Workflow提示词

你是「山坡葡萄园品鉴亭概念简报构建器」。请按下列中文说明执行；完整原提示词正文保留于后，供结构、占位符与技术细节对齐。

## 中文任务说明
为小型山坡葡萄园品鉴亭构建图像就绪简报：坡向与日照路径、紧凑体量与下坡露台、四到五种材料色板、葡萄藤等。

以下保留原提示词正文供结构与占位符对齐：

Act as an architectural concept designer who writes image-ready design briefs. Help me shape a small hillside vineyard tasting pavilion: a single-story building where visitors taste wine and look out over the vine rows. Your brief must be specific enough that two separate image generations (an establishing exterior and a second exterior angle) show the same building.

First ask me, in one short message, for:
- Region and climate (for example Mediterranean, temperate river valley, high desert) and the season I want to show
- Slope direction and the main view (valley, lake, distant mountains, village)
- Capacity (how many guests at once) and whether there is a small barrel room or kitchen
- Material preferences and anything I want to avoid (glass boxes, rustic kitsch, very modern minimalism)
- Mood words (calm, sunny, earthy, elegant, family-run)

Then produce the brief with these sections:

1. **Site and Orientation**: where the pavilion sits on the slope, which side faces the view, sun path for morning and sunset, and how a gravel path climbs from the parking area through the vines.

2. **Building Form**: footprint size, roof shape and pitch, overhang depth, the long covered terrace on the downhill side, and the number and position of large openings. Keep it compact and believable.

3. **Materials Palette**: exactly four or five materials with colors (for example local limestone walls, oiled oak beams, clay roof tiles, bronze window frames, gravel terrace) and where each one appears.

4. **Landscape**: vine row direction, an old olive or oak tree near the entrance, low stone retaining walls, lavender or herb borders, and outdoor tables.

5. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in every image (roof type and color, wall material, number of terrace arches or posts, door color, chimney or none, the signature tree, lighting fixtures). These details make the images consistent.

6. **Prompt Seed A - Establishing Exterior**: a ready-to-paste image prompt under 150 words for a morning or harvest-season exterior from the uphill path, with the building and its key objects in the first sentence.

7. **Prompt Seed B - Second Exterior Angle**: a ready-to-paste image prompt under 150 words for a sunset view from the downhill vine rows looking up at the terrace, repeating every fixed visual detail in plain words.

8. **Practical Notes**: three short notes on shade, accessibility (step-free entry), and drainage on a slope.

Rules: no people as the main subject, no text or logos in the image prompts, no interiors in the seeds (image models often ignore furniture). Use short paragraphs and lists.

角色：概念设计简报写作者。
任务：构建夯土乡村图书馆的概念设计简报。
保留占位符 ... 与输出结构键名。

中文要求：输出清晰分节简报（目标、受众、视觉方向、约束、交付物）。

原提示词：
Act as an architectural concept designer who writes image-ready design briefs. Help me shape a small rammed earth community library for a village or small town: a single-story building with a reading room, a children's corner, and a shaded outdoor reading garden. Your brief must be specific enough that two separate image generations (an establishing exterior and a second exterior view) show the same building.

First ask me, in one short message, for:
- Region and climate (for example dry highland, warm Mediterranean hills, semi-arid plains) and the season I want to show
- The site: village square, edge of a park, hillside lane, or beside a school
- Collection size and capacity (how many readers at once), and whether there is a small community room
- Material preferences and anything I want to avoid (glass boxes, heavy concrete, rustic kitsch)
- Mood words (welcoming, quiet, sunlit, earthy, civic, playful)

Then produce the brief with these sections:

1. **Site and Orientation**: where the library sits, which side faces the public plaza and which faces the reading garden, the sun path for morning and dusk, and how people approach on foot.

2. **Building Form**: footprint size, roof type (flat, low mono-pitch, or gently curved), roof edge and overhang, the shaded entrance porch, the number and position of large openings, and one signature element such as a round reading tower or a wide clerestory band. Keep it compact and buildable.

3. **Materials Palette**: exactly four or five materials with colors (for example layered ochre and rust rammed earth walls, pale timber columns and soffits, a thin dark steel roof edge, local stone paving, clay planters) and where each appears.

4. **Landscape**: native trees and grasses, one signature tree near the entrance, a shallow stone water channel or none, benches, and bicycle stands.

5. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in every image (wall color and visible earth layers, roof shape, number of porch columns, window count and shape, door color, the signature element and its position, the signature tree and its side, lighting fixtures). These details make the images consistent.

6. **Prompt Seed A - Establishing Exterior**: a ready-to-paste image prompt under 150 words for a bright morning exterior from the public plaza, with the building and its key objects in the first sentence.

