ASSET MAP — @image1 = the traveller who is leaving (person, identity only). @image2 = the one who stays behind (a different person, identity only). @image3 = the platform of an orbital rail station (location only, no person). ATTACHED IMAGES ARE FINAL: @image1 and @image2 are the people in this film and the images outrank this text. For each of them preserve facial structure, eye shape and spacing, exact skin tone, hairline, hair length, texture and colour, distinctive marks, apparent age, build and proportions, and their gender presentation exactly as shown. Do not beautify, de-age or restyle. Two different faces, each appearing once per frame. WARDROBE (from THIS TEXT, never from @image1 or @image2; the garment is fixed, only its drape adapts): @image1 in an ivory-white EVA pressure suit with a long camel-tan thermal over-mantle worn open, carrying a white helmet low in one hand. @image2 in a charcoal-grey pressure suit with a slate-green utility overjacket, helmet under one arm. A 1985 science-fiction television drama on the platform @image3: tungsten warmth against cold blue planet-light, soft analog broadcast texture, fine grain, gentle optical zooms and fixed shots only, one movement per shot. 0-4s Medium shot, slow optical zoom-out. @image1 stands on the deck of @image3, face toward the lens, the lit windows of a departing shuttle streaking behind, then turns to look down the platform. <shuttle whine, ventilation hum, one footstep> 4-8s The shot cuts to a medium shot, fixed. @image2 steps out of the lit station kiosk under a red illuminated sign reading "PLATFORM 7"; two travellers cross close to the lens, out of focus with faces turned away. @image2 looks toward @image1 off frame. <a pressure door sighing open, muffled voices> 8-11s The shot cuts to a two-shot, fixed. @image2 is in the near foreground with the back of the head to the lens; @image1 faces @image2 and holds the look. <ventilation hum, a distant chime> 11-15s The shot cuts to a wider two-shot at the kiosk window, slow optical zoom-out. At the 13-second mark a second shuttle sweeps across the foreground and blurs the frame; when it clears @image1 and @image2 still stand in the same position. <heavy rush, then a sudden quiet> 15-19s The shot cuts to a close-up of @image1, speaking quietly with a pause between the lines: {I signed the transfer this morning.} {I did not come here to argue about it.} <suit fabric shifting> 19-22s The shot cuts to a close-up of @image2, restrained: {Then why did you come?} <ventilation hum> 22-26s The shot cuts to a two-shot. @image1 lowers the gaze, turns away from @image2 without answering and steps toward the lens; @image2 stays in place and keeps watching. (a sparse warm analog synth pad, two chords) <footsteps on the metal deck> 26-30s The shot cuts to a wide shot down the platform, slow optical zoom-in. @image1 passes the lens on the left, gaze lowered; far down the deck @image2 stands alone under the canopy of @image3. In the last second @image1 glances back once. (the pad fades out) Hands stay anatomically correct with five fingers wherever a hand is visible, and the helmet never merges with the glove. No people other than the two out-of-focus travellers, and no readable face but those of @image1 and @image2. English dialogue only, three lines, quiet, with natural pauses. No subtitles.
Use @avatar as the person in the clip - identity only: face, hair, skin and build exactly as shown, never reinterpreted. Wardrobe comes from this text, not from @avatar: a plain light knit top, simple jeans and simple sunglasses, the same in every second. One 15-second vertical selfie, one unbroken handheld shot, no cuts and no zoom. @avatar sits on a bench in a green city park - trees, grass, dappled daylight, a few people far away and out of focus. Natural light only, no grading, no beauty filter. Head-and-shoulders framing with natural arm drift. The phone is the camera itself and is never visible - no phone, camera body or selfie stick appears in frame; one arm of @avatar is off-camera holding the camera, the other holds the cat. The clip opens mid-action on a fully exposed frame, never on a still or a fade from black, and every second carries action. Exactly one small playful cat, the same one from start to finish, and no other animal anywhere. In the very first second the cat, held in the arms of @avatar, already has a paw raised at the sunglasses and bats at them. @avatar pulls back with a surprised laugh: "What are you doing?" The cat grabs one arm of the glasses with its mouth, pulls them sideways and then completely free, turning its head away proudly - @avatar laughs in disbelief: "Hey, give me those!" The cat climbs out of their arms with the sunglasses, @avatar reaches after them laughing and the framing drifts off centre. In the last beat the cat pushes up toward the lens, its nose almost touching it, @avatar starts saying "You little-" and never finishes as the clip ends on that frame. Diegetic sound only: the voice of @avatar, laughter, soft cat breathing, fabric rustle, park ambience with distant birds. No BGM; generate only environmental sounds and action sounds. No subtitles.
Four steps, one generation each. Step 1 pick any avatar (@avatar). Step 2 turn the visitor's product photo (@product) into a three-view product map on grey so every later step sees the same details. Step 3 a two-frame reference sheet that locks the face, the hair, the jacket and the chained product together (Nano Banana Pro holds the face). Step 4 one unbroken 30s 16:9 Seedance 2.5 render, reference mode, with the sheet and the product map attached. The prompts never name the product or a gender, they read both from the images, so the recipe works with any avatar and any product the courier can hold in their hands. Known traps: never write 'a held beat of silence', the model renders it as a literal frozen frame, write tension as micro-motion instead; never write 'walks to the doors', the model walks to the END of the car, so stage the fight to finish beside the side doors; never cut to an outside camera on a door that already opened, the model closes and reopens it.
