Recreate the viral Rumpelstiltskin tip toe scene with two faces: a "shhh", a gasp, and the half-squat tip toe dance in pointed slippers, in a 1980s fantasy-film barn. 12 s, 9:16.
Drag the clip sideways
Recreate the viral Rumpelstiltskin tip toe scene with two faces: a "shhh", a gasp, and the half-squat tip toe dance in pointed slippers, in a 1980s fantasy-film barn. 12 s, 9:16.
REFERENCES: @image1 is the person. @image2 is the PRODUCT, a reusable cup. CHARACTER LOCK — HIGHEST PRIORITY: @image1 is the person, exactly as shown. Preserve facial identity, facial structure, eye shape and spacing, nose, mouth, exact skin tone, hairline, hairstyle, hair length, texture and colour, makeup, freckles and distinctive marks, apparent age, build, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. @image1 is the only person in focus; no other person is ever in the foreground. The person is @image1 — no pronouns, no description. WARDROBE: in every shot @image1 wears the same outfit — the clothes worn in the @image1 photo, or simple casual everyday clothes in colours that suit @image1. Never a robe. PRODUCT LOCK: the PRODUCT keeps its exact shape, colour, finish, lid, proportions, label and markings from @image2 in every shot; never redesign it, never invent text, stickers, barcodes or logos, never duplicate it — exactly ONE product exists in the film. Ignore the background of @image2. Only the FRONT of the PRODUCT, with its printed lettering, ever faces the camera; its back is never shown. Other drinkware in the film — a clear glass café cup and an old plain white ceramic mug — is plain, unbranded and clearly a different object from the PRODUCT. DRINKING: whenever @image1 drinks from the PRODUCT, it is done the way this cup is really drunk from — @image1 opens or uses the lid exactly the way the lid in @image2 is built and drinks through it, or drinks with the lid off. Never sipping from a closed lid. ORIENTATION: the footage is NOT mirrored. The product's lettering reads correctly, left to right, exactly as in @image2, in every shot, including the car selfie shots. TEXT AND LOGOS: no on-screen text, captions, subtitles, split screens or picture-in-picture. The product's markings appear only on the product — never on cars, cups, mugs, shelves, boxes, signs or clothing. FORMAT: an influencer UGC testimonial filmed on a phone, 9:16, full-screen hard cuts that alternate between A-ROLL (@image1 talking straight to the camera from the driver's seat of a parked car, natural daylight, steering wheel in the lower corner, the phone held by the off-screen hand at arm's length) and full-screen B-ROLL clips of @image1's day. In the A-ROLL @image1 speaks the lines on camera with matching lip-sync; in the B-ROLL the same voice continues as a voiceover and @image1's lips do not mouth the words. ACTING: dramatic, excited influencer energy — big eyes, raised eyebrows, gasps, hand gestures, leaning toward the lens, real enthusiasm, talking fast and naturally; never cartoonish. MOTION: real-time natural speed, no slow motion; objects move only when a hand moves them; liquids pour and land believably. TIMELINE (25 s): 0–3s: A-ROLL, car. On frame one @image1 is already mid-sentence, leaning toward the lens and holding the PRODUCT up beside the face, front lettering to the lens; the free hand points at it; eyebrows up. @image1, on camera: "Okay — everyone on a budget NEEDS to know about this cup!" 3–5.5s: B-ROLL, a sunny outdoor café table. @image1 sips a creamy latte with a thick layer of milk foam from a clear glass café cup held in both hands, eyes closing in bliss. Voiceover: "I was spending an insane amount on café coffee," 5.5–8s: B-ROLL, home kitchen. @image1 takes a sip from an old plain white ceramic mug and pulls a dramatic disgusted face, nose scrunched. Voiceover: "because it just tasted SO much better than mine." 8–10s: A-ROLL, car. @image1 tilts the PRODUCT toward the lens, front lettering visible, eyes wide, finger raised. On camera: "And then I figured out why…" 10–12s: B-ROLL, top-down close-up: @image1's hand holds the old white mug toward the camera; its inside is stained brown. Voiceover: "It's the inside of your cup —" 12–14s: B-ROLL, top-down close-up: @image1's hand holds the PRODUCT, lid off, toward the camera, showing its clean inside. Voiceover: "it literally changes how your coffee tastes!" 