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

spent way too long on this one but the fireworks scene made it worth it 🎆 lantern streets,…

公开作者的 SEEDANCE2.5 视频案例,包含可复用的完整提示词。

spent way too long on this one but the fireworks scene made it worth it 🎆 lantern streets,… — AI video creation
spent way too long on this one but the fireworks scene made it worth it 🎆 lantern streets,…

提示词 / Prompt

English prompt

SCENE CONTEXT A young Japanese woman films a handheld selfie vlog at a riverside shrine summer festival at night — paper lanterns strung along a stone embankment, floating lanterns drifting on the water below. She walks the lantern-lined path, buys a skewer of grilled mochi, plays a cork-gun shooting gallery and wins a small bell charm, then sits on the riverbank and watches fireworks burst over the water before signing off to camera. ACTIVE REFERENCES @image1: young woman, dark hair styled loosely up with soft face-framing strands, warm brown eyes, soft round face, light natural makeup, delicate floral hair ornament. 100% matches the reference. LOCATION MAP Foreground: her extended selfie arm holding the phone, natural front-camera framing. Midground: stone embankment path lined with red and cream paper lanterns on bamboo poles, food stalls and a shooting-gallery stall with warm bulb lighting to one side. Background: the river below reflecting lantern light, distant silhouettes of festival-goers, a low wooden footbridge. Practical light sources: paper lanterns (warm amber), stall string-lights (soft white-warm), no signage or neon of any kind. FIRST FRAME / BLOCKING She is centered-left in frame, phone held at arm's length and slightly above eye level, walking toward camera along the lantern path, lantern glow rimming her hair, river visible over her shoulder in the background. FORMAT MODE Timed multishot — HARD CUTs at stated seconds, cuts only at the specified points, the camera does not cut on its own. OPTICS 0–8s: 84° wide FOV, selfie-arm framing, natural handheld phone-camera distortion at the frame edges. 8–16s: 63° FOV, still selfie framing, slight downward tilt toward the food stall. 16–23s: 63° FOV, selfie framing angled toward the shooting-gallery counter, phone held lower to keep both her face and the targets visible. 23–30s: 84° FOV, selfie framing seated on the riverbank, wide enough to hold her face in the lower third and the firework bursts in the upper frame simultaneously — no phone-flip needed. No drift mid-segment. CAMERA Handheld selfie-arm operator throughout: natural micro-shake, small vertical bounce matched to her walking pace, arm drifts and re-centers her face every few seconds the way a real phone selfie does. At 23s she lowers herself to sit, camera settles into a steadier handheld hold braced on her knee, minor sway only. ACTION 0.0s to 8.0s — She walks along the lantern path, glancing between the camera and the path ahead, loose hair strands lifting slightly in the warm night breeze, lanterns passing softly out of focus behind her. 8.0s HARD CUT 8.0s to 16.0s — She stops at a grilled-mochi stall, takes the skewer from the vendor's hand just out of frame, bites it, chews, and grins wide at the camera with her cheeks puffed, steam rising faintly from the mochi. 16.0s HARD CUT 16.0s to 23.0s — She leans over a cork-gun shooting-gallery counter, one eye closed aiming the toy gun at a shelf of small prizes, fires, a cork dart knocks a tin bell off its stand with a clatter, she yelps and claps once, the stall attendant hands her the small bell charm on a cord. 23.0s HARD CUT 23.0s to 27.0s — She walks a few steps to the riverbank and sits down cross-legged facing the water, phone still held at selfie angle, the first fireworks bloom in the sky behind and above her, their glow and color briefly washing across her upturned, delighted face as she watches over the top of the phone. 27.0s HARD CUT 27.0s to 30.0s — Still seated, she turns her focus back to the lens, face lit warm from the lantern light and cool flicker from the fireworks above, she waves once at the camera and says, "That's tonight's little adventure — catch you on the next one, bye!" PERFORMANCE Unscripted, lightly breathless energy between beats from walking; sharp startled-delight micro-expression at the shooting gallery (eyebrows lift, small flinch at the clatter, then a laugh); softer, awed half-smile during the fireworks with eyes tracking upward before returning to camera; catch-lights from lantern glow visible in her eyes throughout; pore-level skin realism, soft natural blush. PHYSICS Hair and kimono sleeve fabric move naturally with her walking pace and the night breeze; steam rises and dissipates off the grilled mochi; the cork dart travels in a real short arc and knocks the tin bell with a visible small bounce and wobble; water ripples naturally under the floating lanterns and firework reflections; her seated weight settles naturally onto the stone embankment. LIGHTING Warm 3200K practical key from paper lanterns and stall bulbs throughout, soft ambient fill from the diffuse night sky; at 23–30s a secondary cool-white and amber flicker from fireworks washes across her face and the river in time with each burst, without overpowering the warm base tone. WARDROBE Sage-green cotton kimono-style summer robe with a subtle white crane-and-wave print, pale blush obi sash tied in a simple bow at the back, wide sleeves trimmed in cream, fabric soft and slightly loose from a night of walking. AUDIO Ambient festival murmur, distant taiko drum, crunch of gravel underfoot, sizzle from the food stall, clatter of the tin bell at the shooting gallery, crackle and boom of fireworks overhead, her voice: "That's tonight's little adventure — catch you on the next one, bye!" STYLE Photoreal smartphone vlog look, natural front-camera color science, ultra-high-definition 4K clarity with fine authentic skin and fabric micro-detail, slight authentic handheld imperfection, no artificial neon or synthetic lighting anywhere in the scene. OUTPUT SETTINGS 16:9 widescreen, 4K resolution, real-time throughout, natural phone-camera dynamic range and grain. POSITIVE LOCKS Her face and identity stay consistent with the reference in every cut. Lighting stays warm-lantern-based throughout, only fireworks add a brief cool-amber accent. No neon signage or neon-colored light sources anywhere in frame. Kimono-style robe, obi, and bell-charm prop stay visually consistent across all cuts.

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

  • 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

  • Miniature Luxury Treehouse Timelapse Build

    在树上建造一座小型豪华住宅 🏡生成提示词 MOTION PROMPT 1 Step1:在 Google flow 生成一张初始图片,选择 Nano Banana 2 生图模式,复制下面的提示词,生成图片—— A hyper-realistic miniature luxury treehouse construction site at the very beginning of construction, built high among the thick branches of a large mature tree, set in a natural forest environm

  • Bedroom Goth Makeup Transformation Video

    Duration:16秒 Aspect ratio:9:16竖屏 Overall style: 真人美妆变身短视频,固定手机机位,近距离人像构图。 前半段是日常卧室里的自然状态,光线明亮中性;后半段变为暗黑华丽的哥特妆造,脸部有柔和正面光,黑色羽毛与珍珠反光清晰。 保留真实皮肤纹理、细小亮片、薄纱和羽毛质感,不做动漫脸或塑料磨皮。 SUBJECT / 角色绑定: @图片1 命名为【女主】,全片唯一人物。保持角色卡的面部身份与骨相;前后造型可以变化,不能变成另一张脸。 ENVIRONMENT / 场景: 前半段是普通卧室:浅灰色墙面,后方可见床靠和床品,画面右上角有一幅抽象挂画。固定手机正