CHARACTER LOCK - HIGHEST PRIORITY: The person in every frame is exactly the person in @avatar. 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 identity drift, no other people in the film. ATTACHED IMAGES ARE MANDATORY AND FINAL: If an avatar image is attached, that is the person - reproduce them exactly in every frame. The attached images outrank every word below them; wherever image and text disagree, follow the image. @avatar defines identity only - its clothing, pose, background and lighting are ignored completely. Wardrobe (comes from this text, never from @avatar): a loose cream-and-navy striped knit sweater, straight-leg blue jeans, worn trail sneakers and a small dark backpack, unisex cut, no logos or lettering. Fit each garment to the character's body naturally without altering its design, cut, proportions or colour - the garment is fixed, only its drape adapts. The same in every second of the film. Ultra-realistic cinematic outdoor cinematography, 30 seconds, one continuous immersive handheld follow with no cuts anywhere. @avatar runs without ever breaking stride while the ground transforms under the feet, each new world spreading outward from where a foot lands. The stride, speed and direction never change. Hands stay correct in every frame: five fingers per hand, natural running arm swing. 0-5 seconds - GREEN. The film opens already at full speed: @avatar mid-stride, running hard across a high alpine meadow at golden hour, grass whipping past the lens, burning meteors already streaking down the sky behind. No fade in and no still opening frame. The camera runs behind at shoulder height. 5-10 seconds - LAVA. Mid-stride the grass darkens and splits into black volcanic rock veined with molten orange, heat shimmer and drifting ash. The camera swings around into a front-on lead shot. 10-15 seconds - ICE. The molten crust freezes over into blue glacier ice with wind-driven snow streaming across it. Breath fogs. @avatar runs straight at the camera as it leads backwards, close enough that the face is fully readable. 15-20 seconds - DESERT. The ice turns to sand: red-gold dunes, hard flat light, sand smoking off the crests. The camera drops to ground level beside the feet, then rises back behind @avatar. 20-25 seconds - JUNGLE. The sand greens over into dense wet jungle, huge leaves and shafts of light through the canopy, leaves brushing past the lens. 25-30 seconds - GREEN AGAIN. The jungle thins back into the same golden meadow. @avatar slows, stops and turns to look straight into the lens, face fully readable, then out at the way the world has come. Final wide, clouds below the ridge. Light travels with the terrain: warm golden hour, hot orange bounce, cold blue, hard flat sun, green filtered light, then golden hour again. Sound: breathing and footfalls all the way through plus the sound of each world in turn, and a restrained low score. No subtitles.
@avatar is the lone warrior. @avatar defines IDENTITY ONLY - face, hair and skin. Gender, face, hair and skin come entirely from @avatar and never from this text; the clothing, pose, background and lighting of @avatar are ignored completely. Wardrobe (comes from this text, never from @avatar): a heavy dark grey hooded coat with a long torn cloak over one shoulder, dark wrapped forearms and dark boots, all of it scorched and ash-dusted, unisex cut, no logos or lettering. The same in every shot. Stylized cinematic CG dark-fantasy, 30 seconds, one continuous firestorm over a scorched black ash plain with industrial towers and wind turbines far off in the smoke and heat haze. Long lens, handheld weight, low angles and straight overheads, real motion blur, embers and ash crossing the lens. The world and every enemy burn in deep ember orange, and the light from @avatar's blade is the only white-hot light in the film. 0-5 seconds - A horde of burning beast-riders, their bodies cracked black rock with fire running in the seams, charges in from the horizon. @avatar slides low across the ash crust toward them, the long sword held back, its edge cutting a thin white-hot line through the embers. 5-9 seconds - @avatar plants both feet and raises the sword overhead in both hands; the blade ignites into a long horizontal bar of white-hot light. Straight overhead: the bar comes down into the ash and opens a wide crater ringed with burning embers, the horde curving around the rim into concentric rings. 9-15 seconds - @avatar drops into the centre of the crater and a radial shockwave throws the nearest ranks outward, then dashes low across the plain, the sword dragging one continuous white-hot line that blasts a whole row of burning beasts into cinders and smoke. 15-21 seconds - A wave of white-hot energy sweeps an entire flank and bodies lift off the ground into a rising column of fire and ash, and the column takes shape as a long dragon of flame and embers uncoiling up out of the firestorm. 21-27 seconds - A molten colossus heaves up out of the ash behind @avatar, lava glowing in every seam of its cracked black crust, and swings one huge arm across the frame. @avatar slides flat under the arm and drives the glowing blade up under its jaw; the giant goes over and slides across the crust, throwing up a bank of cinders. 27-30 seconds - The fire dragon collapses back into falling embers. Final wide: @avatar walks away, small in the frame, two tracks in the ash, the plain burning dark orange behind. Sound: the low roar of fire throughout, ash crunching under the boots, blade impacts, beast roars, a deep low hit on each energy release, and a restrained low orchestral score. No subtitles.
