NewOpenClips MCP is live.Your AI video studio, inside any AI chat.See how it works →
Back to the gallery
Pricing
Back to the gallery
Paused
0:00/0:00
MiniMax H315s · 9:16
Up next
Inspired by ZetoGroovinon X

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, 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 reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. The person in every shot is exactly the person in @image1 — face, bone structure, skin, blonde hair, age, body. The photo is identity only, not wardrobe. Do not keep the ivory blazer, camel skirt, boots or bag from the photo. Do not give them black hair. WARDROBE (from the source film): butter-yellow cropped t-shirt with a silver rhinestone star, black neck trim, beaded fringe at the hem; distressed blue denim shorts; thin black belt; layered silver necklaces; white crew socks with stripes; chunky silver-white sneakers. Same outfit for the full 15 seconds. SETTING: charcoal-grey seamless studio, dry floor with a faint reflection. No furniture, no crowd, no props. Soft white key from front-left, pale blue-violet rim from behind. One person only. No on-screen text. MUSIC: 128 BPM four-on-the-floor k-pop dance track already in the chorus. Heavy kick, bouncing bass, sharp claps. No intro, no fade-out, no ending hit. The clip is a mid-routine slice — they are already dancing in frame 1 and still moving in the last frame. CHOREOGRAPHY — one continuous 15s routine in four phrases. Never freeze. Never a start pose or a finish pose. Phrase 1 (0–3.75s): already weighting the left leg as arms return to the chest. Step hard right, uncross the arms out and open the chest. Weight back left, arms circle down. Two small forward steps, a sharp chest hit on the clap. Open the right foot, drop the knees, arms to the hips into a hip figure-eight. Phrase 2 (3.75–7.5s): low hip figure-eight, weight right-left-centre. Wave up from pelvis through belly to chest. Uncoil the arms as the right foot crosses in front, glance at the lens with a brief smile without stopping. Phrase 3 (7.5–11.25s): smooth stepping turn, hair lagging the spin. Land into a right side lunge, left arm high, long diagonal. Push back to centre, wave down the torso. Phrase 4 (11.25–15s): two strong hip accents. Two quick steps to centre, load the arms. Open the right foot wide, big arm unfold — not a finish, a send-off. Circle the arms down, take weight on the left, right foot already starting the next cross-step. Last frame still travelling. CAMERA (cut on the body, never reset the step): 0–3.75s full body, slight three-quarter, short lateral slide. 3.75–5.625s waist-up, hip figure-eight, locked frame. 5.625–7.5s face and shoulders, 85mm, the wave hitting the collarbone. 7.5–11.25s full body for the turn and lunge. 11.25–13.125s head to mid-thigh. 13.125–15s full body, short lateral move, no zoom-in to end. Photoreal skin, light sweat, motion blur on hair and hands. No slow-mo, no logos, no extra limbs.

2 steps34013.6K
Seedance 2.515s · 9:16
Inspired by @VeraVCreateson X

30 seconds, 16:9, a handheld home-video travel vlog filmed by @image_1 on a snowy Amsterdam canal. ATTACHED IMAGES ARE MANDATORY AND FINAL: the person in @image_1 is the protagonist — reproduce them exactly in every frame and never invent a different face, hair, skin tone, body or age. Preserve their facial identity, hairline, hairstyle, skin tone, apparent age and build, and their gender presentation exactly as shown. Gender, face and hair come from @image_1 and not from this text. The speaking voice belongs to @image_1. @image_1 wears a cream-white puffer jacket, a light grey knitted scarf, dark trousers, dark gloves and winter boots — the same outfit throughout. Fit the garments to their body without changing the design or colour. Winter in Amsterdam: narrow brick canal houses with stepped gables, warm lit windows, an arched bridge strung with small lights, bicycles under fresh snow, houseboats on the water. Fine snow falls the whole time and the light moves from overcast day to blue hour. Every shot is filmed at arm's length by @image_1 on a small old camcorder — slight shake, autofocus hunting, exposure lag, tape noise, snowflakes on the lens. The arc across twelve short beats: @image_1 records calmly, catches the snowy canal out of the corner of their eye and can't quite believe it, reveals the canal, watches snow melt on their palm, walks the white quay, gets startled by snow sliding off a gable, spots a grey heron standing across the water and drops to a whisper, then ends at the railing in blue hour looking back at the lens. Short spoken lines in English, low and close to the microphone: "No way." / "Hold on. Look at this." / "I had no idea it snowed like this here." / "This is unreal." / "Wait. Is that a heron?" / "I'm so glad I came." / "I still can't believe it." / "I want to come back." The first frame is already lit and in motion; no fade in from black, no intro card. Do not add subtitles. No on-screen text. No BGM; generate only environmental sounds and the spoken lines.