14–16s: B-ROLL, kitchen counter close-up: rich dark coffee pours from a plain clear glass carafe into the open PRODUCT, front lettering facing the camera, steam rising, the PRODUCT filling up. 16–19s: A-ROLL, car. @image1 opens the PRODUCT's lid the way it is built in @image2, sips from it, eyes close, a delighted "mmm", then grins at the lens. On camera: "This one? Café-good. Every. Single. Time." 19–22s: B-ROLL, grocery store aisle with shelves of plain unbranded food packages — cereal boxes and snacks, no cups or drinkware on the shelves. @image1 walks toward the camera holding the PRODUCT, opens the lid the way it is built in @image2, takes a sip and grins. Voiceover: "And it comes with me literally everywhere." 22–25s: A-ROLL, car. Medium close-up: @image1 holds the PRODUCT next to the cheek — beside the face, not covering it — front lettering to the lens, points at it with the other hand and gives a knowing, excited look; holds on @image1 and the PRODUCT until the end. On camera: "Trust me — you have GOT to try this!" SPEECH: @image1 says ONLY the lines written above, word for word. No other words, no ad-libs, no filler, no brand names. SOUND: @image1's natural, energetic voice close to the phone mic, every word fully clear; a light upbeat pop beat low underneath; soft café, kitchen and store ambience in the B-ROLL. QUALITY: anatomically correct — two arms, two hands, five fingers per hand, no extra or detached limbs; natural movement and believable physics; the same face, hair and outfit in every shot; the PRODUCT exactly as in @image2; realistic smartphone footage, not glossy commercial.
CHARACTER LOCK — HIGHEST PRIORITY: @image2 is the person, exactly as shown. Preserve 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, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. @image2 is the only person in focus and the only person in the foreground. The person is @image2 — no pronouns, no description. PRODUCT LOCK: @image3 is the product. Keep its exact shape, colour, finish, proportions and markings in every shot; never redesign it, never invent a logo, never duplicate it. Ignore the background of @image3 — only the product itself carries over. @image1 shows how the product looks while it is in use: from 0:05 to the end, the product is in use exactly as in @image1 and nothing else of it is held or visible. PRODUCT STATE — a strict timeline: 0:00–0:03 the product is in @image2's right hand. 0:03–0:05 @image2 puts the product into use exactly as in @image1. From 0:05 to 0:20 the product appears only in use, as in @image1. LOGOS: the product's markings appear ONLY on the product itself — never on carts, bags, cups, dumbbells, gym equipment, shelves, walls, clothing or signs. Every other object is plain and unbranded. WORLD: authentic phone-shot UGC day-in-the-life reel, 9:16, natural daylight and real store light, handheld smartphone look with natural shake, real skin texture. Four places: a bright home hallway, a grocery store aisle, a café pickup counter, a gym floor with dumbbell racks. @image2 wears the same outfit in every shot. In the grocery aisle, the café and the gym, two or three other people are far in the background, out of focus, facing away, never looking at the camera and never interacting with @image2. ACTING: high-energy, genuine creator delivery — quick grins, eyebrows up, animated hands, lively pace, natural laughs; real enthusiasm, never cartoonish. CAMERA: hard cuts between shots, each cut landing on a beat of the music; allowed verbs: crash zoom, push-in, whip pan, speed ramp. No on-screen text, captions or subtitles, no store signage text. SPEECH: @image2 says ONLY the lines written below, word for word, with a short breath between lines. The café staff says only "Order up!". No other words, no ad-libs, no filler. TIMELINE (20 s): 0–3s: HOME HALLWAY. @image2 steps into frame from the right edge and pushes the product toward the lens in the right hand, with a big grin and raised eyebrows; crash zoom on the product. @image2, own voice, excited, to camera: "This solved a problem I didn't even know I had!" 3–5s: HOME HALLWAY, close-up. @image2 puts the product into use in one quick continuous motion, ending exactly as in @image1; @image2 lets out one short laugh. @image2, own voice: "Every part of my day needed something different." 