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
@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.
Five steps, one render. Steps 1 and 2 are your two avatars: Avatar 1 brings the gift and ends up running, Avatar 2 gets the gift and becomes the tiger. Any gender, any pairing, the prompts never say he or she. Step 3 builds one two-frame character sheet of both avatars in the film's wardrobe (Nano Banana Pro): this is where faces get locked and where you may recolor hair or restyle, never in the video prompt. Step 4 is one clean photo of your product, any product. Step 5 is the 30s video: @image1 is the sheet, @image2 is the product, all beats timestamped, the twist at 19s, the only camera move is the push-in on the product at the end. Fire as ONE 30s 9:16 Seedance 2.5 render with audio, 720p. Two traps: a small product is tiny in a wide shot, so the final beat pushes in on it while the tiger stays seated; and never let the product end up on the floor, that is where Avatar 1's shoe goes.
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.
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.
SUBJECT. The same @avatar throughout — 25, long honey-blonde hair with sun-lifted ends in a low messy bun with loose strands around their face, green-hazel eyes, freckles across their nose and cheeks, warm sun-kissed skin with real texture, minimal makeup, slim. Soft-yellow sleeveless knit top, loose light-grey trousers, white retro sneakers, dark-green shoulder bag, silver bracelet. Keep face, hair, outfit and accessories identical in every shot. 0–5s. @avatar leaves home with a shopping bag, locks the door, checks their keys, tucks a strand back into their bun, smiles at the camera, walks off down the street. 5–10s. @avatar buys a cup of cold cut mango with lime at the corner store window. Takes a bite, reacts to the sour lime, laughs, offers the cup toward the camera. 10–15s. A small dog behind a chain-link fence notices @avatar and wags. @avatar crouches to let it sniff their hand through the gap. The dog trots along the fence beside them, then turns back. 15–20s. Dry leaves and a few bougainvillea petals drop from the banyan onto their shoulder and hair. @avatar looks up and brushes the leaves away. The camera zooms in awkwardly. @avatar says, "Again?" 20–25s. @avatar sits on a low garden wall and finishes the fruit while a bicycle passes and a neighbour waters plants with a hose. Warm breeze in their hair and clothes; @avatar wipes their hands and adjusts their bag. 25–30s. @avatar walks toward the end of the street, turns back with a playful smile and says, "Let's go." Walks around the corner; the camera follows; abrupt cut to black. AUDIO. Location sound only — cicadas, birds, footsteps on cracked pavement, a bicycle bell, distant scooters, leaves, the hose, the dog, neighbourhood voices, a TV through an open window, camera-handling noise. No music, no narration, no captions.
Sunglesses ThiefRecreate workflow