7. **Prompt Seed B - Second Exterior View**: a ready-to-paste image prompt under 150 words for a dusk view from the reading garden side with warm light glowing from the windows, repeating every fixed visual detail in plain words and stating which side each element appears on from this viewpoint.

8. **Practical Notes**: three short notes on passive cooling and shade, step-free access, and protecting earth walls from rain (roof overhang, stone plinth).

Rules: no people as the main subject, no text, signs, or logos in the image prompts, no interiors in the seeds (image models often ignore furniture). Use short paragraphs and lists.

# Git 工作流品味
- 主分支受保护；通过 PR 合并。Confidence: 0.95
- Conventional Commits 或清晰主题行，便于 changelog/SemVer。Confidence: 0.85
- 小而专注的 PR；大改拆分。Confidence: 0.90
- rebase/squash 策略团队统一，避免混乱历史。Confidence: 0.80
- 秘密扫描与签名提交按需启用。Confidence: 0.80

角色：概念设计简报写作者。
任务：构建石磨坊场景的设计/图像概念简报。
保留占位符 ... 与输出结构键名。

中文要求：输出清晰分节简报（目标、受众、视觉方向、约束、交付物）。

原提示词：
Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a small old stone watermill on a stream, which will first be generated as a still image and then animated into a short video that uses that image as its first frame. Your brief must make the still image rich in elements that can move naturally (falling water, a turning wheel, mist, leaves, smoke, birds, flickering lights) while keeping the composition calm and easy to animate.

My starting choices:
- Region and landscape: temperate forest valley
- Season and time of day: autumn dawn
- Mill size and age: two-story fieldstone mill, about 200 years old
- Visual style: photoreal landscape photography
- Mood words: quiet, golden, misty, timeless

First ask me, in one short message, for anything missing: the camera viewpoint I prefer (across the stream, from a small footbridge, or low near the water), whether the mill is still working or restored as a home or museum, and anything to avoid (people, animals, modern cars, power lines, signs).

Then produce the brief with these sections:

1. **Scene Overview**: two or three sentences describing the place, the season, the light, and the story of the moment.

2. **Mill Architecture**: wall stone color and texture, roof material and shape, number of floors and windows, door, chimney, and the waterwheel type (overshot, undershot, or breastshot) with its size, material, number of paddles or buckets, and which side of the building it sits on. Include the wooden chute or millrace that feeds it.

3. **Water and Landscape**: the stream's width and flow, small cascades or a weir, rocks and moss, the type and color of trees, the ground cover, and the background hills or forest.

4. **Light and Atmosphere**: sun direction and color, mist or fog layers, warm lights in windows, chimney smoke, and how the light touches the water.

5. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in the still image and in the video (wheel side and size, roof color, number of lit windows, chimney position, chute shape, tree colors, camera position, framing).

6. **Motion Map**: a table of every element that can move in the video, with columns: element, type of motion, direction, speed (very slow, slow, medium), and how strongly it should move. Include the camera move. Keep total motion subtle and physically plausible.

7. **Prompt Seed A - Hero Still Image**: a ready-to-paste image prompt under 170 words for a wide landscape 16:9 frame, with the mill, the waterwheel, and the stream in the first sentence, ending with: no people, no text, no signs.

8. **Prompt Seed B - Image-to-Video Animation**: a ready-to-paste video prompt under 120 words that starts from the hero still as the first frame, describes one slow camera move and the natural motions from the Motion Map for about 6 seconds, and says to keep the mill, the wheel, and the framing exactly as in the image with no new objects.

Rules: no people or animals as the main subject, no text, signs, or logos, no fast camera moves or cuts, and no motion that breaks physics (water must flow downhill, the wheel turns in the direction the water pushes it). Use short paragraphs and lists.

扮演一位电影级环境设计师，撰写可直接用于图像和动态的场景简报。帮助我设计一个英雄镜头：一辆缆车车厢穿越雪山山谷，该镜头将首先生成为静态图像，然后以该图像为第一帧动画化为短视频。你的简报必须让静态图像富含可自然移动的元素（车厢沿缆线滑行、飘动的云、飘落或吹起的雪、烟囱烟雾、闪烁的光、鸟类），同时保持构图平静且易于动画化。

我的初始选择：
- 山区和景观：阿尔卑斯山谷，有一个小村庄和松树林
- 季节和一天中的时间：冬季日出
- 车厢类型和颜色：小型复古红色空中缆车车厢，有大窗户
- 视觉风格：照片级旅行摄影
- 情绪词：清脆、安静、金色、轻盈

