CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Refer to them only as they/them in this prompt. ATTACHED IMAGE IS MANDATORY AND FINAL: The attached image outranks every word written below it: wherever the attached image and this text disagree on the FACE, follow the image. ASSET MAP: @image1 — the person. Photocopy @image1 for face, hair, skin and identity only. Do not copy the olive-green quarter-zip, the white crew t-shirt, the crossed-arms studio pose, or the lounge interior from the still. Ignore any pad around the still — that pad is not a set. Never cut to the attached still as frame 0. WARDROBE — TWO LOOKS ONLY: - 0–8s (bedroom wake, then kitchen coffee): pajamas only — a matching sleep set (soft long-sleeve pajama top and pajama pants). No blazer, no office shirt, no street coat, no olive zip, no bag, no umbrella in this block. - 8–16s (getting ready in a dressing area / by the front door, NOT in the kitchen): they change out of the pajamas into formal first-day clothes — a dark tailored blazer over a light button-down shirt, tailored trousers. Pajamas off; formal on before they leave. Then they pick up bag and umbrella at the door. - 16–30s (wet city and office): formal clothes only. No pajamas on the street or at the office. Do not restyle hair. Do not mix the two looks in one shot. ROOMS — HIGHEST PRIORITY: The bedroom and the kitchen are two different rooms. - Bedroom: bed, window, rain on the glass. They wake HERE. - Then they WALK OUT of the bedroom through a doorway / hall into a real kitchen — separate space with a counter, cabinets, sink, and a coffee maker or kettle. Coffee is made ONLY in that kitchen. No coffee tray on the bed. No kitchen counter beside the bed. No brewing in the bedroom. - Getting dressed happens after coffee, in a dressing area or at a mirror near the front door — not back in bed. UMBRELLA PHYSICS — HIGHEST PRIORITY: The umbrella never holds itself, never stands on its own, never floats, never hovers. Gravity. When the umbrella is open, one of their hands is visibly gripping the handle the entire time. When they check the time (watch or phone), the OTHER hand holds the umbrella — they do not let go. The umbrella does not stay upright without a hand. Closed umbrella is carried in a hand or tucked under an arm, never standing alone. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. SINGLE SUBJECT: @image1 is the only named subject — background pedestrians, drivers and passersby may appear naturally but are never named, aged or described by ethnicity/gender, only by generic role and action. Create a 30-second ultra-photorealistic live-action vlog of @image1 waking to a rainy morning in pajamas, walking to a separate kitchen to make coffee, changing into formal clothes, grabbing an umbrella, walking through a wet city, and arriving at a new office just before their first shift. Already in motion from frame 0 — never a frozen studio pose. 0–8s: @image1 wakes up in pajamas in the bedroom, glances out the bedroom window at the rain, sighs with a small smile, then walks through a doorway into a separate kitchen and makes coffee at the kitchen counter. Modern smartphone vlog style — natural handheld movement, subtle shake, autofocus changes. Dialogue: “Good morning… apparently, it’s raining. Perfect first-day weather.” 8–16s: @image1 gets ready away from the kitchen — taking off the pajamas, putting on the formal blazer and trousers, checking themselves in a hall/door mirror in the full formal look, grabbing their bag and picking up the umbrella with their hand by the door. Natural expressions, believable human movement. Dialogue: “First coffee. Then… new job.” 16–24s: @image1 walks through the wet city streets in the formal clothes. Umbrella is open and held in one hand the whole time. They navigate puddles, reflections, passing traffic and other umbrellas. If they check the time, the free hand does that while the umbrella hand keeps gripping the handle — the umbrella does not stand or float by itself. Realistic rain, wet clothing, natural pacing — not rushed. Dialogue: “Two minutes early. I’m impressed.” 24–30s: @image1 arrives at the office entrance in the same formal clothes, still holding the umbrella, shakes it off with their hands, takes a breath, and steps inside. Dialogue: “Okay… here we go.” CAMERA / REALISM: natural handheld movement, subtle shake, autofocus changes, realistic rain, puddles, reflections, traffic, umbrellas, wet clothing, natural expressions, believable human movement, no overly smooth gimbal look. Landscape 16:9. AUDIO: natural diegetic audio only — rain, footsteps, traffic, umbrella sounds, ambient city noise, and the spoken dialogue lines above. No music, no narration, no voiceover other than those lines. Do not generate: music, narration, CGI look, artificial rain, face changes, distorted anatomy, extra fingers or limbs, impossible physics, floating umbrella, coffee in the bedroom, subtitles, on-screen text, logos, or watermark. Never freeze on the attached still.
