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 3.040

Dracula Hand Dance

Read the full prompt@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 3.080

Read the full prompt@Video1 controls motion, camera, composition, cuts, slow motion, timing, and sound; keep all of it exactly. @Image1 controls the identity of the scoring player (drives, dunks twice, celebrates to camera): replace the player in every shot with the person from @Image1, including face, hair, build, outfit. @Image2 controls the identity of the defender who gets dunked on: replace the defender in every shot, including the final one; if @Image2 is not provided, keep the original defender. No trace of the originals. If @Image3 is provided, it controls the location: replace the environment with that place. Rebuild court, hoops, background, crowd, lighting, and grading to fit it. If @Image3 is not provided, keep the original environment. In the final shot, the only player in frame is the already replaced defender (from @Image2, not the original), standing in the center with a hand covering the face. Remove the man behind; keep the crowd. Keep choreography, dunks, celebration.

Seedance 2.540

Read the full promptA Black groom in a white shirt straightens his emerald bow tie at a mirror while his mother in brown brushes his shoulder, both laughing. Morning light from the open door. Camera slowly pushes in. No text, no logos.

WAN 3.040

Read the full promptA young woman inventor in an olive canvas jacket, dark hair tied back, lifts a white handmade model airplane toward the camera in a garage workshop, smiles and says in a bright female voice: "Look at this, it finally worked!" Lips match the words. An amber desk lamp glows on the left, soft window daylight falls from the right. Medium shot to the shoulders, the camera slowly pushes in. No background music, no text, no logos, no watermark.

Kling 3.080

Read the full promptA Black baker in his thirties, short twists, flour on his forearms, stands behind a market stall counter, looks into the camera and says: "Fresh bread, still warm from the oven." His lips match each word, and he smiles at the end. Steam rises from wheat-gold loaves on a cream linen cloth, a deep green awning overhead. Low early morning sun from the side. Medium shot at eye level, the camera stays still. No background music, no text, no logos, no watermark.

LTX 2.3200

Read the full promptA couple stands on a dirt path beside a field at sunset, laughing at each other; he gently tucks a strand of hair behind her ear. She wears a rose-pink dress, he a cream linen shirt, and the olive-green field glows behind them. Low sun from the side lights both faces warmly. Medium shot at eye level, the camera slowly pushes in. No text, no logos, no watermark.

WAN 3.0110

Read the full promptA woman in a fuchsia raincoat walks under an indigo umbrella past an ivory wall, rain splashing on the wet asphalt. Soft overcast sky light; the camera tracks sideways alongside her. No text, no logos, no watermark.

Seedance 2.070

Read the full promptA bold white sans-serif headline stays burned across the top of the frame for the whole shot. The words are spelled V-O-I-C-E, S-U-B-T-I-T-L-E-S and P-R-E-S-E-N-T-E-R. The headline reads exactly: Change voice, subtitles and presenter. Below it, a scene. The framing, the set and the lighting never change: the same bright modern studio with a soft grey backdrop, the same chest-up framing, the same soft key light. Only the presenter changes. A woman with dark curly hair in a navy blazer stands in frame speaking to the camera with natural lip movement and small hand gestures. A sweep of light passes across the frame and she is instantly replaced, in exactly the same position and pose, by a man with light skin and short blond hair in a grey shirt, still speaking. Another sweep and he is replaced by an older woman with East Asian features and straight black hair in a cream blouse, still speaking. Another sweep and she is replaced by a man with dark skin and a short beard in a black turtleneck, still speaking. All four are ordinary anonymous people and look like nobody famous. Do not depict any real person, actor, celebrity or public figure and do not reproduce anyone's likeness. A clean white rounded subtitle bar sits near the bottom of the frame the whole time. It carries one short caption at a time, in the language of whoever is on screen at that moment, and the caption changes at every swap. While the first presenter is on screen the bar reads exactly Hello, spelled H-E-L-L-O. While the second is on screen it reads exactly Hola, spelled H-O-L-A. While the third is on screen it reads a short greeting written in Japanese characters. While the fourth is on screen it reads exactly Bonjour, spelled B-O-N-J-O-U-R. Each caption is one single word, correctly spelled, centred in the bar, dark text on the white bar, and no other words ever appear in it. Smooth quick dissolves between presenters, shallow depth of field, clean corporate look. Plain unbranded clothing, no logos anywhere. Do not depict any real brand or trademark. Each presenter speaks that same greeting out loud in their own language, one after another: the first speaks English, the second Spanish, the third Japanese, the fourth French. Clear natural speech, accurate lip sync, one calm voice at a time, no music, no background score, no singing. The headline at the top and the one short caption in the bar are the only text in the entire frame.