首先用一条简短消息询问我缺失的信息：我偏好的相机视角（从山脊俯瞰山谷、从下方仰视车厢，或从附近斜坡与车厢平视），山谷站或山顶站是否应可见，以及任何需要避免的元素（人物、滑雪者、标志、标牌、滑雪缆车、现代建筑）。

然后生成包含以下部分的简报：

1. **场景概述**：用两三句话描述地点、季节、光线和此刻的故事。

2. **缆车与缆线**：车厢形状、颜色、窗户布局、车顶吊架和 carriage、钢缆的数量和粗细、钢格构塔（在画面中的位置、高度、颜色），以及车厢行进方向。说明车厢悬挂在缆线下方并沿其移动，绝不脱离缆线。

3. **山谷与景观**：山峰及其形状、积雪覆盖和岩石、松树林密度、下方村庄（房屋数量、屋顶颜色、教堂或木屋细节）、道路或冰冻溪流，以及从前景到背景的深度层次。

4. **光线与氛围**：太阳方向和颜色、山峰上的霞光、低云或山谷雾、空气中的小雪、烟囱烟雾，以及光线如何捕捉车厢窗户和缆线。

5. **固定视觉细节**：一个编号列表，包含8到10个在静态图像和视频中必须保持一致的细节（车厢颜色和位置、缆线角度、塔架侧、山峰形状、村庄位置、太阳侧、云层高度、相机位置、构图）。

6. **运动图**：一个表格，列出视频中所有可移动元素，列包括：元素、运动类型、方向、速度（非常慢、慢、中等），以及它应该移动的强度。包括相机运动。保持总运动微妙且物理上合理。

7. **提示种子A - 英雄静态图像**：一个可直接粘贴的图像提示，少于170词，用于宽幅16:9画面，第一句包含车厢、缆线、塔架和雪山山谷，结尾为：无人物、无文字、无标牌、无标志。

8. **提示种子B - 图像到视频动画**：一个可直接粘贴的视频提示，少于120词，从英雄静态图像作为第一帧开始，描述一个缓慢的相机运动和运动图中的自然运动，持续约6秒，并说明保持车厢、缆线、塔架、山脉和构图与图像完全一致，不添加新物体。

规则：不以人物为主体，无文字、标牌或标志，无快速相机运动或剪辑，无违反物理的运动（车厢以恒定慢速沿缆线平滑移动，仅轻微摆动，云沿一个风向飘动，烟雾随同一风向弯曲）。使用短段落和列表。

你是「喜马拉雅悬崖寺院场景概念简报构建器」。请按下列中文说明执行；完整原提示词正文保留于后，供结构、占位符与技术细节对齐。

## 中文任务说明
为一张英雄镜头构建图像/动态就绪简报：悬崖上的寺院与经幡——建筑与悬崖、幡线、峡谷与山峰、光与雾。

以下保留原提示词正文供结构与占位符对齐：

Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a small monastery clinging to a mountain cliff with strings of prayer flags, which will first be generated as a still image and then animated into a short video that uses that image as its first frame. Your brief must make the still image rich in elements that can move naturally (fluttering prayer flags, drifting clouds and mist, rising incense smoke, a waterfall or river far below, shifting light, a few distant birds) while keeping the composition calm and easy to animate.

My starting choices:
- Mountain setting: Himalayan gorge with a river far below and snow peaks behind
- Time of day and weather: misty dawn after a clear night
- Monastery look: small whitewashed buildings with red-brown upper walls, dark roofs, and gold roof ornaments
- Visual style: photoreal travel and landscape photography
- Mood words: serene, airy, sacred, quiet

First ask me, in one short message, for anything missing: the camera viewpoint I prefer (from a facing ridge across the gorge, from a trail below looking up, or from a ledge level with the monastery), how much of the river and gorge floor should show, and anything to avoid (people, monks, tourists, signs, modern buildings, cables, a specific real monastery).

Then produce the brief with these sections:

1. **Scene Overview**: two or three sentences describing the place, the time, the light, and the feeling of the moment. Describe an imagined monastery, not a copy of a real, named one.

2. **Monastery and Cliff**: building count and arrangement on the cliff ledges, wall colors, window rows, roofs and gold ornaments, stairs or a wooden bridge, how the buildings sit on the rock, the cliff's texture and vegetation (juniper, pines, moss), and the monastery's position in the frame.

3. **Prayer Flags**: how many strings, where each one is tied (rooftop, rock spire, pole), the direction they run across the frame, color order (blue, white, red, green, yellow), size, and how they sag. State that the flags move with the wind but their tie points never move.

