OpenZhenZhen AI 提示词画廊 · SEEDANCE2.5 · video
Seedance 2.5 vs Seedance 2.0
公开作者的 SEEDANCE2.5 视频案例,包含可复用的完整提示词。

提示词 / Prompt
English prompt
**[SCENE]** A two-member female pop duo shoots a retro Y2K-style music video: candy-colored studio sets, tightly synchronized hand choreography, beat-locked hard cuts and fast punch zooms — the texture of 1999 music television, rendered at modern production quality. **[ACTIVE REFERENCES]** <<<image_1>>>: Female singer in her twenties, long straight pink hair with gold hair clips, small nose ring, beauty mark on cheek, white printed crop top, silver chain necklace, chain belt, light-blue washed baggy jeans, off-white platform sneakers. Playful and confident. 100% match to reference image. <<<image_2>>>: Female singer in her twenties, long straight black hair with silver hair clips, light blue eyes with silver glitter eyeshadow, red cord necklace with ruby pendant, gray raglan short-sleeve tee with a gray jacket draped over the shoulders, dark gray pleated skirt with bow, gray knee socks, black platform shoes. Cool and commanding. 100% match to reference image. **[SET MAP]** Three practical studio sets, each roughly 4 meters deep, facing camera: Set A — bubblegum-pink seamless cyclorama, glossy reflective floor, two rows of round studio light bulbs on the back wall. Set B — cobalt-blue seamless cyclorama, a single hard white spotlight circle on the floor. Set C — floor-to-ceiling silver rain-strand curtain wall, mirrored floor. **[FIRST FRAME & SPATIAL LAYOUT]** The first visible frame already contains both girls, on Set A: <<<image_1>>> at frame-left x40%, <<<image_2>>> at right x60%, medium-shot depth, 0.5 m apart, bodies squared to camera, eyes locked on lens, frozen in a mirrored opening pose — inner hand on hip, outer arm raised. No empty establishing shot, no delayed entrance. **[FORMAT]** Controlled multi-shot sequence, seven segments across 15 seconds, every hard cut landing precisely on a musical downbeat. Real-time motion. **[LENS NOTES]** Fisheye = true fisheye wide-angle, 1.5 m from subject, visible barrel distortion at frame edges, deliberate 1999 MV lens language; 47° = standard view, natural proportions; 29° = medium-tele portrait, background lightly compressed; 18° = long-lens close-up, melted bokeh. Locked within each segment, no drift. **[ACTION TIMELINE]** 0.0–2.0s Set A, fisheye low angle: both hit the frozen mirrored pose on beat one, then bounce-groove in sync with every beat, camera slowly pushes in 10%. Hard cut at 2.0s. 2.0–4.0s Set B, 29°: <<<image_2>>> solo dance inside the spotlight circle at x50%, pointed-at-camera precision hand choreography, one fast punch zoom landing exactly on the downbeat. Hard cut at 4.0s. 4.0–6.0s Set C, 47°: <<<image_1>>> whips her pink hair through a full arc, then strides toward camera as the camera pulls back at matched speed, rain-strand curtain shimmering, chain belt swinging. Hard cut at 6.0s. 6.0–8.0s Set B, 18° two-shot close-up: both faces cheek-to-cheek filling the frame, <<<image_1>>> left / <<<image_2>>> right, soft wind lifting pink and black strands, glossy makeup, confident smiles, heads tilting toward each other in sync with the beat. Hard cut at 8.0s. 8.0–11.0s Set A, 47° full body: the chorus dance core — three counts of fully synchronized choreography: wave arms, fast spin, full-body groove into a sharp freeze; positions cross and return, <<<image_1>>> left / <<<image_2>>> right re-locked. Hard cut at 11.0s. 11.0–13.0s Set C, 47°: the two walk toward camera side by side with synchronized arm swings, black and pink hair swinging with each step, reflections in the mirrored floor. Hard cut at 13.0s. 13.0–15.0s Set A, 47°: back-to-back frozen final pose, camera zooms out fast to full body, landing exactly on the last downbeat, one bright camera-flash white sweep over the final frame. **[PHYSICS]** Choreography carries real weight: heel strikes, weight shifts, shoulder isolations with follow-through. Hair whips show visible lag and settle naturally. Chain belt and necklaces swing on the beat points. Rain-strand curtain ripples from body movement. Glossy floor returns soft, believable reflections. **[LIGHTING]** High-key, even studio lighting on every set: large soft frontal key, bright clean exposure, high skin sheen; Set A's bulb rows create back rim light and soft bloom into the lens; Set B's spotlight casts a crisp circular pool; Set C sparkles with hundreds of rain-strand specular highlights. Bright, candy-like, camera-ready — a deliberate flat 1999 broadcast-TV look. **[AUDIO]** Original Y2K bubblegum dance-pop instrumental, 120 BPM, four-on-the-floor kick, bright syncopated synths, faint tape hiss underneath. Every hard cut lands exactly on a downbeat. Instrumental only throughout, no vocals; both girls perform with closed lips, delivering energy purely through expression and choreography. **[POSITIVE LOCKS]** Both faces and identities 100% locked to reference images across all segments including close-ups. Wardrobe stays exactly as referenced across all three sets. Only these two girls appear in the entire video. In every two-person segment <<<image_1>>> is fixed frame-left, <<<image_2>>> fixed frame-right. Within each segment, set geography, spacing, and screen direction stay consistent. **[STYLE]** Shot at modern production quality but graded to 1999 broadcast texture: broadcast-grade videotape master grain layered over high-detail imagery — soft highlight bloom, slight chroma bleed on hard color edges, fine analog tape grain, faint interlace flicker on fast motion; a high-saturation candy palette of bubblegum pink, electric cobalt and chrome silver; Y2K music-television punch-zoom editing energy, with contemporary sharpness preserved underneath.
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
相关作品
- 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