OpenZhenZhen AI 提示词画廊 · SEEDANCE2.5 · video

Japanese Male Character Reference Sheet

公开作者的 SEEDANCE2.5 视频案例,包含完整 prompt 和可播放成片。

Japanese Male Character Reference Sheet — AI video creation
Japanese Male Character Reference Sheet

提示词 / Prompt

English prompt

A single character reference sheet photograph, wide landscape format, on one continuous plain flat mid-grey background, perfectly uniform with no gradient and no shadow falling on it. Flat even studio lighting from the front across the whole sheet, no dramatic light, no rim light, no colour cast. Three views of the same person are arranged side by side on this one sheet, evenly spaced, all standing on the same invisible ground line, all lit identically. THE SUBJECT — an adult Japanese man with the worn look of someone well into working life, lean and wiry, with a long narrow face and a visible jaw hinge. Warm-toned skin, tanned and weathered by sun, with sun lines at the outer corners of the eyes. Narrow hooded eyes, a straight even nose bridge, thin lips, an angular jaw. His gaze is level and unhurried, calm and settled. Short black hair cropped close at the sides, a few grey threads at the temples, pushed back off the forehead. Light patchy stubble across the jaw and upper lip, a few days old. He wears a faded olive-green cotton jungle shirt, softened and thinned by wear, sleeves rolled to just below the elbow, with the top button undone so the collar sits open and loose at the throat; dark khaki cargo trousers with flat side pockets; and scuffed brown leather hiking boots. He wears no harness of any kind: no waist belt, no buckle, no thigh loops, no webbing straps, no rope, no carabiner, nothing strapped over his clothing anywhere on his body. His nose stays exactly the same colour as the rest of his face: no red tint, no pink tint, no rosy tip. His skin is dry and matte: no sweat, no oily sheen, no wet highlights. LEFT VIEW — a large portrait, head and shoulders only. The face is square to the camera and looks straight into the lens — the face is frontal, not turned away. The head is tilted gently to one side: the crown of the head tips toward the subject's own right shoulder, which is the shoulder on the FRAME-LEFT side of the picture. A soft tilt of roughly ten degrees, no more. The shoulders stay level. This tilt is required. This portrait is by far the largest element on the sheet: the head alone is at least twice the height of either standing figure's head, and it fills roughly the left third of the picture from top to bottom. Keep the real fine pores, vellus hair, stubble texture and natural asymmetry of the skin. No retouching, no smoothing, no beauty filter. A small clear catch-light in each eye. CENTRE VIEW — a full-body figure from the neck down, standing straight and facing the camera, arms relaxed at the sides, feet slightly apart. The figure ends cleanly at the base of the n

主题与风格

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作

  • They Picked The Wrong Girl

    Create ONE ultra-realistic cinematic live-action action sequence at night on the famous San Antonio River Walk, Texas. Keep the recognizable River Walk visible throughout: illuminated bridges, stone architecture, trees, river reflections, and warm lights. Exactly ONE young woman, THREE male attacke

  • Three Layer Travel Vlog Montage

    Create a realistic 15-second vertical travel vlog using the reference image. Keep all three horizontal layers visible and continuously moving for the entire video. Never freeze, remove, or stop any layer. Change the location and shot in ALL THREE layers together every 4 seconds: 0–4 sec: Scene 1

  • Underground Worm Chase Escape

    生成一支30秒的写实地下怪兽追逐短片。 采用好莱坞商业生物惊悚片的动作调度:开场立即遇险,中段短暂躲过,随后危险突然升级,最后一次奋力逃脱带来短暂释放,再以撞击收尾。全片是同一场连续事件,多镜头剪辑,时间不跳跃。 角色与怪兽 成年女主角严格参考 #2  图片1 ,发型与服装严格参考 #3  图片_20260911221703_12_537图片_2026091122… ,保持面容设计。右手握带腕绳的手电。她不是始终对着镜头展示惊恐,而是根据眼前发生的事做出不同反应:逃跑时咬牙控制呼吸;听见身后扑击时骤然缩肩、抽气;看见逃生门时眼神集中、身体加速;摔倒后先疼得闭眼,再挣扎爬起;门关上后才出现压

  • Seoul Errand On A 2003 Camcorder

    Create a 30-second, 1080p ultra-realistic personal home video of a young Korean woman running a small summer errand in an old Seoul residential neighborhood. It should feel like an unplanned recording by a friend using an early-2000s DV camcorder. SUBJECT: A naturally pretty Korean woman in her ear

  • New York Vertical Travel Film

    Create a ultra-realistic cinematic vertical travel film in strict 9 16, showcasing the iconic beauty of New York City, USA America, using the generated image as the visual reference for composition, skyline, lighting, and landmarks. — EAST RIVER OPENING Begin with a cinematic view over the East Riv

  • Tsunami Wipes Out a Harbor City

    Create a 15-second ultra-cinematic, photorealistic disaster sequence beginning during a peaceful sunny afternoon at a bustling coastal city harbor before an enormous tsunami suddenly devastates the entire waterfront. The camera must remain in one continuous fluid shot with no cuts. 0-3 sec: Begin