ASTORIE PROMPT LIBRARY

发现你的下一个灵感。

查看作品,发现提示词,创作你的版本。

探索提示词

100 条提示词

Seedance 2.0 Mini Prompt for Xianxia Comedy Duel

SoranSeedance 2.0
你咋一天这么多事,要打就打
prompt:

电影级写实质感,纯古风中国仙侠美学。

把真正庄严的高手挑战,与 “提前包装江湖名声” 的元喜剧进行碰撞。
吸收:
默片式反应节奏

英式一本正经逻辑
港式喜剧快速铺垫与回收
经典“三拍递进”结构
采用:

Arri Alexa 电影机质感

稳定清晰的面部微细节
细腻胶片颗粒
自然体积光
核心喜剧主线

整段只保留一条第一遍就能立即看懂的喜剧主线:

一个极其自信的敌方剑客,为了证明自己即将获得一场传奇胜利,专门带来一名江湖记事先生“客观记录”;结果真正的决斗还没开始,图一图二两名女子就发现——敌人连最后怎么写都已经提前花钱定好了。

角色功能原则

记事先生始终只承担一本正经的辅助角色

年长师父只负责最后一次补刀
参考与环境
将 @图片 1 和 @图片 2 严格作为人物身份锚点。

本轮新上传的所有背景与地点参考图,共同决定同一套环境 DNA。
正式构图前,无声整合能够互相兼容的:

真实地形

建筑语言

材质年代
植被

水体
天气
山雾
主光方向
反光关系
空气纵深
人物真实可行走路线
再重新规划成本轮独有、完整统一的新空间。
背景原则
背景中的以下元素始终持续自然鲜活,但在叙事上绝对中立:
自然风

水体

植被
云层

远处普通弟子
空间环境声
角色设定
角色 ID A|剑仙师姐
始终是同一个 @图片 1 剑仙师姐:
25–30 岁东亚女性

身材高挑纤细

椭圆脸

深色杏眼
黑色长发半挽,以白玉簪固定

始终穿同一套白色刺绣真丝汉服
银色腰封
玉佩
白色布靴
持唯一一柄银色长剑
角色 ID B|小师妹
始终是同一个 @图片 2 小师妹:
20–25 岁东亚女性
身形娇小
圆润灵动的脸

黑发编辫
始终穿同一套青绿色亚麻汉服

深色腰带
木簪
黑色布鞋
持唯一一柄深色钢剑
其他角色
敌方剑客
气势十足
极其自信
非常在意自己的江湖名声

江湖记事先生

唯一一名中年记事先生
手中只有毛笔和一卷没有任何可读文字的素色纸卷
始终一本正经、职业化、认真执行自己的“记录工作”
年长师父

始终沉稳
只在最后完成一次一本正经的补刀
分段结构
0–5s|全景或远景

一名气势十足的敌方剑客进入根据本轮参考图自然形成的开放区域,身旁跟着唯一一名中年江湖记事先生。
记事先生手中只有毛笔和一卷没有任何可读文字的素色纸卷。
敌人拔剑,非常郑重地宣布:

“今日请先生作证,免得有人输了不认。”

同一个小师妹看了一眼旁边的记事先生,平静评价:

“还挺正式。”

同一个白衣剑仙从头到尾保持冷静。

5–10s|中景或牛仔景

保持:

同样人物

同样服装

同样长剑

同一个记事先生

同一卷纸

完全一致的地理空间

真正决斗还没有开始,记事先生突然非常职业化地稍微靠近敌人,小声确认:

“公子,还是按‘十招大胜’记?”
全场绝对安静半拍。
敌人的身体当场僵住,立刻压低声音恼火反问:
“不是说打完再写吗?”
记事先生一本正经回答:
“定金付的是这个结局。”

同一个小师妹非常缓慢地把眼神从记事先生移到敌人脸上,难以置信地问:

“结局都买好了?”

同一个剑仙师姐什么都没说,只极轻微地抬起一侧眉毛,第一次产生真正兴趣。

整个背景从头到尾持续自然运行,却完全不参与笑点。

10–15s|特写或极近特写

同一个白衣剑仙非常认真地问记事先生:

“若他输了呢?”

同一个记事先生几乎零停顿回答:

“补银子,可改成‘虽败犹荣’。”

敌人瞬间恼羞成怒:

“我不会输!”

