Lock a character as a named subject. Instead of describing the same face in every sentence, send it once in elements: 2 to 4 views with the main one first, or one 3 to 8 second single-shot clip of the person. Then write @Mia every time she appears. It does at the request level what long prompts here try to do with "the same person throughout".
  4. 4Script the sound, since it is always on. Sound cannot be turned off on Kling 4.0, so the prompts that land write it out: the kling4.video examples end with a "Sound:" line, and dialogue is quoted with the language named, as in says in English: "Sorry, was that oat milk or almond?" To give a character a set voice, bind a clip with voices on Kling 4.0 or elements[].voice_url on Flash. With reference videos, keep_original_sound keeps their own audio.
  5. 5Write timed shots as text, and make them add up. A common pattern here is "Shot 1 (0-5s): … Shot 2 (5-10s): …" inside one prompt. The API has no separate storyboard field, so those shots travel as plain prompt text: give each one a single action, and make the time ranges add up to the duration you request, 3 to 30 seconds (up to 20 on Flash).
  6. 6Move format lines into the request. Long X prompts often open with "Format: 16:9, 30 seconds, 24fps, 1080p", and a few ask for 4K. On the API those are settings: duration, resolution (720p or 1080p; 4K is not available) and aspect_ratio (auto, 16:9, 9:16, 1:1 or 21:9). Set them in the request so the text and the settings do not disagree.
  7. 7Keyframes for a planned path, references for a look. Keyframes fix where the shot goes: a first frame, up to 8 middle frames and a last frame, with the total capped by the duration, from 4 frames at 3 seconds to 10 from 9 seconds up. References fix what things look like. You cannot send both in one request, and Flash takes a first frame only.

Prompt formula

Format as parameters (duration, resolution, aspect_ratio) + subject, or @Name for a named subject + one action per timed shot + camera move + light and setting + an @mention for every reference + a "Sound:" line with quoted dialogue and its language

Example from the collection, quoted as posted (@Alin_Reaper05 on X): An exploration ship maneuvers through a vast cloud of charged gas and floating debris. Inside the cockpit, the pilot moves the controls while the captain braces against the console and an alien crew member monitors the storm. The camera moves from the crew toward the forward window, cinematic tension, realistic motion.

Frequently asked questions

What is Kling 4.0, and how is Kling 4.0 Flash different?

Kling 4.0 is the newest video model in Kuaishou's Kling family; it generates sound with every clip and runs 3 to 30 seconds at 720p or 1080p. Kling 4.0 Flash is its lighter tier on the same endpoint and request shape, but with 720p only, 3 to 20 seconds, prompts up to 8,000 characters, a first frame as the only keyframe and no standalone voices list. Choose Kling 4.0 when you need 1080p, more than 20 seconds, middle or last keyframes, or standalone voices.

Who wrote these prompts?

Other people did: creators on X and Civitai, the kling4.video prompt library and fal.ai's Kling 4 prompting guide, and we did not write or edit any of them. Each card quotes the prompt in full, word for word, names the author and links the original. The prompts and clips belong to their creators; our own notes and data are licensed CC BY 4.0. To correct a credit or have an entry removed, email us or open an issue on the GitHub repository.

Where can I run these prompts, and what does it cost?

On apimodels.app, as kling-4.0 or kling-4.0-flash on POST /v1/video/generations, billed per second. Kling 4.0 without video input is $0.157/s at 720p and $0.235/s at 1080p: 5 seconds at 720p is $0.785, 10 seconds at 1080p $2.35 and 30 seconds at 720p $4.71. Flash is $0.094/s: 5 seconds $0.47, 10 seconds $0.94. With a reference video the rate is $0.094/s or $0.141/s on Kling 4.0 and $0.063/s on Flash, per billed second: the output length × 2 when the input video is no longer than the output, or input + output when it is longer, so 10 seconds at 720p with a 5-second reference video is $1.88 on Kling 4.0 and $1.26 on Flash. Reference images and keyframes are not billed separately, and failed generations are not charged.

Why does a prompt from this page fail on the API?

Requests outside the limits get a 400 before a task is created, and nothing is charged. Causes include an @mention with no matching input; a prompt over 10,000 characters (8,000 on Flash, which the longest prompt here exceeds); a length outside 3 to 30 seconds (3 to 20 on Flash); 4K, which is not available; frames mixed with references; reference images under 300 px on a side or outside a 0.4 to 2.5 aspect ratio; and a reference video whose length cannot be read. The API also has no negative-prompt field, no multi-shot storyboard mode and no video extension, so prompts written around those features need to be rewritten as one plain prompt.

Do I need the images or videos the creator used?

Only for prompts that point at them. Text-only prompts run as they are. Prompts that say "the supplied image" or "Video 1", or that name a character from a reference, need your own files in image_urls, video_urls or elements, each called with @. Only upload faces and voices you have the rights to use.

How long can a Kling 4.0 prompt be?

Up to 10,000 characters on Kling 4.0 and 8,000 on Flash. The prompts here run from one sentence to almost 10,000 characters, and the long ones tend to spend their words on a fixed character description, a timed shot list and a sound list rather than on adjectives. If a long prompt describes a reference you are not sending, cut that part.

Can I use these prompts and videos commercially?

The prompts and clips belong to their creators, so check the original post before reusing a prompt commercially. For clips you generate yourself, follow the terms of the service you generate them with, and only use faces and voices you have the rights to.

Run these prompts on apimodels.app

Kling 4.0 is live here alongside 180+ other image, video, audio and language models — one API, one key, pay as you go, with $0.10 of trial credit on sign-up.

This library is open source on GitHub

The whole collection is on GitHub as Markdown and JSON: every prompt with its author's credit and a link to the original on X, kling4.video, fal.ai or Civitai. Prompts are quoted in full, word for word, and belong to their creators. The clips stay with their creators and are linked, not re-hosted. Our own notes and data are licensed CC BY 4.0. Open an issue to correct a credit or have a prompt removed.

View on GitHub

Other prompt libraries