5–8s: GROCERY AISLE, low candid angle from the front of a shopping cart. Product in use as in @image1. @image2's left hand takes one plain snack bag off the shelf, holds it over the open cart and lets go; it falls straight down into the basket and stays there; @image2 glances at the lens and grins. @image2, own voice: "Errands? Got it." 8–11s: CAFÉ PICKUP COUNTER. Product in use as in @image1. An iced coffee cup already stands on the counter. Off-screen café staff voice, first: "Order up!" Then @image2's left hand grabs the cup and @image2 takes one sip through the straw while turning toward the camera. @image2, own voice, grinning: "Coffee run? Got it." 11–14s: GYM FLOOR, @image2 standing upright beside the dumbbell rack. Product in use as in @image1. @image2 does exactly three standing dumbbell curls with the right arm using a plain black hex dumbbell with no text, letters or markings, breathing hard, eyes on the lens; speed ramp on the third curl. @image2, own voice, slightly out of breath: "Gym? Still got it." 14–17s: GYM FLOOR, same spot, standing. @image2's right hand sets the dumbbell back on the rack; the right index finger points at the product where it is in use; @image2 laughs. @image2, own voice: "One for everything." 17–20s: HOME HALLWAY. Close-up: @image2 leans one shoulder against the wall, product in use as in @image1, and winks once at the lens; push-in; holds on @image2 and the product until the end. @image2, own voice, playful: "Thank me later." QUALITY: anatomically correct — two arms, two hands, five fingers per hand, no extra or detached limbs; natural movement and believable physics; objects move only when a hand moves them; same face and same product in every shot; realistic smartphone footage, not glossy commercial. SOUND: 0:00–0:05 only @image2's voice and light hallway room tone, no music. At 0:05, the instant the product is in use, an upbeat feel-good indie-pop / house track kicks in at about 120 BPM — bright synths, punchy kick, handclaps — mixed low under @image2's voice, every line fully clear. The beat hits on every hard cut and whip pan, lifts slightly in the gym, and resolves with a soft final chord under "Thank me later." Natural store, café and gym ambience underneath.
REFERENCES: @image1 is the person. @image2 is the CASE — the brand's glasses case. Every reference image after @image2 is a pair of the eyewear being advertised. PAIR A is the FIRST eyewear reference (@image3). PAIR B is the LAST eyewear reference. PAIR C is any eyewear reference between them. When only one eyewear reference is attached, PAIR A and PAIR B are that same single pair. CHARACTER LOCK — HIGHEST PRIORITY: @image1 is the person, exactly as shown. Preserve 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, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. The only eyewear @image1 ever wears is the advertised eyewear — never any other glasses. The person is @image1 — no pronouns, no description. PRODUCT LOCK: every pair keeps its exact frame shape, colour, finish, lens tint, bridge, temples and proportions from its own reference image in every shot; never redesign, never swap one pair's details onto another, never invent logos or text, never duplicate a pair. The CASE keeps its exact shape, colour and lettering from @image2, and it stays CLOSED for the whole film — it is never opened. Ignore the white backgrounds of all product images. Only one pair is ever on @image1's face; a pair not being worn rests on a surface or in the hand. TEXT AND LOGOS: no on-screen text, captions or subtitles. Lettering appears only on the eyewear and the CASE as in their references — never on clothing, signs, shop windows, records, cups or walls; storefronts and posters are plain colour blocks. Any lettering that appears reads correctly; the footage is not