Drag the clip sideways
VERTICAL 9:16 30 seconds. Handheld selfie GRWM. Hard cuts. ONE person. No on-screen captions. No hat at any second. CHARACTER LOCK: the person is exactly @image1. Preserve face, hair, skin, age, build, gender presentation. Use they / their / them only. @image1 = FACE only. Photocopy this person. Do not copy studio wardrobe from the lock. WARDROBE: gold CROSS necklace always visible. Black denim jeans. They PULL ON a loose-fit brown t-shirt (already in jeans — skip a long shirtless intro). Brown leather belt. Brown leather cowboy boots. Gold ring. Hair uncovered, no hat. VOICE: casual influencer, clear English lip-sync. 0.0–8.0s Modern walk-in closet, white walls, black door. Eye-level selfie. Black jeans, pull on the brown t-shirt, step back, fasten the belt. VO: “What’s going on guys. Quick get ready with me. Throwing on this brown shirt and a belt.” 8.0–13.0s Hard cut. Hold brown cowboy boots to the lens, then they’re on. Close-up: gold ring onto a finger. VO: “Going with my nicest brown boots to match, and adding the gold ring.” 13.0–24.0s Hard cut. Bathroom, black marble. Small WHITE squeeze bottle with a BLUE cap to the lens. Open, dab on a finger, rub into face. Tight on face and product. VO: “But this right here is the main event. If you know, you know. You gotta keep the face fresh and hydrated.” 24.0–27.0s Same bathroom. Sleek BLACK cologne bottle. Two sprays on neck and chest. Confident nod. VO: “Quick spray of this cologne. Always gets a ton of compliments.” 27.0–30.0s Hard cut. Bedroom, large bed. Hand through hair — NO HAT. Step back, one arm slightly raised. VO: “Alright, that’s the final look. Let’s head out.” Same person every cut. Gold cross on. Hatless. No extra people. Never a studio still as frame 0.
16:9 30 seconds. Seedance 2.5. Cinematic live-action, light-comedy sparring in a luxury apartment. Two people only. No dialogue. CHARACTER LOCK: @image1 and @image2 are exactly those people. Preserve each face, hair, skin, age, build, gender presentation. Do not beautify or restyle. No other people. Use they / their / them only. @image1 = PERSON 1 (the one who dodges, two-finger taps, gets the kiss, then the hook). Photocopy FACE only. Do not copy studio wardrobe from the lock. @image2 = PERSON 2 (the one who punches, gets tapped, kisses, then the uppercut). Photocopy FACE only. Do not copy studio wardrobe from the lock. Casual fitted apartment clothes. Bare hands. SET: one luxury living room, evening. Floor-to-ceiling city skyline, warm interior vs cool dusk. Wood walls, low sofa and stone table at the edges, thick light carpet in the CENTER. All action on that open carpet. @image2 starts LEFT, @image1 RIGHT. AUDIO: no speech, no lyrics. Breath, effort, footsteps, cloth, punches cutting air. Two light tap sounds on the head knocks. Light tight rhythm music, then quieter after the strategy change. Solid hit on the last punch, dull carpet thud on the fall. 0.0–4.5s Already sparring. @image2 guard up, fast jabs and hooks at head height. @image1 slips, leans, lets punches miss. Bigger right cross; @image1 steps outside, behind the shoulder, RIGHT HAND: index+middle fingers together slightly bent, one light knuckle TAP on the top of the head, then retract. 35mm two-shot. Light tap — not a fist, slap, grab, or forehead flick. 4.5–7.3s 75mm on @image2: surprise → pout → frown. @image1 half-step back, easy. 7.3–12.6s Harder attack. @image1 ducks a hook, rises; jabs, fades. Second independent duck-and-rise, then circles behind and TWO-FINGER TAPS again. @image2 flinches, stays standing. Two separate ducks. 12.6–15.8s 85mm @image2: sly small smile — an idea. Hands unclench. No laugh, no magic. 15.8–18.0s Over @image2 shoulder on @image1: confused head tilt, hands lower, guard down. 18.0–21.4s Side two-shot, @image2 left / @image1 right. Short kiss on the lips (~0.25s), no hug. Pull back. THEN @image1 is stunned. @image2 jaw sets, right fist closes. 