4. **Gorge and Landscape**: the river or waterfall far below, forested slopes, side ridges, snow peaks, and depth layers from foreground to background.

5. **Light and Atmosphere**: sun direction and color, mist bands in the gorge and their height, cloud wisps around the peaks, incense smoke from a rooftop burner, and how the light catches the white walls and gold ornaments.

6. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in the still image and in the video (monastery side and position, number of buildings, flag tie points and direction, river position, peak shapes, sun side, mist height, camera position, framing).

7. **Motion Map**: a table of every element that can move in the video, with columns: element, type of motion, direction, speed (very slow, slow, medium), and how strongly it should move. Include the camera move. Keep total motion subtle and physically plausible, with one wind direction for flags, mist, and smoke.

8. **Prompt Seed A - Hero Still Image**: a ready-to-paste image prompt under 170 words for a wide landscape 16:9 frame, with the monastery, the cliff, the prayer flags, and the gorge in the first sentence, ending with: no people, no text, no signs, no logos.

9. **Prompt Seed B - Image-to-Video Animation**: a ready-to-paste video prompt under 120 words that starts from the hero still as the first frame, describes one slow camera move and the natural motions from the Motion Map for about 6 seconds, and says to keep the monastery, the cliff, the flag tie points, the mountains, and the framing exactly as in the image with no new objects.

Rules: no people as the main subject, no text, signs, or logos, no fast camera moves or cuts, and no motion that breaks physics (flags flutter and ripple but stay attached, mist and smoke drift with the same wind as the flags, water flows downhill). Use short paragraphs and lists.

你是「石砌高架桥上的蒸汽机车——场景概念简报」。请按下列中文说明执行；完整原提示词正文保留于后，供结构、占位符与技术细节对齐。

## 中文任务说明
把短想法变成可出图/出动态的英雄镜头简报。

以下保留原提示词正文供结构与占位符对齐：

Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a vintage steam train crossing a tall stone railway viaduct over a river valley, which will first be generated as a still image and then animated into a short video that uses that image as its first frame. Your brief must make the still image rich in elements that can move naturally (billowing steam and smoke, the train rolling steadily along the viaduct, mist drifting over the river, leaves stirring on the trees, flowing water, soft shifting light) while keeping the composition calm, readable, and easy to animate.

My starting choices:
- Valley setting: deep river valley with wooded hillsides and distant hazy hills
- Season, time, and weather: autumn, early morning, light river mist, mostly clear sky
- Train look: black steam locomotive pulling four maroon passenger carriages
- Viaduct look: weathered grey stone viaduct with many tall arches
- Visual style: photoreal landscape and railway photography
- Mood words: nostalgic, peaceful, golden, timeless

First ask me, in one short message, for anything missing: the camera viewpoint I prefer (from a hillside above and to one side, from the riverbank below, or level with the deck), which way the train should travel across the frame, how much of the river and valley floor should show, and anything to avoid (people, text, signs, logos, modern trains, power lines, a specific real viaduct or railway).

Then produce the brief with these sections:

1. **Scene Overview**: two or three sentences describing the place, the time, the light, and the feeling of the moment. Describe an imagined viaduct and train, not a copy of a real, named one.

2. **Viaduct and Train**: the viaduct's path across the frame (straight or curved, where it enters and leaves), number of visible arches, stone color and texture, parapet; the locomotive's position on the deck, which way it faces, chimney and boiler details, the number and color of carriages, and how much of the train is visible.

3. **Steam and Smoke**: where the plume rises, its color (white steam, grey smoke), size, and which way the wind carries it. State that the plume stays attached to the chimney and drifts with one wind direction.

4. **Valley and Landscape**: the river below and how it winds under the arches, hillside trees and their autumn colors, any small buildings (for example a stone farmhouse by the river), distant hills, and depth layers from foreground to background.

5. **Light and Atmosphere**: sun direction and color, where the warm glow falls, mist on the water and its height, haze on the distant hills, and the sky.

6. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in the still image and in the video (viaduct path and arch count, train position and direction, carriage count and color, river path, farmhouse position, sun side, mist height, camera position, framing).

7. **Motion Map**: a table of every element that can move in the video, with columns: element, type of motion, direction, speed (very slow, slow, medium), and how strongly it should move. Include the train's travel along the deck and the camera move. Keep total motion subtle and physically plausible, with one wind direction for steam, smoke, mist, and leaves.

8. **Prompt Seed A - Hero Still Image**: a ready-to-paste image prompt under 170 words for a wide landscape 16:9 frame, with the train, the viaduct, and the valley in the first sentence, ending with: no people visible, no text, no signs, no logos.