镜头焦点转移到两人数步后方自然存在的同一个年长师父。

师父从头到尾保持绝对一本正经,只淡淡说道:

“那先替他记一句:未开打,先改稿。”

同一个记事先生非常职业化地点一下头,立即抬起毛笔准备继续记录。

敌人这一次真正慌了,马上喊道:

“这句别记!”

记事先生停顿半拍,看着他认真评价:

“这句也挺好。”

极近特写:

同一个小师妹迅速转开脸,肩膀出现极轻微颤动,拼命忍住笑

同一个剑仙师姐则依旧保持真正高手的庄重表情,非常礼貌地向敌人做出一个继续比武的手势:

“现在能打了吗?”

敌人先看看记事先生,再看看自己手中的剑,最后又看看后方师父,突然意识到现在真正岌岌可危的已经不是自己的身体,而是自己苦心经营的江湖名声。

在他回答之前精准切黑。

喜剧节奏原则

整段必须符合清楚的“三拍递进”:

第一拍

敌人郑重带着记事先生上场,像要见证一场传奇胜利。
第二拍

记事先生职业化暴露:胜负文案已经提前付费定好。

第三拍

师父一本正经补刀,记事先生准备如实记下,敌人终于发现真正危险的是自己的名声。

表演原则

敌方剑客

不是丑角表演

不是故意滑稽
必须认真维护自己的排场和体面

喜剧感只能来自他越想保住名声,越暴露自己提前包装结果
记事先生

必须极端职业化
一本正经

逻辑清楚

完全不觉得自己荒唐

他的喜剧感来自“过度认真”
剑仙师姐
全程冷静
不嘲讽
不抢台词

后半段才因为事情的荒谬性,第一次表现出真正兴趣
小师妹
反应要自然
不夸张大笑
重点是“忍笑”
年长师父

必须绝对平静
那句“未开打,先改稿”要像陈述事实,而不是故意抖包袱
硬性要求
严格总时长 15 秒
16:9 横屏

三个连续清晰镜头
原生同步普通话对白
精准口型
明确的喜剧停顿

针对 Seedance 2.0 Mini 强化多参考人物身份连续性
人物面部全程稳定
发型全程稳定

服装全程稳定

长剑全程稳定

记事先生道具全程稳定
配角位置全程稳定
地理空间全程稳定
人物走位简单清楚
真丝衣料和头发物理效果真实
前景、中景、远景保持自然视差与真实空间环境声
不生成字幕
Negative
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
使用此提示词 ↗
Luxury Travel Fashion Portrait Prompt — output 1

Cinematic Wuxia Night Scene

MahaSeedance 2.0
Create a 30-second cinematic, ultra-realistic wuxia-style video set at night in an ancient Chinese village, with traditional wooden buildings, a stone-paved street, a small arched bridge, misty mountains in the background, and many glowing red lanterns hanging along the street. A beautiful young woman in an elegant flowing red traditional Chinese Hanfu walks calmly toward the camera, with long dark hair styled traditionally and a serious, confident expression. As she moves closer, the camera slowly pushes in and follows her naturally, capturing the lantern light, fabric movement, atmospheric mist, and realistic footsteps. Around the middle of the scene, she suddenly stops and confidently draws a glowing red magical sword, holding it horizontally in front of her while her expression becomes focused and powerful. The camera moves into a dramatic close-up of her face and sword, showing realistic skin texture, detailed hair, glowing reflections, and cinematic depth of field. Several mysterious black-clothed attackers appear around her, rushing toward her from different directions, creating a tense martial-arts atmosphere. She swiftly turns and performs powerful choreographed sword movements, blocking and striking the attackers with fast but believable movements while the glowing sword leaves subtle red light trails. The attackers are knocked down onto the stone street around her, while she remains standing confidently in the center with her sword raised, surrounded by red lanterns and light mist. End with a wide cinematic shot slowly pulling back to reveal the woman standing alone among the fallen attackers, ancient village buildings and mountains behind her, maintaining consistent character appearance, realistic motion, cinematic lighting, detailed textures, dramatic atmosphere, smooth camera movement, 16:9 aspect ratio, 30 seconds, no text, no watermark.
使用此提示词 ↗
Seaside Cafe Medallion Illustration — output 1
Noble Beige Autumn Editorial Art — output 1

Noble Beige Autumn Editorial Art

Saul GoodmanGPT Image 2.5
Create a premium 4:5 vertical noble-beige autumn editorial artwork for {argument name="country/location/subject" default="[COUNTRY / LOCATION / SUBJECT]"}.