21.4–25.5s One right uppercut to the jaw while stunned. Contact, then slow-mo: head snaps, fall onto the carpet on the back. @image2 stays standing. No extra punches. No blood. 25.5–27.7s Low on @image1 on the carpet, dazed, eyes open, not unconscious. @image2’s legs in the background. 27.7–30.0s Tilt up to @image2 looking down, small satisfied smile. No hug, no help-up, no extra people. Same two faces every second. Never a studio still as frame 0.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, eyebrows, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. No face changes, no identity drift. No other people share their face. Use they / their / them only. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person — reproduce them exactly, in every single frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached images outrank every word written below them: wherever an attached image and this text disagree, follow the image. ASSET MAP: @image1 — the character. @image1 is face, hair, skin and identity only. Ignore the café, bookshelves, window street, espresso machine, and any beige pad around the still — that pad is not a set. Wardrobe is comfortable at-home loungewear from the scene (soft knit, lounge pants) — do not treat the still as a frozen smiling headshot, and do not copy the café as the location. SINGLE SUBJECT: only @image1 appears in this video — no other people, hands, or faces enter frame at any point. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. PROP CONTINUITY: the laptop, the blanket, and a mug on the side table are all present from Scene 1 onward — nothing new appears later that wasn’t already established (only refills/accumulation of the same mug, shown clearly as a growing stack, not a new object type). Unmarked laptop — no brand logos on the lid. CAUSALITY LOCK: every prop change has a shown cause — the mug stack grows only through visible refill actions across the cuts, the window light shifts only through a natural time-lapse of the sky, and the laptop/room-scale shift in Scene 4 is an intentional stylized visual metaphor, not a continuity error. OPENING LIGHTING — HIGHEST PRIORITY FOR 0–4s: Do not open on an empty couch, a blown-out lampshade, a dark hallway, or a person entering from the shadows. Frame 1 already has @image1 in a medium shot on/near the couch, face fully in frame and fully readable. Warm practical lamp light plus a soft fill so skin, eyes and hair are correctly exposed from the first frame — cozy, even, cinematic, not gloomy, not silhouette, not spotlighted from behind. The lamp is a light source in the room, not the subject. No underexposed doorway, no motion-smear collapse as the first beat. Create a short cinematic, humorous lifestyle video about someone who refuses to sleep because they finally have time for themself after work — this time, the trap is “just one more episode.” SCENE 1 — 0–4s: Late evening, already home. Warm, even lamp lighting on @image1 from frame 1. They drop their bag beside the couch, settle into comfortable loungewear, and sit down — face readable the whole time. Exhausted but relieved, they reach for a laptop already on the couch. Exposure stays correct on their face. SCENE 2 — 4–8s: They settle under a blanket and dim the room lights (a visible, motivated dim — not a sudden blackout). They open a streaming show on the laptop. The laptop’s glow mixes with the remaining warm lamp. A soft whispered voice-over: “Just one more episode.” They press play, smiling. Face stays readable. SCENE 3 — 8–12s: A cinematic time-lapse of the night passing — shown only through the sky outside the window steadily darkening and the moon rising higher, never through any on-screen clock or number. Intercut quick beats of @image1 still watching, eyes growing progressively more tired, soft dark circles slowly deepening under their eyes with each cut. The mug on the side table is refilled again each time, the stack quietly growing taller. Faces stay lit enough to read. SCENE 4 — 12–15s: Visual metaphor, stylized and