mirrored. WARDROBE: @image1 wears the same outfit in every shot — a simple casual everyday outfit in colours that suit @image1. Plain fabrics, no logos. WORLD: an energetic, colourful phone-shot UGC reel, 9:16, fast hard cuts every 1.5–2 seconds, each shot starting mid-movement. Four lively places: a sunny city street with colourful storefronts; a café with green tiled walls and warm lamps; a vintage record shop with colourful shelves; a rooftop at golden hour with a city view. Other people only far in the background, strongly out of focus, never interacting with @image1. Handheld, natural light, real skin texture. ACTING: high-energy, confident, playful creator — walking toward the lens, quick head turns, raised eyebrows, a wink, laughs, talking fast with attitude; never cartoonish. MOTION: real-time natural speed, no slow motion; objects move only when a hand moves them; glasses go on and off by the temples, the natural way. TIMELINE (20 s): 0–1.5s: STREET. @image1 strides toward the lens and pushes PAIR A onto the face mid-step. On camera: "Okay, glasses people —" 1.5–3s: STREET. Crash zoom on @image1's face wearing PAIR A, one eyebrow up. On camera: "— you need to see this." 3–4.5s: CAFÉ, green tiles. @image1 drops into a seat; the closed CASE lies on the table; @image1 takes PAIR A off and turns it in the fingers, amazed. On camera: "These are crazy light." 4.5–6s: CAFÉ, macro. A fingertip slides along PAIR A's temple to the hinge. Voiceover, same voice: "Like, I forget they're on." 6–7.5s: RECORD SHOP. @image1, wearing PAIR A, walks between colourful shelves and snaps the head round to the lens. Voiceover: "And the details?" 7.5–9s: RECORD SHOP, close-up. @image1 taps the frame of PAIR A and grins. On camera: "Unreal." 9–10.5s: STREET, bright sun. @image1 pulls PAIR A off with one hand and slides PAIR B on with the other in one quick motion. On camera: "Then the sun comes out…" 10.5–12s: STREET, sun. @image1 lowers PAIR B down the nose with one finger and winks at the lens. On camera: "…and I switch." 12–14s: ROOFTOP, golden hour. Side profile of @image1 wearing PAIR B, wind in the hair, a laugh. Voiceover: "Zero effort." 14–16s: ROOFTOP. On the ledge, every advertised pair rests in a neat row beside the closed CASE; @image1's hand picks one pair up. Voiceover: "Whatever the day throws at me." 16–18s: STREET. @image1, wearing PAIR A, walks toward the lens pointing at the glasses. On camera: "Honestly?" 18–20s: Close-up, @image1 wearing PAIR A, confident grin into the lens; holds until the end. On camera: "Time to upgrade." SPEECH: @image1 says ONLY the lines written above, word for word, fast and lively. No other words, no ad-libs, no brand names. SOUND: @image1's energetic voice close to the phone mic, every word fully clear; street, café and rooftop ambience. QUALITY: anatomically correct — two arms, two hands, five fingers per hand, no extra or detached limbs; natural movement and believable physics; the same face, hair and outfit in every shot; every pair and the CASE exactly as in their references; realistic smartphone footage, not glossy commercial.
REFERENCES: @image1 is the person. @image2 is PRODUCT 1. @image3 is PRODUCT 2. @image4 is PRODUCT 3. CHARACTER LOCK — HIGHEST PRIORITY: @image1 is the person, exactly as shown. Preserve 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, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. No other people in frame. The person is @image1 — no pronouns, no description. PRODUCT LOCK: PRODUCT 1, PRODUCT 2 and PRODUCT 3 each keep their exact shape, colour, finish, proportions, label and markings from their own reference image in every shot; never redesign, never swap one for another, never invent text or logos, never duplicate. Ignore the backgrounds of the product images — only the products carry over. Only ONE product is in @image1's hands at a time; the others stand on the tray. After using a product, @image1 sets it back on the tray. TEXT AND LOGOS: no on-screen text, captions, subtitles, circles or picture-in-picture insets. Lettering appears only on the products' own labels — never on the tray, towel, walls, furniture or clothing. WORLD: an aesthetic