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

Ancient Style Whistle Dance OOTD

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

Ancient Style Whistle Dance OOTD — AI video creation
Ancient Style Whistle Dance OOTD

提示词 / Prompt

English prompt

7 seconds, 9:16, single take, sweet ancient style OOTD short video. 7 seconds of audio plays completely, synchronized with the character's dance. Strictly use the adult female in the @Character Reference Image Character Design Diagram as the sole character: use the right-side close-up face as the facial reference, and the left-side front image and middle back image as references for clothing, hairstyle, and back structure. Fully maintain her small oval face, refined features, red forehead flower makeup, deep brown-black high classical bun, light gold leaf hairpin, pearl tassels, and side hanging bead chains; fully maintain the light champagne white and pale pink ancient style dance outfit, embroidered corset inner layer, light apricot transparent long sleeve gauze robe, light gold sash, metal chain accessories, and multi-layered hanging long skirt. Throughout, no face swapping, outfit changing, hairstyle alteration, or accessory addition/removal is allowed. Only reference the @Video Character's motion path, posture, rhythm, shot size changes, and composition, without inheriting the original video character's face, hairstyle, clothing, color, or material. Pure white studio, high-angle slight overhead shot, ultra-wide angle slight perspective, camera mostly fixed, character always fully or mostly in focus. 0-1 seconds, character walks in from the right side of the frame holding a small amount of the skirt lightly, long skirt and thin gauze sleeves naturally swaying; 1-2 seconds, character approaches the lens, upper body slightly leaning forward, eyes looking at the lens, expression sweet and restrained; 2-3 seconds, hands gently rest on the waist, forming a natural hourglass silhouette, playful slight head tilt; 3-4 seconds, elegant side turn half-circle, showcasing the back of the outfit, bun, and sash structure, then glances back at the lens; 4-5 seconds, returns to front with a faint smile, arms naturally extended to sides, gauze sleeves slowly descending; 5-6 seconds, hands lightly placed behind, first lowers head to adjust posture, then slightly tilts head toward the lens; 6-7 seconds, again gently rests hands on the waist, character first turns head to the 90° side front, eyes first focus on something beyond the lens, then turns to the lens, ending with a sweet, confident, and dignified ancient style pose. Movements natural and smooth, light and restrained, no large-scale dance movements. Skirt hem, gauze sleeves, bead chains, and ear-side hair strands show slight realistic inertia with movements, avoiding exaggerated flapping. Bright soft light, clear and bright, soft champagne tone, high-end texture combining ancient costume film ads and Korean-style fashion short films, upbeat rhythm, no dialogue, paired with light, ethereal Chinese pop music. Character identity, facial features, hairstyle, clothing patterns, and accessory positions remain stable throughout, facial clarity and stability, realistic skin texture, 4K quality, clear details. Do not use the blank face-covering in the left-side front image as the character's face, facial features must come from the right-side close-up; do not inherit the original video character's face, hairstyle, or clothing; do not add characters, change outfits, jump cuts, large camera movements or shakes, rapid rotations, vigorous sleeve swings, skirt hem covering face, limb deformation, repeated arms, extra fingers, hand adhesion, clipping, clothing mutation, accessory disappearance, hairstyle changes, or background changes.

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