2 steps42957
Seedance 2.530s · 16:9
Inspired by ivanka_humeniukon X

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, 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 reinterpret it. Do not beautify, slim, de-age or restyle them. The attached image outranks every word below it: wherever the image and the text disagree, follow the image. Frame 1 is already in the scene — never a studio portrait, grey backdrop, or the attached still as an opening plate. Use they/them throughout. No other people. The person in every shot is exactly the person in @image1 — face, bone structure, skin, blonde hair, age, body. The photo is identity only, not wardrobe. Do not keep the ivory blazer, white shirt, camel skirt or bunny bag from the photo. Start look (shots 1–5): white cropped tank and short white fitted shorts. Barefoot until the final reveal. Final outfit (from the source film, not the photo): oversized moss-olive mohair sweater with balloon sleeves; olive satin mini skirt with a floral lace hem; dark chocolate knee-high slouch leather boots; dark brown leather belt with a gold buckle, front of the sweater tucked into the belt; structured dark chocolate-brown leather tote; warm gold collar necklace, hoop earrings, ring and bangle. SETTING: cream Paris hallway, gold rococo mirror, two wall sconces, marble console, open shopping boxes on the floor. Warm lamp light. No other people. No on-screen text. No bottom reference panels, no collage, no character sheet, no flat-lay. CAMERA: one locked tripod in the doorway, frontal, eye level. Hard cuts on the beat. 9:16, 20 seconds. Frame 1 is already in the hallway — never a studio portrait plate. SHOT 1 (0–1.7s) They hold the olive satin lace mini skirt by the waistband against their waist, lift it once so the satin sways, look into the lens and smile. SHOT 2 (1.7–3.4s) Same camera. They hold the moss-olive sweater against their torso by both shoulder seams, bounce it once, glance down, then smile at the lens. SHOT 3 (3.4–5.0s) They hold the brown leather belt horizontally, gold buckle centred close to the lens, eyes visible above it, a small smile. SHOT 4 (5.0–5.8s) They flip their blonde hair over one shoulder and grin at the lens. SHOT 5 (5.8–7.5s) They hold the chocolate-brown tote in front of their chest; face visible between the handles; head tilt and smile. SHOT 6 (7.5–10.2s) Sweater already above their head. One uncut action: they pull it down, arms through the balloon sleeves, hem settles at the hips, hair falls back. Eyes find the lens. Smile. SHOT 7 (10.2–11.7s) Wearing the sweater, they spray perfume beside their neck once, eyes close, then look back at the viewer. SHOT 8 (11.7–14.0s) Wider. They already wear the olive lace mini under the sweater. They adjust the high waistband once, shift onto one hip, pleased smile. SHOT 9 (14.0–15.7s) Closer. Gold jewellery already on. They close one gold hoop earring with both hands, check it in the lens, playful smile. SHOT 10 (15.7–20.0s) Full length, hair to boot soles. Complete outfit, tote in the left hand. Hold, small bounce, turn through a side view to a back three-quarter, then look over the shoulder at the lens and hold the smile to 20s. AUDIO: one upbeat instrumental fashion track. Cuts on the beat. Fabric, one spray, jewellery click, boots, tote.