golden-hour morning skincare routine filmed on a phone, 9:16. Warm low sunlight through a sheer curtain, soft leaf shadows on a beige wall, a wooden vanity table; on it, a round white marble tray with a thin gold rim holding the three products, a few dried flowers beside it. A small balcony with a city view. Real skin texture, handheld with gentle natural movement. Hard cuts on the music's beats. MOTION: everything moves at real-time natural speed — no slow motion. Hands move lightly and quickly like a real person doing a familiar routine: quick light fingertip taps, short smooth strokes. Each product comes out of its own packaging the way that packaging really works — poured, dropped, pumped or squeezed — and the product visibly lands on the palm or fingertips. EXPRESSIONS: influencer-style, playful and confident facial expressions with the mouth closed or smiling — never talking to the camera. TIMELINE (25 s): 0–3s: BALCONY, low sun. The film opens mid-motion: on frame one @image1 is already pulling a white towel off the head, the hair coming free in the sunlight, exactly as in @image1; @image1 tips the face up into the sun, then looks straight into the lens and winks once, landing on a beat. 3–5.5s: VANITY, white towel turban on the head. @image1 walks into frame from the left toward the vanity and stops in front of the marble tray; eyes light up at the products with raised eyebrows and an excited closed-mouth smile; the right hand picks up PRODUCT 1. 5.5–7s: Close-up: @image1 holds PRODUCT 1 beside the face toward the lens, label to camera, one eyebrow raised in a playful half-smile. 7–7.7s: Full-screen macro: PRODUCT 1 coming out of its own packaging onto the palm or fingertips, glistening in the sun. 7.7–11s: @image1 applies PRODUCT 1 with quick light pats over cheeks and forehead, eyes closed, a content smile and a small head tilt; then sets it back on the tray. 11–12.5s: Close-up: @image1 holds PRODUCT 2 toward the lens, label to camera, with a delighted "wow" face — eyes wide, lips parted in a smile — then a satisfied nod. 12.5–13.2s: Full-screen macro: PRODUCT 2 coming out of its own packaging onto the fingertips, glistening. 13.2–16.5s: @image1 taps PRODUCT 2 into the skin with the fingertips, quick and light, eyes half-closed, pleased smile; then sets it back on the tray. 16.5–18s: Close-up: @image1 holds PRODUCT 3 beside the face toward the lens, label to camera, blows a small kiss-pout toward the lens and winks. 18–18.7s: Full-screen macro: PRODUCT 3 coming out of its own packaging onto the fingertips, glistening. 18.7–21s: @image1 smooths PRODUCT 3 across the cheek in short strokes, side-lit by the sun, satisfied smile. 21–25s: RESULT, back on the balcony in the low sun, no towel, hair exactly as in @image1: close-up of @image1's glowing skin; @image1 lightly touches the jaw with the fingertips, gives the lens a confident, knowing look and a soft smile; slow push-in; holds on this until the end. VOICEOVER — @image1's own warm, intimate voice heard off-camera; @image1's lips never mouth the words. Say ONLY these lines, word for word, no other words: 0:00: "Watch what five minutes of golden hour does to my skin…" 0:07: "Step one — this. Quick, gentle, done." 0:13: "Then this one… press it in." 0:18.5: "And this, to lock it all in." 0:22: "No filter. Just this light… and that glow." SOUND: from the very first frame, a warm, catchy dreamy pop / R&B track at about 100 BPM — soft synth chords, finger snaps, a groovy bassline and a crisp beat — clearly audible throughout the whole film, dipping only slightly under each voiceover line and coming straight back up between lines. A beat hit lands on the wink at 0:03 and on each product reveal; the track opens up on the balcony at the end and resolves on a warm final chord. Every voiceover word stays fully clear. Light room tone underneath. QUALITY: anatomically correct — two arms, two hands, five fingers per hand, no extra or detached limbs; natural movement and believable physics; objects move only when a hand moves them; the same face in every shot; each product exactly as in its reference; realistic smartphone footage, not glossy commercial.
