VdoBloom
← Back

Paper Cutout Hero Shadow Comedy

Cinematic Scene Showcaseby @Soran · source ↗August 1, 2026

Full prompt

[Overall Style]
Cinematic ancient-style comedy. Merges a real-life traditional opera backstage with a flat 2D Chibi-style sticker character. Focuses on Seedance 2.0 reference-guided performance, controllable lighting and shadows, and stable physical interaction. Uses restrained martial arts aesthetics, warm amber lantern light vs. cool backstage shadows, layered veils, and graphic silhouettes to build a comedy arc about a small character directing their own heroic image.

[Character Setting]
Subject ID: Chibi Female Martial Artist. A 19-23 year old Chibi East Asian female. Round head is 57% of body height. Pale peach flat-shaded skin, dark brown dot eyes, small confident mouth. Black hair in a high circular bun with red tassels. Wearing white boots, black leggings, gold-trimmed red silk opera robe, jade belt, and a mini straight sword. Maintains Cel-shading, thick ink outlines, and flat sticker depth throughout.

[Shot 1 | 0-5s | Wide Shot]
Locked camera with slow dolly-in. Establishes a real opera backstage with wooden beams, red costumes, brass hooks, instrument cases, translucent veils, and a floor lantern. Her full body stands by the lantern while her massive shadow covers the entire veil.

[Shot 2 | 5-10s | Cowboy Shot]
Horizontal tracking. The same robe-wearing Chibi character performs a clean three-beat sword sequence—stepping, turning, slashing. Simultaneously, a realistic human hand pushes the lantern forward, causing her shadow to expand into a towering heroine silhouette. Sleeves and sword movements are perfectly synchronized with the shadow. Sounds of fabric, footsteps, and a deep opera drum punctuate the action.

[Shot 3 | 10-15s | Close-up]
Same character and lantern-lit backstage. The human hand accidentally pulls the lantern back, causing the massive shadow to shrink to a tiny point. She pauses, squints her dot eyes, and uses the mini sword to hook the lantern ring, dragging it back to restore the giant silhouette. She maintains her solemn stance but casts a proud side-glance at the camera. Ends on the sharp contrast between her tiny flat body and the massive shadow.

[Technical Requirements]
9:16 vertical, 8K cinematic detail. Uses one locked character reference, one real scene reference, and one audio reference. Realistic shadow physics, no dialogue, no animal characters.

[Negative Prompts]
blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Original prompt

【整体风格】

电影级古风喜剧,将真实实拍的传统戏班后台与一名纯 Flat 2D Q 版人类贴纸角色融合,围绕 Seedance 2.0 的参考素材引导表演、可控灯光与阴影、稳定物理交互、同步音效和多镜头调度进行设计;采用克制的武侠美学、暖琥珀色灯笼光与清冷后台暗部的对照、层叠纱幕、图形化剪影、经过设计的视觉误导,并以“小人物主动导演自己的英雄形象”构建喜剧弧线,跳脱捣乱与受罚模式。

【角色设定】

Subject ID|Q版女性小武生

一名 19-23 岁的 Q 版东亚女性小武生,圆润大头约占全身高度的 57%,浅桃色平涂肤色、深棕色豆豆眼、细小自信的嘴巴,黑发盘成高位环形发髻,系红色流苏发带,从脚到头穿白色布靴、黑色绑腿、金边大袖红色织锦戏袍、窄玉腰带,并持一柄迷你直剑。

全程只保持赛璐璐平涂、粗墨线描边与僵直贴纸景深。

【镜头 1|0-5s|全景】

锁定机位配合缓慢推轨,建立一个真实传统戏班后台。

画面包含深色木梁、悬挂的红色戏服、青铜挂钩、层叠乐器箱、半透明白色纱幕、一盏落地灯笼、缓慢漂浮的香雾、散落的化妆刷与磨损木地板。

她的完整身体站在灯笼旁,而她的巨大影子覆盖整面纱幕。

【镜头 2|5-10s|中景偏牛仔景】

同一个穿红色织锦戏袍的 Q 版女性小武生、同一柄迷你直剑、同一盏灯笼与同一面纱幕,background remains the same real opera backstage。

镜头进行横移跟拍。

同一个穿红色织锦戏袍的 Q 版女性小武生只完成一套干净的三拍剑式——踏步、转身、横斩。

与此同时,一只皮肤纹理真实的真人手轻轻把灯笼向前推,使她的影子扩张成顶天立地的女侠剪影,巨大衣袖与长剑严格同步她的真实动作。

衣料掠风声、木地板脚步声、剑刃破风声和一记低沉戏曲鼓点精准卡点。

【镜头 3|10-15s|特写】

同一个穿红色织锦戏袍的 Q 版女性小武生,background remains the same lantern-lit backstage。

真人手意外把灯笼拉远,她威风凛凛的巨大影子骤然缩成一个小点。

她停顿一拍,眯起豆豆眼,用迷你直剑勾住灯笼提环,把灯笼重新拖回准确位置,恢复顶天立地的英雄剪影。

随后,她保持庄严剑式,却向镜头投来一个得意的侧眼。

结尾定格在她微小平面身体与巨大影子形成的强烈尺度反差上。

【技术要求】

9:16 竖屏,使用最高可用原生分辨率,电影级 8K 观感细节,使用一张锁定角色参考图、一张真人场景参考图与一段戏曲鼓点音频参考。

首镜之后加入轻微手持呼吸感,服装与道具严格连续,灯笼移动和影子缩放符合物理逻辑,无对白,无可识别文字,不出现动物,不做拟物角色。

【负面词】

blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props
Generate this with Seedance 2 on VdoBloom.
Opens the image-to-video creator with this prompt and Seedance 2 pre-selected.
✨ Generate Video