WAN 3.080

Read the full prompt@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.

WAN 3.050

Read the full prompt@Video1 controls motion, camera, composition, cuts, slow motion, timing, and sound; keep all of it exactly. @Image1 controls the identity of the scoring player (drives, dunks twice, celebrates to camera): replace the player in every shot with the person from @Image1, including face, hair, build, outfit. @Image2 controls the identity of the defender who gets dunked on: replace the defender in every shot, including the final one; if @Image2 is not provided, keep the original defender. No trace of the originals. If @Image3 is provided, it controls the location: replace the environment with that place. Rebuild court, hoops, background, crowd, lighting, and grading to fit it. If @Image3 is not provided, keep the original environment. In the final shot, the only player in frame is the already replaced defender (from @Image2, not the original), standing in the center with a hand covering the face. Remove the man behind; keep the crowd. Keep choreography, dunks, celebration.

Kling 3.020

Read the full promptEye-level medium shot: a woman in her fifties with deep brown skin and short grey-streaked natural hair sits on a low wooden bench in a village courtyard, against an ochre mud-brick wall, in an indigo cotton wrap, green banana leaves behind. Low evening sun lights her smiling face. She beckons with one hand, looks into the camera and says: "Come closer, I want to show you something." Camera slowly pushes in. No background music, no text.

Kling 3.080

Read the full promptA woman by a window reads, tears on her lashes, a gentle smile slowly rising. Dusty-blue wall, caramel knit sweater, cream curtain, soft overcast window light. Close-up, the camera slowly pushes in. No text or logos.

Veo 3.190

Read the full promptClose-up of a university student at a desk in a dark dorm room at night, her face lit only by the cool pale-blue glow of a laptop screen below the frame, the screen itself unseen. A warm brass desk lamp glows softly behind her, graphite walls fall into shadow, an unmarked canvas tote hangs on her chair. She reads with focus and tucks a strand of hair behind her ear with a small tired smile. The camera slowly pushes in. No text, no logos, no watermark.

WAN 3.080

Read the full promptA man in a dusty blue shirt stands in profile at a caramel-wood window, slowly lifting a cup. Warm window light shifts across his face as clouds pass. The camera stays still. No text, no logos, no watermark.

Seedance 2.0150

Read the full promptA bold white sans-serif headline stays burned across the top of the frame for the whole shot. The first word is spelled G-E-N-E-R-A-T-E, the second word is spelled C-I-N-E-M-A-T-I-C, the third word is spelled S-C-E-N-E-S. The headline reads exactly: Generate cinematic scenes. Below it, a cinematic film scene. A man in his forties in a dark coat stands alone at a rain-soaked window at night, blurred city lights behind the glass. One warm lamp lights him from the side, the other half of his face in deep shadow. He breathes out, his eyes glisten, he slowly closes them. The camera pushes in very slowly to an extreme close-up of his eyes. Anamorphic lens, shallow depth of field, film grain, teal and amber grade. Quiet restrained emotion, no action. Plain unbranded clothing, no logos or lettering in the background. No dialogue, no subtitles. The headline at the top is the only text in the entire frame.

WAN 3.040

Read the full prompt@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.

Seedance 2.020

Read the full promptWarm morning backlight from a living-room window: a mother in a mint sweater rocks her smiling baby, then the father steps in and hugs them both, cream walls, a terracotta sofa behind. The camera slowly pushes in.