surreal: the laptop screen appears to loom larger in frame while @image1 curls smaller beside it, as if the show is consuming the night. Their dark circles read as soft, ink-like shadows beneath their eyes. Still enough light on the face to hold identity. SCENE 5 — 15–18s: Close-up on @image1's face, lit by a mix of leftover lamp warmth and laptop glow, heavy-eyed. They glance at the tall mug stack beside them, then back at the screen — and immediately click to the next episode anyway, whispering “Just one more...” Cut to black as the faintest hint of dawn light touches the window. STYLE: cinematic realistic lifestyle film, relatable internet humor, warm even lamp lighting at the open mixed later with cool laptop-screen light, subtle exaggerated dark circles, expressive facial acting, smooth camera movements, realistic skin and fabric, shallow depth of field, natural handheld moments, tasteful comedy, premium social-media reel aesthetic, seamless time transitions, highly polished visual storytelling. Vertical 9:16. Never freeze on the reference still. CAMERA: Scene 1 opens already as a medium shot on their face and upper body — not a foreground couch/laptop still-life with them out of focus in the back. Then close-ups, medium shots, natural handheld moments, shallow depth of field, natural focus transitions. AUDIO (native, synced, no BGM, no extra music): home-evening ambience, bag drop, fabric and blanket, laptop keys/trackpad, a soft whispered “Just one more episode,” mug refill clink, then a last whisper “Just one more...” No karaoke, no soundtrack bed. Do not generate any legible on-screen text, subtitles, numbers, clocks, or timestamps anywhere in frame. No BGM, no watermark, no logos, no distorted hands, no extra fingers or limbs, no duplicated people, no flickering, no sudden identity changes.
VERTICAL 9:16 15 seconds. ONE continuous handheld smartphone recording. Spectator at standing eye height beside a running lane. No cuts. No slow-mo. No captions. No music. No logos. CHARACTER LOCK — the person is exactly @image1. Preserve facial identity, hair, skin, age, build, gender presentation. Do not beautify or restyle. Use they / their / them only. @image1 = FACE only. Photocopy this person. Do not copy studio wardrobe from the lock photo. OUTFIT: fitted cobalt-blue short-sleeve top, high-waisted light-grey straight-leg trousers, white low-top sneakers. Their hair, exactly as in @image1, moves with the run. They are silent. Crowd noise only. SET: public plaza, dark-grey stone slabs, glass towers, trees, bright day. Dense spectators behind silver barriers. ONE enormous matte charcoal-grey curved ramp, several storeys high, starts off-screen right then enters during the pan. CAMERA: one phone lens, slight shake, tilted horizon, imperfect track, motion blur on the fast pan. Stay on the ground. Zoom ONLY after they land. 0.0–4.0s Already sprinting from left background toward camera. Crowd behind them. ~2–3s they rush past 1–2 metres away, filling the frame. Spectator pans right: front ¾ → side → rear ¾. They run toward the ramp. ~4s their foot hits the ramp’s lower curve. 4.0–6.9s Continuous run UP the steepening curve. Camera tilts up. They get small against the towering ramp. Last running footstep just below the lip launches them. Palms never touch the ramp. 6.9–9.9s Launch, several rapid end-over-end somersaults against sky and buildings, then they open out. ~9.9–10s BOTH sneakers hit the paving inside the barriers. Off-screen (~6.7–9.3s): “Oh my God, that was insane!” 10.0–12.4s Deep knee bend, recover, small step, upright by ~10.7, satisfied smile. Crowd erupts. Off-screen (~10.3–12s): “Whoa! That was crazy!” 12.4–15.0s Fast 3–4x smartphone zoom ~0.5s to a medium of them. ~13.2 they smile bigger, both arms up. Crowd still cheering. Off-screen (~12.7–13.6s): “Oh, no way!” End on raised arms. Same person every second. Crowd is behind barriers — extras, not a second hero. Live phone audio. Never a studio still as frame 0.
