Seedance 2.0
A senior swordswoman returns a sealed scroll to her junior on a mountain stone terrace — inside is her old love poem covered in corrections
Prompt
【Generation Mode and General Requirements】 Must use Seedance 2.0 Fast to generate a complete 15-second video, strictly, in horizontal 16:9, with three clear continuous shots and native synchronized Mandarin dialogue. Master-level cinematic realism, the look of an Arri Alexa cinema camera, with a restrained, poetic, deadpan xianxia comedy tone. The image is sharp and clear; volumetric morning light is naturally visible; performances are restrained; character movement is realistic yet cinematic; silk fabric, hair, paper, flowing water, mountain mist, and natural light respond to the physics of the world convincingly. Use a “reference-image-driven living world system”: all reference images jointly define the location and visual world, including terrain logic, architectural language, spatial scale, the age and materials of structures, vegetation and ecology, water flow, weather conditions, cloud and mist movement, key-light direction, reflective surfaces, overall color palette, and atmospheric depth. Before formal generation, first silently complete one round of environmental planning, then reorganize the shared environmental DNA into a completely new, unified, physically plausible space. The background must feel vibrant and distinctive, and remain naturally active throughout, but should only establish the presence of the environment: it must not trigger gags, change the characters’ goals, or draw focus away from the story. 【Characters and Key Prop】 Character ID A|Senior Sister, Sword Immortal Always the same East Asian woman, 25–30 years old, from @图片1. Strictly maintain the same face, oval face shape, naturally fair skin, dark almond-shaped eyes, long black hair half-up, white jade hairpin, tall, slender proportions, white embroidered silk hanfu, layered translucent wide sleeves, silver waist sash, jade pendant, and white cloth boots. Character ID B|Junior Sister Always the same East Asian woman, 20–25 years old, from @图片2. Strictly maintain the same face, rounded, lively features, braided black hair, petite proportions, teal-green linen hanfu, dark belt, wooden hairpin, and black cloth shoes. Key Prop There is only one sealed bamboo scroll throughout the video. Its position, open or closed state, and who is holding it must remain continuous and consistent across all three shots. 【0–5s|Low-Angle Wide Shot, Slow Dolly In】 A stone platform in the covered corridor by the mountain gate on a rainy morning. Below lies a valley of clouds; carved stone railings, wet flagstones, a narrow water channel, ancient pines, pale flowering branches, distant halls with tiled roofs, slowly drifting mountain mist, and ever-changing reflections on the wet ground together create a real, breathing environment. The same white-clad Sword Immortal senior sister and the same green-clad junior sister stand on opposite sides of a stone table. The white-clad Sword Immortal senior sister gently places the same sealed bamboo scroll on the stone table between them and says calmly: “Three years ago, you left something behind. Today, I’m returning it.” The environment moves with restraint: water keeps flowing through the channel, thin mist drifts slowly through the corridor, branches and hems respond to the same morning breeze, and reflections on the rain-wet stone change naturally as the camera dollies in. 【5–10s|Cowboy Shot, Medium】 The same green-clad junior sister slowly reaches for the same bamboo scroll, while her other hand rests naturally by her sword. The same white-clad Sword Immortal senior sister remains completely composed and adds: “I’ve already proofread it for you.” Nearby leaves naturally pass across the frame, creating realistic foreground parallax; water continues flowing through the channel, and mountain mist drifts slowly between the corridors. The background only sustains the sense of a living world and never triggers a new story event. After taking the scroll, the junior sister begins to unroll it, continuing the action seamlessly into the next shot. 【10–15s|Close-Up Transitioning to Extreme Close-Up】 The same bamboo scroll is fully unrolled. Inside is not a cultivation manual, but an old love poem written by the same green-clad junior sister three years ago; the paper is densely covered with neat, elegant red annotations. The same green-clad junior sister instantly freezes and asks quietly: “You read all of it?” The same white-clad Sword Immortal senior sister calmly replies: “And fixed three rhymes. The third line is the best.” An extreme close-up captures the junior sister’s ear tips turning visibly red. The Sword Immortal senior sister remains composed and dignified, with no hint of mockery in her expression. At that moment, a raindrop naturally falls from the eaves into the same water channel, making a soft but distinct splash as the final deadpan beat. End strictly at 15.0 seconds. 【Hard Execution Constraints】 Must use Seedance 2.0 Fast Must generate the full 15 seconds; do not shorten to 10 seconds or end early Horizontal 16:9 Exactly three shots Native synchronized Mandarin dialogue Accurate Mandarin lip sync Character identity, face, hairstyle, body proportions, and clothing remain consistent throughout The same bamboo scroll remains continuous and consistent: no duplication, disappearance, or replacement Realistic parallax between foreground, midground, and background The environment stays alive but must never steal the scene Silk, paper, flowing water, mountain mist, hair, flowering branches, raindrops, and lighting must behave realistically Only two visible characters at all times No on-screen subtitles No additional characters 【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
【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、玉佩和白色布靴。 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、木簪和黑色布鞋。 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 and 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
- Needs your photo: attach an image to the request — the prompt works with it.
The rights to this prompt belong to its author @Soranlan. You are responsible for any commercial use — promoting AI tools, aggregators or Telegram bots: mozgi.io accepts no liability. Details →