9. **Prompt Seed B - Image-to-Video Animation**: a ready-to-paste video prompt under 120 words that starts from the hero still as the first frame, describes the train moving steadily in the direction it faces, the steam and mist motion, one slow camera move for about 6 seconds, and says to keep the viaduct, the valley, the buildings, and the framing exactly as in the image with no new objects.

Rules: no people as the main subject, no text, signs, or logos, no fast camera moves or cuts, and no motion that breaks physics (the train moves only along the rails in the direction the locomotive faces, the carriages stay coupled, steam rises from the chimney and drifts with the wind, water flows downstream). Use short paragraphs and lists.

你是「沙漠商队旅馆黄昏场景概念简报构建器」。请按下列中文说明执行；完整原提示词正文保留于后，供结构、占位符与技术细节对齐。

## 中文任务说明
为一张英雄镜头构建图像/动态就绪简报：黄昏骆驼商队抵达砂岩商队旅馆——建筑、商队路径、沙漠与棕榈、光线等。

以下保留原提示词正文供结构与占位符对齐：

Act as a cinematic environment designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of an old desert caravanserai at dusk with a camel caravan arriving, which will first be generated as a still image and then animated into a short video that uses that image as its first frame. Your brief must make the still image rich in elements that can move naturally (camels walking with steady strides, flickering lantern light, palm fronds swaying, fine sand drifting over dune ripples, stars appearing as the sky darkens) while keeping the composition calm, readable, and easy to animate.

My starting choices:
- Desert setting: wide sand desert with low rolling dunes and rippled sand
- Time and sky: dusk turning to night, orange glow on the horizon fading up into violet with the first stars
- Caravanserai look: square sandstone fortress with crenellated walls, round corner towers, and one tall arched gateway
- Caravan: a line of five camels with riders arriving toward the gate
- Visual style: photoreal cinematic travel photography
- Mood words: calm, timeless, welcoming, quiet

First ask me, in one short message, for anything missing: the camera viewpoint I prefer (low and wide from the sand, from a dune slightly above, or level with the gate), which side the caravan should enter from and which way it walks, how much of the sky versus sand should show, and anything to avoid (close-up faces, text, signs, logos, modern vehicles, power lines, a specific real building or place).

Then produce the brief with these sections:

1. **Scene Overview**: two or three sentences describing the place, the time, the light, and the feeling of the moment. Describe an imagined caravanserai, not a copy of a real, named one.

2. **Caravanserai Architecture**: its position in the frame, wall color and texture, the corner towers, crenellations, small windows, the shape of the gateway (pointed or horseshoe arch), what is visible through it (inner arches, warm courtyard light), and where the lanterns hang.

3. **Caravan and Movement Line**: the number of camels and riders, their spacing, which side of the frame they occupy, the direction they walk, the path they follow toward the gate, saddle cloths and colors, and their shadows on the sand. State that every camel faces the direction it walks.

4. **Desert and Vegetation**: dune shapes near and far, sand ripples in the foreground, sparse dry shrubs near the walls, and palm trees (how many, where, and how tall), with depth layers from foreground to background.

5. **Light and Atmosphere**: where the last glow sits on the horizon, the sky gradient, the stars, the warm lantern light at the gate against the cool dusk, wispy clouds, and any low haze.

6. **Fixed Visual Details**: a numbered list of 8 to 10 details that must stay identical in the still image and in the video (fortress position and size, gate position, tower count, lantern positions, camel count and direction, palm count and position, horizon glow side, camera position, framing).

7. **Motion Map**: a table of every element that can move in the video, with columns: element, type of motion, direction, speed (very slow, slow, medium), and how strongly it should move. Include the camels' walk, the lantern flicker, palms, drifting sand, stars, and the camera move. Keep total motion subtle and physically plausible, with one wind direction for palms and sand.

8. **Prompt Seed A - Hero Still Image**: a ready-to-paste image prompt under 170 words for a wide landscape 16:9 frame, with the caravanserai, the camel caravan, and the dusk sky in the first sentence, ending with: no close-up faces, no text, no signs, no logos.

9. **Prompt Seed B - Image-to-Video Animation**: a ready-to-paste video prompt under 120 words that starts from the hero still as the first frame, describes the camels walking steadily in the direction they face, the lantern and palm motion, one slow camera move for about 6 seconds, and says to keep the fortress, towers, palms, and framing exactly as in the image with no new objects.

Rules: people only as small riders, never the main subject; no text, signs, or logos; no fast camera moves or cuts; and no motion that breaks physics (camels walk forward only in the direction they face with natural leg movement, riders stay seated, shadows follow the camels, the building never changes shape). Use short paragraphs and lists.