TEXT-TO-IMAGE ONLY — generate the entire artwork creatively from {argument name="country/location/subject" default="[COUNTRY / LOCATION / SUBJECT]"} alone. No reference image required.

CORE CONCEPT
Create a small, intimate autumn moment surrounded by generous warm ivory negative space, as if a precious fragment of an autumn memory has been painted onto a luxury art-book page. Automatically determine the most fitting human figure, setting, foliage, atmosphere, and seasonal details associated with {argument name="country/location/subject" default="[COUNTRY / LOCATION / SUBJECT]"}.

SUBJECT & WARDROBE
Place one elegant human figure within the scene, wearing understated Italian quiet-luxury autumn clothing: soft cashmere, fine wool, brushed suede, or refined natural fabrics with relaxed tailoring.

Use a sophisticated tonal wardrobe of ivory, cream, oatmeal, sand, camel, cappuccino, taupe, and soft greige. Keep the styling effortless, timeless, minimal, and free of visible branding or logos.

ARTISTIC STYLE
Render the scene as delicate soft gouache and sophisticated dry-brush painting with subtle handmade texture, translucent tonal transitions, softly unfinished edges, and gentle color fading into the surrounding ivory paper.

Keep the human figure more refined and visually defined than the surrounding painterly environment, while maintaining a natural, understated appearance.

COLOR PALETTE
Build the entire artwork around noble beige and warm neutral tones: warm ivory, ecru, parchment, cashmere beige, oatmeal, sand, biscuit, light camel, mushroom, greige, and warm taupe.

Use only restrained accents of muted chocolate, dusty olive, or softly browned foliage. Avoid strong orange, red, yellow, or rustic autumn colors.

AUTUMN DETAILS
Add only a few delicate autumn leaves and understated foliage. Let several pale beige or muted ochre leaves subtly extend beyond the painted scene into the surrounding negative space.

LIGHTING
Use soft diffused creamy light with a slightly luminous quality, gentle contrast, and no harsh shadows. Emphasize tactile natural fabrics, quiet atmosphere, and sophisticated tonal harmony.

FINAL AESTHETIC
Luxury art-book page × noble beige autumn painting × soft gouache × Italian quiet luxury × cashmere-like tonal harmony × minimalist editorial composition.

The result should feel serene, intimate, expensive, tactile, collectible, and timeless.

Avoid photorealism, saturated autumn colors, rustic styling, excessive foliage, harsh contrast, heavy shadows, excessive accessories, busy backgrounds, collage layouts, hard frames, logos, text, watermarks, or artificial 3D rendering.

FORMAT: 4:5 vertical, generous warm-ivory negative space, refined minimalist composition.
使用此提示词 ↗
GPT Image 2.5 Eastern Aesthetic Autumn Poster — output 1
Broken Mirror Fashion Editorial Prompt — output 1

Broken Mirror Fashion Editorial Prompt

HeisenLegacyGPT Image 2
Ultra-realistic cinematic high-fashion editorial photograph of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a sharply defined sculpted jawline, subtle natural stubble, and realistic skin texture with visible pores.

Concept: His face is seen through several large, irregularly broken mirror fragments, each piece reflecting a slightly different angle of his face — one showing his intense eyes, another capturing his sharp side profile, another revealing his jawline and lips, and the central fragment showing his face staring directly into the camera. The fractured mirror pieces create a mysterious, artistic composition, with sharp geometric edges and realistic reflections.

Expression & Pose: Calm, mysterious and emotionally intense expression, deep captivating gaze directed toward the camera through the mirror fragments, head slightly tilted, with a subtle sense of introspection and hidden identity.

Outfit: Elegant black high-neck shirt beneath a tailored black blazer, minimal luxury styling, sophisticated and timeless.

Lighting: Dramatic low-key cinematic lighting, deep shadows, subtle cool blue highlights along the mirror edges, soft light illuminating his eyes and facial features, realistic reflections and delicate specular highlights on the broken glass.

Background: Dark minimalist interior with a charcoal-black background, subtle atmospheric haze, faint reflections and a sophisticated noir aesthetic.