16:9 30 seconds. Seedance 2.5. Cinematic live-action action-comedy, 24 fps, dynamic handheld. Photoreal. RIGHT-SIDE UP from frame 0. NEVER a studio still as frame 0. No on-screen captions. No spoken brand names. CHARACTER LOCK: the person is exactly @image1. Preserve face, hair, skin, age, build, gender presentation, AND the outfit in the photo — do not change their clothes. Use they / their / them only. @image1 = THIS person. Photocopy face and the clothes they are wearing. Do not describe or replace the outfit. @image2 = THIS drink. Photocopy it. NEVER a different bottle. They drink from @image2. Zombies are extras, not extra heroes. They attack because they want the drink. SET: a long hallway just off a loud party (muffled bass behind a door). Dim party spill. A bench or side table where they set @image2. AUDIO: fight impacts, zombie groans, muffled bass. They SPEAK only the last line, clearly, in English: “Everyone wants a sip.” 0:00–0:00.5 CU: they calmly sip @image2, zombies in the blurry hallway behind. 0:00.5–0:02 A zombie lunges from behind. They spin away. 0:02–0:05 They set @image2 on the bench. Several zombies rush; dodge, block, counter; a kick at 0:04. 0:05–0:07 Camera pulls back. They push and strike; one zombie hits the floor. 0:07–0:08.5 They kick a zombie in the chest — bright blue electric flash and sparks. Wide stance. 0:09–0:13 Fast fight beside the bench with @image2. Shove, spin, strike. ~0:12 dust/smoke; a zombie thrown backward. 0:13.5–0:18 Wide hallway, many zombies down. They run; two lunge from both sides; high kick. 0:18–0:22.5 Knees, kicks, punches, blocks; zombies crawl. Handheld closer. 0:22.5–0:26 Spin, high kick through smoke; last attackers collapse. Calm, they walk to the bench and pick up @image2. 0:27–0:30 Front-facing medium: they RAISE @image2 toward camera and say, clearly, “Everyone wants a sip.” Bodies in the hallway behind. Deadpan. Hold. Same person as @image1. Same drink as @image2. Clothes from @image1.
VERTICAL 9:16 15 seconds. Seedance 2.5. CINEMATIC luxury-product commercial. Douyin-style transformation. The RESULT is from @image2. Photoreal. Dramatic lighting, high-end framing. Immersive whoosh, flash, wind, score. No on-screen captions. No spoken brand names. RIGHT-SIDE UP from frame 0. NEVER a studio still as frame 0. 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. Looks: (a) BEFORE — bare face, messy hair, oversized T-shirt, sleepy, casual room. (b) AFTER — same person, glamorous, styled, elegant fashion, black studio. The after-look is the result of @image2. @image2 = THIS product. Photocopy it. NEVER a different product. They present @image2 to camera before the swipe. After the cut, @image2 is the hero still-life. One person only as hero. 0.00–3.50 BEFORE. Bare face, messy hair, oversized tee, sleepy, casual room. @image2 on the vanity — they hold it up to camera. Slow push-in. They become confident and FAST sideways palm-swipe the lens. Whip-pan with their hand; palm covers the frame. 3.50 HARD CUT + WHITE FLASH + WHOOSH + SHAKE. Instant hidden transformation. No morph. SNAP ZOOM. 3.50–7.00 AFTER. Black studio. Same person as @image1, glamorous. Fast head turn, intense eye contact. @image2 sharp in the foreground. 7.00–15.00 EDITORIAL. Rapid FLASH → HARD CUT → NEW POSE. Hair sweep (SLOW-MO). 3/4 turn. Hand near jaw. Low-angle. @image2 inserts between poses. Final hero: them + @image2. Huge white photography flash + brief freeze. Same person as @image1. Same product as @image2.