CHARACTER LOCK — HIGHEST PRIORITY: The person in every shot is exactly the person in @image1. Preserve their facial identity, facial structure, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, build and body proportions — identically, shot to shot. Preserve their gender presentation exactly as shown; do not masculinize, feminize or otherwise reinterpret it. Do not beautify, slim, de-age or restyle them. Refer to them only as they/them in this prompt. ATTACHED IMAGE IS MANDATORY AND FINAL: The attached image outranks every word written below it: wherever the attached image and this text disagree on the FACE, follow the image. ASSET MAP: @image1 — the person. Photocopy @image1 for face, hair, skin and identity only. Do not copy the olive-green quarter-zip, the white crew t-shirt, the crossed-arms studio pose, or the lounge interior from the still. Ignore any pad around the still — that pad is not a set. Never cut to the attached still as frame 0. WARDROBE (scene, not the still): they wake in simple home lounge clothes, then put on a dark tailored blazer over a light shirt, grab a bag and a compact umbrella for a first-day commute. Do not restyle hair. HANDS: hands are always anatomically correct with five fingers each, naturally proportioned, in every shot they appear. SINGLE SUBJECT: @image1 is the only named subject — background pedestrians, drivers and passersby may appear naturally but are never named, aged or described by ethnicity/gender, only by generic role and action. Create a 30-second ultra-photorealistic live-action vlog of @image1 waking to a rainy morning, making coffee, getting ready, grabbing an umbrella, walking through a wet city, and arriving at a new office just before their first shift. Already in motion from frame 0 — never a frozen studio pose. 0–8s: @image1 wakes up, glances out the window at the rain, sighs with a small smile, and heads to the kitchen to make coffee. Modern smartphone vlog style — natural handheld movement, subtle shake, autofocus changes. Dialogue: “Good morning… apparently, it’s raining. Perfect first-day weather.” 8–16s: @image1 gets ready — putting on a blazer, checking themselves in the mirror, grabbing their bag and umbrella by the door. Natural expressions, believable human movement. Dialogue: “First coffee. Then… new job.” 16–24s: @image1 walks through the wet city streets, umbrella up, navigating puddles, reflections, passing traffic and other umbrellas. Realistic rain, wet clothing, natural pacing — not rushed. Dialogue: “Two minutes early. I’m impressed.” 24–30s: @image1 arrives at the office entrance, shakes off the umbrella, takes a breath, and steps inside. Dialogue: “Okay… here we go.” CAMERA / REALISM: natural handheld movement, subtle shake, autofocus changes, realistic rain, puddles, reflections, traffic, umbrellas, wet clothing, natural expressions, believable human movement, no overly smooth gimbal look. Landscape 16:9. AUDIO: natural diegetic audio only — rain, footsteps, traffic, umbrella sounds, ambient city noise, and the spoken dialogue lines above. No music, no narration, no voiceover other than those lines. Do not generate: music, narration, CGI look, artificial rain, face changes, distorted anatomy, extra fingers or limbs, impossible physics, subtitles, on-screen text, logos, or watermark. Never freeze on the attached still.