Photography: Extreme attention to facial details, photorealistic skin texture, natural facial proportions, 85mm portrait lens, shallow depth of field, cinematic color grading, high contrast, ultra-detailed 8K HDR, luxury fashion magazine editorial, masterpiece composition.

Mood: Mysterious, introspective, dark, elegant, psychologically intriguing and cinematic.

Vertical 9:16 composition, close-up portrait, face occupying the central area, mirror fragments artistically arranged around the face, realistic glass reflections, perfectly coherent facial features within each reflection, professional editorial photography.

No text, no typography, no watermark, no extra faces, no distorted facial features, no artificial-looking skin, no cartoon effects.
使用此提示词 ↗
GPT Image 2 Premium Poster Design Prompt — output 1

GPT Image 2 Premium Poster Design Prompt

SairahGPT Image 2
Please create a separate, independently designed premium poster from each uploaded photo. Do not combine multiple photos into one composition; output one individual poster for each photo. Use a vertical 3:4 composition, with the upper and lower sections strictly divided 1:1, each occupying exactly 50% of the total height.

Upper Half:  
Preserve the original photograph, maintaining the subject’s identity, structure, pose, realistic texture, natural lighting, and original color atmosphere. Apply only subtle, sophisticated color grading to give it the visual quality of an art magazine, independent publication, or exhibition image. To adapt the image to the 3:4 format, the surrounding background may be naturally extended, but do not stretch, distort, or alter the subject.

Lower Half:  
Extract the most recognizable subject, silhouette, structure, pose, and narrative relationship from the photograph and reconstruct it in the style of Mid-century vernacular graphic illustration + schematic line drawing + two-color spot printing.

Do not completely trace or replicate the photograph. Instead, use diagrammatic abstraction to compress complex objects into a small number of clear geometric shapes, functional contours, and essential structural elements. The result should resemble an illustration from an old instruction manual, advertising card, technical label, or vernacular print: immediately recognizable, yet more direct, humorous, and symbolic than the realistic object itself.

Emphasize economy of line: if a structure can be explained with a single line, do not use unnecessary strokes. Use direct black pen outlines, rectangles, circles, diamonds, straight lines, and simple planes to describe the objects. People, animals, and objects may have slightly exaggerated proportions, while machines, buildings, and complex structures should be simplified into clear boxes, openings, panels, and silhouette relationships.

Use a flat, schematic diagrammatic perspective rather than realistic lighting or strictly accurate spatial depth. The visual language should exist somewhere between illustration and technical diagram, maintaining this distinctive character throughout the composition.

Reorganize the composition according to the most important narrative relationship in the original image. Maintain one clear primary subject, while using a small number of supporting objects, guide lines, directional relationships, or structural symbols to reinforce the story.

Pay close attention to visual hierarchy, geometric order, scale contrast, positive and negative space, and intentional whitespace. The image may feel slightly naïve, awkward, or handmade in a vernacular way, but it must never feel cluttered. Every visual element should appear to exist for the purpose of “explaining what is happening”, rather than simply serving as decoration.
使用此提示词 ↗
Rain and Fire Warrior Portrait Prompt — output 1

Rain and Fire Warrior Portrait Prompt

Prompt アトリエ|AI画像プロンプトGPT Image 2
主題:
雨炎の濡れた戦装

主体:
画面中央、雨と火の光の中で泥に濡れた戦士風女性の近接肖像が主役。

人物・表情:
小さな卵形の顔、濃茶の大きな瞳、細い眉、整った鼻、艶のある淡桃色の唇。表情は、顔を正面から少し下へ向け、視線を鋭くカメラへ合わせて唇を閉じた真剣な表情。黒に近い濡れた長髪が細い毛束で顔、首、肩へ張り付く。

服装・ポーズ:
泥で汚れた生成りの深いVネック革トップ、金属鋲と細い鎖、右肩の茶革ストラップ、右上腕の布巻き、青石の金色ネックレスと耳飾り。上体を前へ低く傾け、右肩を手前へ突き出してカメラへ迫る。

背景・光:
画面左から画面右の背景に、前景に濡れた石と水滴、背景左に青白い反射、右に橙色の炎と煙。画面右後方の硬い炎光と左の冷たい柔らかな補助光が濡れた輪郭を照らす。

