Skip to main content

Portraits & People Prompts

Close-up beauty and portrait prompts: subtle blinks, breathing and hair in the wind, with skin that holds up under a macro lens.

WAN 3.090
Read the full prompt — Locker Room Gear Check@Video1 controls motion, camera, framing, timing, the room and sound; keep all of it exactly: the handheld selfie camera on an outstretched arm with a wide lens from slightly below, the hero talks to the lens in a close selfie, his partner leans in over his shoulder, the hero turns to the partner and back with a smile, then shows his gear to the lens one item after another exactly as in @Video1 - pistol with a mounted flashlight, the flashlight shining straight into the lens as a blinding white flash with a turquoise glint, knife, handcuffs raised in both hands, two magazines, a small flashlight - with the same fast whip-pan blur transitions between items. The same locker room with dark metal lockers and stickers, the same lighting and color. @Image1 controls the two people: the man holding the camera becomes the person on the left of @Image1, the partner who leans in becomes the person on the right of @Image1, with the same faces, hair, build and clothes. No trace of the original people. From @Video1 take the motion, camera, room and props; take none of its people. Five fingers on each hand, hands grip each item naturally. Photorealistic, natural phone footage, one continuous shot with the same transitions as @Video1, no subtitles, no text, no watermark.
LTX 2.360
Read the full prompt — Paper Airplane ClassroomA stylized 3D animated character: a schoolgirl of about nine with a short dark bob and big expressive brown eyes, in a navy blazer, pleated navy skirt and white collared shirt, sits at a light-wood desk in a bright classroom. She raises a white paper airplane in her right hand, grins, and with one smooth throw sends it gliding forward across the room, her eyes following it. Lemon-yellow curtains frame a tall window on the left, a lemon-yellow backpack hangs on her chair, the floor is pale wood. Strong midday sun pours through the window and casts soft warm light on her face and the desk, with gentle violet-blue shadows, soft materials like in a 3D animated film. Medium shot from slightly front-side, the camera stays still, the whole girl and the desk in focus. Smooth simple shapes, clean surfaces, no other students, no text, no logos, no watermark.
WAN 3.080
Read the full prompt — Dracula Hand Dance@Video1 controls motion, camera, framing, timing, and sound; keep all of it exactly: the static waist-up shot and the whole hand and finger routine on the beat - crossed fists at the chest, a triangle made with the fingertips, palms crossed flat on the chest, fingers interlaced into a pyramid, fingers flicking and parting, then palms rolling over each other in front of the chest. Both hands stay in frame the whole time, five fingers on each hand, short nails, no claws. @Image1 controls the identity of the performer: replace him in every frame with the person from @Image1, including face, hair, build, outfit, and any special features such as eye colour or fangs, which stay visible in every frame. Calm deadpan face looking straight into the lens, no smile. No trace of the original. If @Image2 is provided, it controls the location: replace the environment and the crowd behind him to fit that place, with everyone dressed to match it. If @Image2 is not provided, keep the original environment. From @Video1 take only the motion and the camera; take none of its people, clothes, props or walls. One continuous shot, no cuts, no subtitles, no text.
WAN 3.070
Read the full prompt — Dracula Wife Hand Dance@Video1 controls motion, camera, framing, timing, and sound; keep all of it exactly: the static waist-up shot and the whole hand and finger routine on the beat - crossed fists at the chest, a triangle made with the fingertips, palms crossed flat on the chest, fingers interlaced into a pyramid, fingers flicking and parting, then palms rolling over each other in front of the chest. Both hands stay in frame the whole time, five fingers on each hand, short nails, no claws. @Image1 controls the identity of the performer: replace him in every frame with the person from @Image1, including face, hair, build, outfit, and any special features such as eye colour or fangs, which stay visible in every frame. Calm deadpan face looking straight into the lens, no smile. No trace of the original. If @Image2 is provided, it controls the location: replace the environment and the crowd behind him to fit that place, with everyone dressed to match it. If @Image2 is not provided, keep the original environment. From @Video1 take only the motion and the camera; take none of its people, clothes, props or walls. One continuous shot, no cuts, no subtitles, no text.
MiniMax H3 Turbo30
