Xianxia Deadpan Comedy Video Sequence
Full prompt
[Generation Mode & General Requirements] Must use Seedance 2.0 Fast, strictly generate a full 15-second video, 16:9 aspect ratio, three continuous clear shots, with native synchronized Mandarin dialogue. Masterpiece cinematic realism, Arri Alexa cinematic look, with a restrained and poetic Xianxia deadpan comedy atmosphere. Sharp and clear visuals, visible volumetric morning light, restrained acting, and realistic yet cinematic movement. Physical feedback for silk fabric, hair, paper, water, mountain mist, and natural light must be believable. Uses a "Reference Image Driven Living World System": all reference images together determine the location and visual world, including terrain logic, architectural language, spatial scale, material age, vegetation ecology, water flow, weather, mist movement, main light direction, reflective surfaces, comprehensive colors, and atmospheric depth. Before official generation, an environment planning pass is completed silently to reorganize a new, unified, and physically sound space from these shared environmental DNA. The background must be vivid, unique, and continuously operating naturally, but only responsible for environmental presence, not actively triggering comedic gags, changing character goals, or stealing focus from the plot. [Characters & Core Props] Character ID A | Sword Immortal Senior Sister Consistently the same 25–30 year old East Asian female from @Image1, strictly maintaining the same face, oval face shape, fair natural skin tone, dark almond eyes, long black hair partially tied up, white jade hairpin, tall and slender proportions, white embroidered silk Hanfu, semi-transparent layered wide sleeves, silver waist seal, jade pendant, and white cloth boots. Character ID B | Junior Sister Consistently the same 20–25 year old East Asian female from @Image2, strictly maintaining the same face, round and lively face shape, black hair in braids, petite proportions, lime green linen Hanfu, dark belt, wooden hairpin, and black cloth shoes. Core Prop A single sealed bamboo scroll throughout. The position, opening state, and holding relationship of the bamboo scroll across the three shots must be continuous and stable. [0–5s | Low-angle Panorama, Slow Tracking Shot] A stone terrace in a mountain corridor on a morning after rain. Below is a sea of clouds and valley. Carved stone railings, wet stone slabs, narrow water channels, ancient pines, light-colored flowering branches, distant tiled temples, slowly moving mountain mist, and continuously changing wetland reflections create a real, breathing environment. The same white-clad Senior Sister and green-clad Junior Sister are at opposite sides of a stone table. The Senior Sister gently places the sealed bamboo scroll on the stone table between them and says calmly: "Three years ago, you left something behind. I return it today." The environment maintains restrained movement: water flows continuously, thin mist passes slowly through the corridor, branches and clothes respond to the morning breeze, and reflections on the wet stone change naturally with the camera track. [5–10s | Cowboy Medium Shot] The same Junior Sister slowly reaches for the bamboo scroll, her other hand still resting naturally near her sword. The Senior Sister maintains a perfectly calm expression and adds: "I have already proofread it for you." Nearby leaves pass naturally through the frame, creating realistic foreground parallax; water flows continuously, and mountain mist moves slowly between corridors. The background only maintains the world's presence and does not actively create new plot events. After the Junior Sister takes the scroll, she begins to unfold it, maintaining continuous action for the next shot. [10–15s | Close-up to Extreme Close-up] The bamboo scroll is fully unfolded. Inside is not a secret manual, but a poem written by the Junior Sister three years ago; the paper is