構図・カメラ:
3:4の縦構図、顔より少し高い近接俯瞰カメラで頭頂から胸下までのクローズアップを収めるポートレート。人物を中央へ非常に大きく配置し、画面高の大部分を占める。髪、肩、腕を画面端で大胆に裁切し、両目と濡れた顔の水滴にピント、背景は軽くぼかす。

質感・スタイル:
フォトリアルな実写写真。自然な肌と髪、衣装の素材、周囲の小物を高精細にし、泥茶、炎の橙、冷たい青の映画色を保つ。

ネガティブ:
乾いた清潔な肌髪;炎と戦士装具省略
使用此提示词 ↗

Seedance 2.0 Cinematic Optical Zoom Video Prompt

灰度笔记Seedance 2.0
【全局设定】
古风写实电影镜头,东方古典生活叙事,雨后江南古镇:青石台阶、青砖黛瓦、木质廊檐、雕花木门、竹帘、湿润石板巷道。阴天柔和漫射光,低对比度,冷灰青与温暖木色融合,轻微35mm胶片颗粒,真实皮肤、木石与织物纹理,电影级浅景深,8K,16:9。

女主A:图1
女主B:图2

全片严格保持角色身份、空间位置、左右关系、行进方向、天气、光线、色调连续。

【核心摄影技法】
全片以“渐进式光学变焦”为唯一核心运镜。摄影机尽量固定机位,不依赖实体移动,通过缓慢连续的光学推近、拉远改变人物画面占比与空间关系。保持真实镜头压缩、景深变化和光学特征,禁止数字裁切。前景遮挡、浅景深、焦点转移辅助叙事,形成“远处发现→隔巷对视→空间压缩→情绪确认”。

【0-4s】
中景起幅,35mm,固定机位,视线高度。女主A沿青石台阶缓慢下行至巷口,停步转身抬头,看见远处廊檐下的女主B。镜头从较宽环境关系构图开始,仅缓慢光学推近,逐渐收紧至女主A中景,摄影机不移动。

古镇行人先后从左右前景横向经过,近距离形成自然虚化遮挡,女主A始终保持清晰;遮挡期间曝光、色温、光影稳定。变焦持续平滑克制,最终形成女主A与远处女主B隔巷对视。

【4-9s】
承接上一段,机位完全不变。女主B从画面右侧前景缓慢进入,靠近木质廊柱,与廊柱形成天然前景框;女主A位于左中部巷道深处。

缓慢连续光学变焦,女主A先保持清晰,随后画面逐渐收紧,女主B前景占比增大,女主A退入背景并柔和虚化。逐渐进入长焦端,通过真实空间压缩使古巷纵深被压缩,两人实际距离不变,但视觉距离明显拉近。焦点平滑由女主A转向女主B,最终女主B侧脸清晰、女主A虚化。摄影机不横移、不摇摄、不绕拍,曝光与色调连续。

【9-13s】
保持固定机位与长焦关系。女主B站在木质廊柱旁缓慢转身,看向女主A。仅进行一次极缓慢光学推近,从双人关系构图收紧至女主B中近景。画面左侧保留女主A局部虚化轮廓,形成窥视式前景框架。

女主B成为主要焦点,看向女主A,短暂停顿后轻声说:“好久不见。”露出极轻微笑意。竹帘被雨后微风吹动,屋檐水滴自然落下,湿润青石反射柔和天光。镜头稳定推进,在近距离情绪确认中结束。

【镜头控制】
核心必须是“光学变焦制造叙事距离变化”,而非摄影机移动。镜头语言依次完成:环境建立→发现女主A→缓慢收紧→女主B进入前景→长焦空间压缩→焦点转移→情绪确认。变焦速度缓慢连续,具有真实镜头惯性;保持自然人物比例、真实景深与稳定曝光,明确呈现光学变焦感,但无廉价数码放大感。

【连续性与负面约束】
严格遵循角色卡,禁止外貌、发型、服装漂移;保持空间地理关系、左右位置、运动方向、光线方向一致。禁止现代建筑、交通工具、路牌、现代物件、字幕、水印;禁止新增主要人物、人物重复、肢体异常、身份交换。禁止横移、环绕、突然摇镜、无人机运动、强手持抖动、数字变焦、数码裁切、透视异常、焦距跳变、景深瞬切、曝光闪烁、色温漂移、过度雾化、过度磨皮、AI塑料皮肤。
使用此提示词 ↗
Cute Anthropomorphic Sunflower Character Sheet — output 1

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