15-second vertical 9:16 fashion lookbook music video. The only person is the person from image 1: same face, hair, skin and body in every shot, only the outfit changes. Premium editorial fashion photography meets Y2K magazine design: black-and-white base, electric cobalt blue accents, oversized typography, scan lines, crosshairs, grids, thin borders, subtle film grain. Camera controlled, model always centered. Structure: 0-1.5s white studio, the brand name from your card expands huge behind the model. 1.5-3s fast push-in to a close-up, direct eye contact. 3-12s six complete outfit changes, one every 1.5 seconds on the beat, each with a new wordless magazine layout and a new pose: natural stance, one step forward, half-turn, lean-in with a smile under the same name in cobalt, a full deep squat sitting on the heels, then standing again. 12-15s final look in a sharp suit: the model walks to camera, stops, crosses arms, the brand name appears large across the lower frame, freeze on the last beat. Outfits: seven looks read from the outfit sheet by position. Brand: read from the brand card. Text rule: the only letters ever on screen are the brand name copied from the brand card, exactly three times, huge and exact. No numbers, no other words, no small print. Audio: music only, a confident runway electronic beat at 120 BPM, no voice, no lyrics. Avoid: face drift, extra limbs, distorted hands, misspelled or invented text, cartoon or CGI look, watermark, subtitles.
subject_definitions: @image_1 - the performer, first reference image; it defines face and identity. CHARACTER LOCK - HIGHEST PRIORITY: the person in every shot is exactly the person in @image_1. Preserve the facial identity, exact skin tone, hairline, hair length, texture and colour, apparent age, build and body proportions of @image_1 shot to shot, and the gender presentation of @image_1 exactly as shown. Do not beautify, slim, de-age or restyle @image_1. No other people appear. @image_1 outranks this text: wherever @image_1 and these words disagree, follow @image_1. @image_1 defines identity only - its clothing, pose, background and lighting are ignored. summary: [reference generation] A fifteen-second vertical fashion film: @image_1 walks an alpine meadow trail above a glacial lake and speaks one line across three shots. retention_analysis: @image_1 (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - identity, skin tone, hair, apparent age and build stay exactly as in the reference. detailed_description: Photorealistic cinematic fashion film at golden hour, warm low sun against the cool turquoise of the lake, hazy palette, shallow depth of field, subtle film grain. Wardrobe lock: @image_1 wears an oversized brown knit sweater and wide ivory trousers, taken from this text and not from @image_1, with no logos or printed words; fit each garment to the body of @image_1 without altering its design, cut or colour - only its drape adapts. Both hands of @image_1 keep five fingers. [Shot 1] A close shot on the sleeve and shoulder of @image_1, wildflowers crossing the foreground out of focus. The camera pulls out with large amplitude at slow speed as mountain wind lifts the knit fibres and the hair of @image_1, opening onto the trail, a turquoise glacial lake far below and a snow-patched ridge behind. [Shot 2] At 00:04.500, the shot cuts to a tracking shot alongside @image_1 walking unhurried, one hand brushing the grass. @image_1 (S1), speaking softly and unhurried, says: <d>[English] Sometimes all you need is a quiet place, a little fresh air,</d> <scenetrans> and the sentence continues uninterrupted into the next shot. [Shot 3] At 00:10.000, <scenetrans> the shot transitions to a close-up of @image_1 turning slightly toward the camera, the voice carrying over without a break. The camera pushes in with small amplitude at slow speed as @image_1 (S1) finishes: <d>[English] and a moment to slow down and enjoy where you are.</d> The camera then holds a static shot through the final frame. overall_soundscape: A steady mountain wind moves through the meadow grass and the knit fabric throughout. Quiet footsteps land on packed earth and gravel, and a few small birds call over the valley. non_diegetic_music: N/A
WHAT YOU CHANGE: TWO PHOTOS OF PEOPLE, ONE PRODUCT PHOTO, AND FOUR SLOTS IN THE VIDEO PROMPT ([PRODUCT], [BEFORE], [USE], [AFTER]). NOTHING ELSE. Upload a photo of two people (anyone, one photo each) and one clean photo of @product, all at least 300 px on each side. Steps 1 and 2 turn the two photos into character sheets that hold the faces, step 3 turns the product photo into a three-view product map, step 4 renders the film with both character sheets, the product map and the original photo attached as references. Before firing, answer four questions and paste the answers into the four [SLOTS] of the video prompt (each slot explains itself and carries a mascara example): 1) PRODUCT: what is it, in three words? 2) BEFORE: what does the close-up show before anyone uses it? 3) USE: what does the person do with it, in one sentence? 4) AFTER: what has visibly changed? The same BEFORE answer also goes into the two character sheet prompts, so the characters start in the before state. Everything else stays as written. Two rules: never describe an effect that leaves a face (flash, gust, glow), Seedance renders it as mist; and keep six stages, more than that in 15 seconds collapses into a calm two-shot.
HOT. LOUD. REPEAT.Recreate workflow