REFERENCES: @image1 is the person. @image2 is the PRODUCT — a single-serve packet of drink mix powder. @image3 is the PACK — the box the packets come in. CHARACTER LOCK — HIGHEST PRIORITY: @image1 is the person, exactly as shown. Preserve 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, body proportions and gender presentation exactly as shown. Do not beautify, slim, de-age or restyle. @image1 is the only person in focus; no other person is ever in the foreground and nobody interacts with @image1. The person is @image1 — no pronouns, no description. PRODUCT LOCK: the PRODUCT and the PACK keep their exact shape, colour, finish, proportions, labels and markings from @image2 and @image3 in every shot; never redesign them, never invent text or logos, never duplicate the PACK. Ignore the backgrounds of the reference images. The footage is NOT mirrored; all lettering reads correctly. TEXT AND LOGOS: no on-screen text, captions or subtitles. Lettering appears only on the PRODUCT and the PACK — never on glasses, gym equipment, walls, laptops or clothing. All clothing is plain, with no logos, prints or text. WARDROBE: at the table @image1 wears plain, comfortable at-home clothes in colours that suit @image1; in the gym and boxing shots plain training clothes. FORMAT: an authentic phone-shot UGC testimonial, 9:16. A-ROLL: @image1 seated at a wooden table in a warm, dim home kitchen at night, a tall clear glass of ice water on the table, talking straight to the camera with matching lip-sync. B-ROLL: full-screen clips; during B-ROLL the same voice continues as a voiceover and @image1's lips do not mouth the words. Fast hard cuts. ACTING: relatable, animated creator energy — expressive eyebrows, hand gestures, a knowing smile, talking fast and naturally; never cartoonish. MOTION: real-time natural speed, no slow motion; objects move only when a hand moves them; powder pours and dissolves believably. TIMELINE (20 s): 0–3s: A-ROLL. On frame one @image1 lifts the glass of ice water toward the lens, eyebrows raised, mid-sentence. On camera: "Drinking a ton of water and STILL feeling drained?" 3–5s: B-ROLL, a gym with machines, other gym-goers far in the background, strongly out of focus and facing away. @image1 pushes the leg press platform away twice, legs extending, then drops the head back, exhausted. Voiceover: "Yeah… that was me." 5–8s: A-ROLL. @image1 leans in and points at the lens. On camera: "Turns out I wasn't missing water — I was missing this." 8–10s: A-ROLL. @image1 lifts the PACK up beside the face with both hands, front of the PACK to the lens, and grins. 10–13s: B-ROLL, close-up on the table. @image1's hands tear the top off one PRODUCT packet and pour the powder into the glass of ice water; the water turns colour; a spoon stirs it once. Voiceover: "One packet. No junk." 13–15s: A-ROLL. @image1 takes a big sip from the glass, eyes widen, nods. On camera: "And honestly? It tastes SO good." 15–16.5s: B-ROLL, gym. @image1 pushes a chest press machine with ease, focused. Voiceover: "Now I feel locked in —" 16.5–18s: B-ROLL, a small boxing gym. @image1 throws two quick punches into a hanging heavy bag. Voiceover: "all day." 18–20s: A-ROLL. @image1 holds the glass up beside the face with one hand and points at the lens with the other, confident smile; holds on @image1 and the glass until the end. On camera: "Try it — thank me later." SPEECH: @image1 says ONLY the lines written above, word for word. No other words, no ad-libs, no filler, no brand names. SOUND: @image1's natural voice close to the phone mic, every word fully clear; light kitchen room tone; gym clatter and a punching-bag thud in the B-ROLL. QUALITY: anatomically correct — two arms, two hands, five fingers per hand, no extra or detached limbs; natural movement and believable physics; the same face and hair in every shot; the PRODUCT and PACK exactly as in their references; realistic smartphone footage, not glossy commercial.
A 20-second UGC "one product for every mood" ad: @image1 (you) shows @image2 (your product) on a cozy day at home, getting ready for a night out, on errands and at the gym — talking to the camera in every shot, quick cuts, outfit change per mood. TIMELINE (20 s): 0–2s: @image1 bursts into frame and thrusts @image2 at the lens for the hook. 2–5s: cozy day: curled in the armchair under a knit blanket, @image1 holds @image2 beside the face. 5–9s: night out: at the bathroom mirror in an evening outfit, @image1 uses @image2 once. 9–12s: errands: @image1 drops @image2 into a tote bag and slings it over the shoulder. 12–16s: gym: @image2 stands on the yoga mat while @image1 does three quick squats. 16–20s: close-up: @image1 holds @image2 beside the face and asks the viewer which mood they are in, holding to the last frame. Upload your face and your product.
A 15-second luxury perfume film built from @image1 (your bottle) and your notes (@image2 onward): each note gets its own macro shot, top notes first, the heart in the middle, the base at the end, then your bottle as the hero. Instrumental sound, no voice. Upload your perfume and its notes.