Seedance 2.010

Read the full promptA woman in her fifties with a grey-streaked bun and a mint cardigan stands in a light wooden doorway of a terracotta house, one hand opening inward in welcome. With a moved smile she looks into the camera and says: "Good evening, and welcome to our home." Two guests stand still, barely visible at the frame edge. Warm evening lamp by the door lights her face. Eye-level, the camera stays still. No background music, no text, no logos, no watermark.

WAN 3.030

Read the full promptA woman in her thirties with box braids in a loose bun and an ochre apron over a white tee stands at a wooden loom in a bright workshop, indigo yarn skeins hang on the wall behind her. Soft daylight from a window on the left lights her face. She smiles, holds a turquoise woven scarf out toward the camera and says: "I made this one just for you." The camera stays still. No background music, no text.

Seedance 2.560

Read the full promptA Black bride in a cream gown pins a coral boutonniere on her groom's jacket as both laugh, on the gold-lit porch of their family home, low sun behind them. The camera slowly orbits them.

Seedance 2.090

Read the full promptA heavyset coffee shop owner in his sixties, bald, round glasses, rolled sleeves of a faded denim shirt, leans on a light-wood counter next to a ceramic pour-over kettle and a green fern. He looks at a guest and says quietly: "Welcome in, please sit anywhere you like." He smiles as he finishes. Exposed brick wall behind him, warm evening light from one bare-bulb pendant lamp. Medium shot, the camera stays still. No background music, no other voices, no text, no logos, no watermark.

LTX 2.360

Read the full promptWide shot from a low angle close to the ground. On a pitch of dusty orange earth, a boy in a white shirt runs up and kicks a football across the frame while two friends in grass-green shirts watch it fly. Behind them a football stadium with tall floodlight towers, white beams switched on against the evening sky. Warm low sun from the left, floodlights as a second cool-white source. The camera stays still. No text, no logos, no watermark.

LTX 2.3200

Read the full promptA businesswoman in a white blazer walks at an even pace along a glass-walled office gallery, seen in a medium side shot. Sage-green panels line one side, an ochre wooden floor runs beneath her, white walls fill the far end. Daylight pours down from a skylight above her head and lays soft bright bands across the floor. The camera tracks smoothly alongside at her pace, nothing else moves. No text, no logos, no watermark.

Seedance 2.040

Read the full promptThere is no writing of any kind anywhere in this shot: no headline, no caption, no subtitle, no sign, no label, no lettering and no logo appears at any point. In that frame, a fashion-magazine style shot of a woman presenter standing in the bright glass office of a glossy fashion magazine. She wears a striking scarlet-red tailored wool coat with strong shoulders, worn open over a crisp white silk shirt, a wide black belt at the waist, and large sculptural gold earrings. Sleek dark hair in a sharp bob, bold red lip, confident poised posture. Behind her, thrown far out of focus, a rail of colourful garments, a tall window full of city light, white orchids on a polished desk and pale marble walls; warm reflected light, glossy editorial styling, rich saturated colour. She looks straight into the camera and speaks to the viewer with natural lip movement, calm confident delivery and small precise hand gestures. Framed from the chest up, eye level, crisp key light with a soft rim light along her shoulder, shallow depth of field. The camera pushes in very slowly and comes to rest; at the end she finishes her sentence, holds the look at the camera and gives one small confident nod, and the shot settles calmly on her — the movement finishes on screen and nothing is cut off halfway through a gesture. She says out loud in English: "Our platform turns your idea into a finished video in minutes." Clear natural speech, accurate lip sync, one voice only, no music, no background score, no singing. She has a symmetrical oval face with high cheekbones, a straight nose and dark brown eyes. She is an ordinary anonymous person and looks like nobody famous. Do not depict any real person, actor, celebrity or public figure, and do not reproduce anyone's likeness. Her clothes and every object in the room are plain and unbranded: no logo, no monogram, no emblem, no lettering on the clothes, the walls, the desk or anything else. Do not depict any real brand or trademark. No subtitles, no captions. Remember: not a single readable character appears anywhere in the frame.

FAQ