Read the full prompt — Grandmother And Baby SweaterA woman in her seventies with dark brown skin, short silver hair and a grey-blue knit shawl sits sideways to the camera beside a window in a dim room, holding a small hand-knitted faded-yellow baby sweater in both hands. She slowly lifts it to her cheek, a smile breaks across her face and a single tear runs down, her eyes wet and shining. The walls are blue-grey plaster and the armchair is worn brown leather. The only light is a weak overcast daylight from the window, tracing her cheek and hands in warm tones while the rest of the room falls into deep shadow. Medium shot from the side, the camera slowly pushes in toward her face. Natural skin texture, fine wool stitches, quiet and real. No text, no logos, no watermark.
Seedance 2.560
Read the full prompt — Agent and Alien Gear Check@Video1 is the exact template for camera, framing, every movement and its timing, the locker room set, lighting, sound and the props in order - follow @Video1 strictly. @Image1 is the main hero who holds the camera: appearance only, never its background. @Image2 is the partner who peeks in over his shoulder: appearance only, never its background. Keep every special feature of both, such as skin colour, eye shape and number of fingers, visible in every frame. Photorealistic live-action footage, real skin texture, natural locker-room light, real metal and fabric, hands grip each prop naturally. Handheld selfie camera on an outstretched arm, wide lens from slightly below, dark metal lockers with stickers behind. [0-1 s] the hero talks to the camera in a close selfie. [1-2 s] the partner peeks in over the hero's left shoulder. [2-4 s] the hero turns to the partner for a quick friendly moment and turns back to the camera smiling. [4-5 s] a sleek retro-futuristic silver-and-black blaster pistol held up to the camera and turned sideways. [5-6 s] the hero points a slim silver pen-shaped device at the lens and clicks it: a blinding white flash with a turquoise glint fills the whole frame, then fades back to the hero. [6-7 s] a folding knife held to the camera. [7-8 s] handcuffs raised in both hands. [8-9 s] two pistol magazines held to the camera. [9-10 s] a small black flashlight held to the camera. [10-11 s] hands reach to the camera and the shot whips away with motion blur. The hero ends standing in the locker room, frame settled. Only the people and the named props change; everything else stays as in @Video1. Avoid: subtitles, captions, any text, logos, watermark, extra people, extra fingers, studio grey background, cuts that are not in @Video1.
LTX 2.340
Read the full prompt — Empty Stadium Red ScarfA lone man sits on the top concrete step of an empty stadium, seen from behind in a wide shot. He is in his thirties, with short natural black hair, broad shoulders in a charcoal wool coat, a red knitted scarf around his neck, hands resting on his knees. Below him rows of empty steel-grey seats curve down to a pale green pitch. The only movement is the end of the red scarf lifting and settling in a light wind. Early morning, cold diffused light from an overcast sky, no sun, soft shadows. Palette: steel-grey seats and sky, a red scarf, pale concrete steps. The camera stays still at a low angle behind and slightly below him, the whole stadium in focus. Matte concrete, painted metal seats, no other people, no birds. No text, no logos, no watermark, no signage, no background music.
WAN 3.0210
Read the full prompt — Dracula Eats Marshmallow@Video1 controls motion, camera, composition, timing, and sound; keep all of it exactly: the dancer comes toward the handheld camera, takes out a plain white marshmallow, bites it and chews with a deadpan face staring straight into the lens, then turns away and dances off into the crowd. @Image1 controls the identity of the dancer: replace him in every frame with the person from @Image1, including face, hair, build, outfit. No trace of the original. @Image2 controls the people who follow and dance behind him: replace the guests behind him with the people from @Image2. @Image3 controls one onlooker in the crowd who squints suspiciously at the dancer; only one of him. If @Image2 or @Image3 is not provided, fill the crowd with people dressed to fit the location. If @Image4 is provided, it controls the location: replace the room, furniture, lights and floor to fit that place, and dress everyone in the background to match it. If @Image4 is not provided, keep the original environment. From @Video1 take only the motion and the camera; take none of its people, clothes, furniture, lights or floor. The marshmallow stays plain white and clearly visible. One continuous shot, no cuts, no subtitles, no text.

How to Write Portraits & People Video Prompts

A portrait video lives on small motion. List it the way you would brief an actor: "blinks naturally once or twice", "minimal micro-movements of the eyes", a breath. Let the hair react to something real: "A light breeze gently moves her hair". If a gesture matters, start from rest. The subject looks away, then "slowly rotates her head to face the lens". A pause that turns into a move reads as intent, not a loop.

Pick one camera behavior. "Camera is static" keeps attention on the face. A slow pull-out that "dollies backward from a tight close-up" reveals the setting. Try a physical dolly instead of a zoom: near and far elements shift against each other, and the space feels real. Say how the clip ends, for example the subject holding the final look. Without an ending, the clip may wander off.

FAQ