VERTICAL 9:16 30 seconds. Talking-head GRWM. Phone on the vanity. ONE person. NO ON-SCREEN TEXT. NO captions. NO subtitles. NO karaoke. NO lower-thirds. Picture + voice only. CHARACTER LOCK: the person is exactly @image1. Preserve face, hair, skin, age, build, gender presentation. Use they / their / them only. @image1 = FACE only. Photocopy this person. Do not copy studio wardrobe from the lock. WARDROBE: silky nightgown / slip. Hair in a WHITE TOWEL turban. Luxury vanity. Never a studio headshot as frame 0. Never say a product name. “one thing” and “it’s in my bio” only. They SAY each line WHILE doing that makeup step. MAKEUP ORDER — LOCKED: 0.0–4.0s NO makeup yet. Bare face, close, venting. THEN they pick up PRIMER and dot it on. 4.0–10.0s PRIMER blending into FOUNDATION. 10.0–13.0s CONCEALER tap-tap-tap, THEN POWDER. Tired face. 13.0–22.0s BRONZER then BLUSH. Hands slow. Brush PAUSES mid-air on “one thing.” Blush brighter. 22.0–26.0s MASCARA, quick strokes, smirk. 26.0–30.0s LIP product, lean back, full finished face, slight smile. 0–4s: “Get ready with me while I tell you why the freelancer lifestyle never sleeps. A client texted me at eleven forty-seven P M — wanted a full ad campaign — video, copy, launched — by 9am. And I said yes.” Never say boring. Say “never sleeps.” 4–10s: “So by midnight I’ve got six tabs open. Video. Captions. Stock photos. Ad account. And one just to remember my logins.” 10–13s: “By 2 am I was beat.” 13–22s: “Next morning, half-dead, I found… one thing that does it all.” Pause on “one thing.” “You type what you’re selling. It writes the ad, makes the video, launches it — and tells you what’s actually working.” 22–26s: “Same client, next campaign? Twenty minutes. From my phone. In bed.” 26–30s: “You’ll still get the eleven P M texts. You’ll just survive them. It’s in my bio.” Same person. Same nightgown. Same towel. No extra people. Zero on-screen words.
VERTICAL 9:16 30 seconds. Outerwear UGC review. Hard cuts. One person only. CHARACTER LOCK — HIGHEST PRIORITY: the person is exactly the person in @image1. Preserve their facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, freckles and distinctive marks, apparent age, build and body proportions. Preserve their gender presentation exactly as shown. Do not beautify, slim, de-age or restyle them. No other people in frame. Use they / their / them only. @image1 = FACE only. Photocopy this person. Do not copy studio wardrobe from the lock photo. @image2 = THE RAINCOAT. Photocopy THIS garment: exactly as shown in @image2 — same colour, length, cut, closures, pockets and fabric. NEVER a different colour. WARDROBE every second: @image2 raincoat over a black turtleneck, black jeans, black over-the-knee boots. NEVER white sneakers. They talk to camera, English, lip-sync. 0.0–4.0s City sidewalk. They point to the raincoat. Cut to CU of the coat's waist and fabric. VO: “I’ve been testing this new raincoat, and I wanted to see how it actually performs in different conditions.” 4.0–9.0s Medium profile walking on a sidewalk, then CU of the coat moving as they walk. VO: “It’s lightweight, comfortable, and really stylish to wear all day.” 9.0–13.0s Medium front-tracking brisk walk on an asphalt park path, then CU of the hood. VO: “For walking, I really like how breathable the material is.” 13.0–18.0s Basketball court. They pose to show length and fit. Cut to CU of the deep pockets. VO: “I also wanted to show off the practical details like these deep pockets.” 18.0–23.0s Wet city street in the rain. Then slow-mo CU of raindrops beading and rolling off THIS coat's fabric. VO: “And it keeps me completely dry when the weather gets bad.” 23.0–30.0s Empty concrete parking garage. They walk toward camera. Final medium in the raincoat. VO: “After testing it out, this raincoat definitely feels built for everyday wear.” Same person. Same @image2 coat. No extra people. No on-screen text. No logos. Never a studio headshot as frame 0.
Last TouchSeedance 2.5 · 9:16Recreate workflow