filled with neat, elegant red annotations. The Junior Sister freezes instantly and asks in a low voice: "You read it all?" The Senior Sister answers calmly: "I even changed three rhymes; the third line was the best." An extreme close-up captures the Junior Sister's ear tips turning visibly red. The Senior Sister still maintains a dignified, calm expression without a hint of mockery. At this moment, a drop of rain from the eaves naturally falls into the water channel, producing a slight but clear splash as a final deadpan beat. Strictly ends at 15.0 seconds. [Hard Execution Constraints] Must use Seedance 2.0 Fast Must generate full 15 seconds, no shortening or early termination 16:9 aspect ratio Strictly three shots Native synchronized Mandarin dialogue with accurate lip-syncing Character identity, face, hairstyle, body proportions, and clothing must remain stable Same bamboo scroll remains stable throughout Realistic parallax between foreground, midground, and background Environment stays alive but does not steal the show Realistic physics for silk, paper, water, mist, hair, and rain Only two visible characters throughout No on-screen subtitles or extra figures [Negative] blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, subtitles, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, hairstyle change, background shift, architecture mutation, lighting jump, glitching cuts, disappearing props, duplicated bamboo scroll, changing scroll design, extra characters, background crowd, environment stealing focus, random environmental gag, exaggerated comedy acting, slapstick reaction, overacting, modern elements, frozen background, static fog, static water, no parallax, abrupt camera jump, dialogue desync, lip-sync error
Original prompt
【生成模式与总要求】 必须使用 Seedance 2.0 Fast 生成,严格生成完整 15 秒视频,16:9 横屏,三个连续清晰镜头,原生同步普通话对白。 大师级电影写实质感,Arri Alexa 电影机观感,带克制而诗意的仙侠冷面喜剧气质。画面锐利清晰,体积晨光自然可见,表演克制,人物运动真实但具有电影感,真丝衣料、头发、纸张、水流、山雾与自然光具有可信物理反馈。 采用“参考图驱动的活世界系统”:所有参考图共同决定地点与视觉世界,包括地形逻辑、建筑语言、空间尺度、材质年代、植被生态、水流走向、天气状态、云雾运动、主光方向、反光表面、综合色彩和空气纵深。正式生成前先无声完成一轮环境规划,从这些共同环境 DNA 中重新组织出一个全新、统一、物理合理的空间。 背景必须鲜活、独特并持续自然运行,但只负责环境存在感,不主动触发包袱,不改变人物目标,不抢夺剧情中心。 【角色与核心道具】 角色 ID A|剑仙师姐 始终是 @图片1 中同一个 25–30 岁东亚女性,严格保持同一张脸、椭圆脸型、白皙自然肤色、深色杏眼、黑色长发半挽、白玉簪、高挑纤细身材比例、白色刺绣真丝汉服、半透明分层宽袖、银色腰封、玉佩 and 白色布靴。 角色 ID B|小师妹 始终是 @图片2 中同一个 20–25 岁东亚女性,严格保持同一张脸、圆润灵动脸型、黑发编辫、娇小身材比例、青绿色亚麻汉服、深色腰带、木簪 and 黑色布鞋。 核心道具 全程只有同一卷密封竹简。竹简在三个镜头中的位置、开合状态和人物持有关系必须连续稳定。 【0–5s|低角度全景,缓慢推轨】 雨后清晨的山门回廊石台。下方是云海山谷,雕花石栏、湿润石板、狭窄水渠、古松、浅色开花枝条、远处瓦顶殿宇、缓慢游走的山雾与持续变化的湿地倒影共同建立一个真实存在、持续呼吸的环境。 同一个白衣剑仙师姐与同一个青衣小师妹位于石案两侧。 白衣剑仙师姐把同一卷密封竹简轻轻放到两人之间的石案上,平静说道: “三年前,你落下一物,今日归还。” 环境保持克制运动:水渠持续流动,薄雾缓慢穿过回廊,树枝和衣摆响应同一晨风,雨后石面反射随摄影机推轨自然变化。 【5–10s|牛仔景中景】 同一个青衣小师妹缓慢伸手去取同一卷竹简,另一只手仍自然停在剑旁。 同一个白衣剑仙师姐保持完全平静的神情,补上一句: “我已替你批过。” 近处叶片自然掠过画面,形成真实前景视差;水渠持续流动,山雾在回廊之间缓慢游走。 背景始终只维持世界存在感,不主动制造新的剧情事件。 小师妹取到竹简后开始展开,为下一镜头保持连续动作。 【10–15s|特写转极近特写】 同一卷竹简完整展开。 里面并不是秘籍,而是同一个青衣小师妹三年前写下的一首旧情诗;纸面上密密写满工整、优雅的红色批注。 同一个青衣小师妹瞬间僵住,低声问: “你全看了?” 同一个白衣剑仙师姐平静回答: “还改了三处韵脚,第三句最好。” 极近特写捕捉小师妹耳尖明显泛红。 剑仙师姐依旧保持端庄、平静、毫无取笑意味的神情。 此时檐角一滴雨水自然落入同一条水渠,发出一声轻微而清楚的水响,作为最后的冷面节拍。 严格在 15.0 秒结束。 【执行硬约束】 必须使用 Seedance 2.0 Fast 必须生成完整 15 秒,不缩成 10 秒,不提前结束 16:9 横屏 严格三个镜头 原生同步普通话对白 普通话口型准确 人物身份、面部、发型、身体比例、服装全程稳定 同一卷竹简连续稳定,不复制、不消失、不更换 前中后景具有真实视差 环境持续活着,但绝不能抢戏 真丝、纸张、水流、山雾、头发、花枝、雨滴和光线物理真实 始终只出现两名可见角色 不生成画面字幕 不出现额外人物 【Negative】 blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, subtitles, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, hairstyle change, background shift, architecture mutation, lighting jump, glitching cuts, disappearing props, duplicated bamboo scroll, changing scroll design, extra characters, background crowd, environment stealing focus, random environmental gag, exaggerated comedy acting, slapstick reaction, overacting, modern elements, frozen background, static fog, static water, no parallax, abrupt camera jump, dialogue desync, lip-sync error
Generate this with Seedance 2 on VdoBloom.
Opens the image-to-video creator with this prompt and Seedance 2 pre-selected.