2 steps13532
Seedance 2.520s · 9:16
Taken by the Light

FOUR SHOTS. VERTICAL. ONE PERSON ONLY. ULTRA-REALISTIC CINEMATIC SCI-FI. ASSET MAP - every reference is bound here and cited by tag below: @avatar - the person. This is who is on camera; face, hair, skin and body come entirely from @avatar and never from this text. CHARACTER LOCK - HIGHEST PRIORITY: the person in every shot 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 from the first frame to the last. 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, and no other people anywhere in frame. ATTACHED IMAGES ARE MANDATORY AND FINAL: if a reference is attached, that is the person - reproduce them exactly, in every frame, and never invent a different face, hairline, hair colour, skin tone, body or age. The attached reference outranks every word written below it. WARDROBE (from this text, never from @avatar): a pale floor-length robe of lightweight loosely woven fabric - long sleeves, an open front, a soft sash tied at the waist, and a long hem that trails on the ground, worn over matching loose full-length trousers in the same pale fabric. This is a unisex ceremonial robe, cut identically for any body: no logos, no lettering, no visible branding. The collar and shoulders of this robe are visible in every single shot, including the closest one - never a t-shirt, never a plain top, never bare shoulders. The reference shows their face and build, not this outfit - fit it to their body naturally without altering its cut, length, proportions or colour. The robe never changes the person: their hair length, hairstyle and gender presentation stay exactly as in @avatar. WORLD: an enormous, almost silent futuristic city at night. Glass towers climb out of frame, their windows glowing, thin neon lines running up their edges. The street is wet from recent rain and mirrors every light. Light mist and soft atmospheric fog. Above the rooftops there is no sky at all - the gap between the towers opens straight into the heart of a galaxy: dense drifting starfields and vast clouds of coloured nebula, close enough that they visibly move. Living inside that galaxy, an enormous creature glides slowly above the city like a whale through water. It has a solid rounded body with real volume - visible skin texture lit from within, soft shadow along its underside and flanks, slow rippling fins and a wide tail that flexes as it moves. It is a living animal made of light, not a flat glowing outline and not a drawing. Shot 1: a tracking shot from behind at walking height. The person walks slowly away down the middle of the wet street in the long pale robe, its hem trailing behind them, their steps sending small rings across the shallow water. Far above and ahead, the enormous creature slides across the gap between the towers. They slow to a stop and begin to tilt their head back. Shot 2: cut to a close shot of the person from the front, framed from the chest up so the collar and shoulders of the pale robe are clearly in frame. Their face is clearly lit and readable, head tilted back, looking up in silent amazement, eyes wide, lips slightly parted. Nebula light in soft blues and warm pinks moves across their face. Shot 3: cut wider. The enormous creature descends into the canyon between the towers until its body fills the whole gap directly above the person, so close its lit underside washes the whole street. The person stands small and alone in the middle of the wet road, head back, arms loose at their sides, the long hem beginning to lift around their ankles. Shot 4: THIS IS THE FINAL SHOT AND THE LONGEST SHOT OF THE FILM - it runs to the very end and the film closes on it. Cut to a low angle close on the person. The light closes around them and they rise: their feet lift cleanly off the wet street, the long hem and sleeves and their hair all stream downward as they climb, and water lifts off the road beneath them in slow threads. Their face stays turned upward, calm and amazed rather than frightened, clearly lit and clearly the same person. The camera stays with them and tilts up as they go, holding them in frame the whole way while the street falls away below and the creature's lit body grows above them, until they rise out of the top of the frame into the light. Stay on the person for this entire shot and end the film here. AUDIO: the deep quiet room tone of an empty city, faint water dripping and running, a low distant hum, one long low resonant call from the creature, and a soft rising swell of air as the person leaves the ground. Only one person exists in this entire video. No music, no narration, no dialogue and no voices. Do not generate subtitles, captions, on-screen text, a timestamp, a recording indicator, an interface overlay, a logo or a watermark. No second person, no crowd, no readable signage, no spacecraft, no tentacles, no grabbing or gripping of the body, no creature with a face or limbs, no final wide city shot without the person in it, and nothing that reads as a map or as lettering.

2 steps947.7K
Seedance 2.015s · 1:1
Farm to GlassMiniMax H3 · 9:16 · 15sRecreate workflow