일관된 AI 디자인 브리프 생성기

Act as an architectural concept brief builder for a floating lakeside teahouse. You translate a vague mood into fixed, visual design details that can be reused across multiple image prompts so the same building stays recognizable from different angles and times of day. You are concrete about materials, dimensions, and what must not change.

About the teahouse I imagine:
- Setting: ${setting:a quiet mountain lake in early autumn, forested shores, soft fog}
- Scale and use: ${scale:intimate, seats 6 to 8 on floor cushions, ceremonial tea for small groups}
- Structure vibe: ${vibe:Japanese-inspired cedar, not a theme-park copy; quiet, handmade, slightly weathered}
- Must include: ${must:hipped cedar shingle roof, sliding paper shoji, narrow engawa deck, two stone lanterns on the dock, a small tied wooden boat}
- Must avoid: ${avoid:neon signs, glass curtain walls, people in the frame, readable text}
- Mood words: ${mood:hushed, misty, warm wood, contemplative}
- Preferred views to generate later: ${views:morning approach from the shore path; dusk interior looking out across the water}

Please do the following:
1. Write a 1-paragraph architecture and setting concept for the floating teahouse.
2. Define a color and material palette (wood tones, paper, water, fog, metal accents).
3. List 10 to 14 fixed design details that must stay identical across every image (roof form and bay count, railing, lantern shapes, dock layout, boat position, mountain silhouette cues, etc.).
4. Produce Image Prompt A: photoreal exterior, misty morning, shore/path approach view, 16:9, embedding every fixed detail in the first half of the prompt.
5. Produce Image Prompt B: photoreal interior at lantern dusk looking out to the lake, 16:9, restating every fixed exterior-visible detail so the building still matches without a reference image.
6. Add a short consistency checklist a human can use when comparing A and B.
7. Add practical notes (what fal flux ultra tends to drop if buried late; keep key objects in the first sentence; under ~200 words per image prompt).

Rules:
- No people, no readable text, no logos.
- Prefer specific measurable details over adjectives alone.
- If I left a detail vague, choose one clear option and mark it as your choice.
- Output in clear Markdown sections.

호숫가 찻집 건축 콘셉트 브리프 작성자 역할을 해주세요. 모호한 분위기를 여러 이미지 프롬프트에서 재사용할 수 있는 고정된 시각적 디자인 세부사항으로 변환하여, 동일한 건물이 다른 각도와 시간대에서도 동일하게 인식되도록 합니다.

내가 구상하는 공간:
- 배경: [초가을의 조용한 산속 호수, 숲으로 둘러싸인 기슭, 옅은 안개]
- 규모 및 용도: [아담함, 방석에 6~8명 수용, 소규모 그룹 다도용]
- 구조물 분위기: [삼나무 소재, 손때 탄 묵직하고 원목 그대로의 느낌]
- 필수 포함: [삼나무 기와 지붕, 미세기 창호문, 좁은 툇마루, 선착장 석등 2개, 묶여 있는 작은 목선]
- 제외 요소: [네온사인, 통유리 벽, 사람, 읽을 수 있는 텍스트]
- 무드 키워드: [조용한, 안개 낀, 따뜻한 목재, 사색적인]
- 생성할 뷰: [이른 아침 기슭 산책로 접근 뷰; 해질녘 실내에서 호수를 바라보는 뷰]

다음 작업을 수행해 주세요:
1. 공간의 건축 및 콘셉트 1문단 작성.
2. 색상 및 소재 팔레트 정의 (목재 톤, 종이, 물, 안개, 금속 포인트).
3. 모든 이미지에서 동일하게 유지되어야 할 고정 디자인 세부사항 10~14개 목록화.
4. 이미지 프롬프트 A 생성: 실사 외관, 안개 낀 아침, 16:9 비율.
5. 이미지 프롬프트 B 생성: 해질녘 실내 뷰, 16:9 비율.
6. A와 B를 비교할 수 있는 일관성 체크리스트 작성.
7. 이미지 생성 모델 입력 시 유의사항 작성.

• 활용건축뿐만 아니라 3D 팝업스토어, 브랜드 시각 디자인 시스템 기획에도 응용 가능합니다.
• 활용생성된 프롬프트를 Midjourney나 Flux에 그대로 복사해서 일관된 연출을 시도해 보세요.

출처 · prompts.chat · Floating Teahouse Concept Design Brief Builder — 원문은 출처에 게시된 그대로이며, 권리는 원작자에게 있습니다.

텍스트 결과

Gemini로 실행한 결과입니다. 입력 항목에는 국내 환경의 예시값을 적용했습니다(AI 생성 — 사실 확인 필요).

Act as an architectural concept brief builder for a floating lakeside teahouse. You translate a vague mood into fixed, visual design details that can be reused across multiple image prompts so the same building stays recognizable from different angles and times of day. You are concrete about materials, dimensions, and what must not change.

About the teahouse I imagine:
- Setting: a quiet mountain lake in Gangwon province in early autumn, pine and maple forested shores, soft morning fog
- Scale and use: intimate single-story pavilion, seats 6 to 8 on floor cushions, ceremonial tea for small groups
- Structure vibe: Hanok-inspired weathered dark cedar, refined minimalist traditional architecture, slightly weathered
- Must include: dark slate tile roof (giwa), sliding paper shoji/hanji, narrow wooden deck (maru), two stone lanterns (seokdeung) on the dock, a small tied wooden rowboat
- Must avoid: neon signs, glass curtain walls, people in the frame, readable text
- Mood words: hushed, misty, warm amber wood, contemplative, deep solitude
- Preferred views to generate later: morning approach from the shore path; dusk interior looking out across the water

Please do the following:
1. Write a 1-paragraph architecture and setting concept for the floating teahouse.
2. Define a color and material palette (wood tones, paper, water, fog, metal accents).
3. List 10 to 14 fixed design details that must stay identical across every image (roof form and bay count, railing, lantern shapes, dock layout, boat position, mountain silhouette cues, etc.).
4. Produce Image Prompt A: photoreal exterior, misty morning, shore/path approach view, 16:9, embedding every fixed detail in the first half of the prompt.
5. Produce Image Prompt B: photoreal interior at lantern dusk looking out to the lake, 16:9, restating every fixed exterior-visible detail so the building still matches without a reference image.
6. Add a short consistency checklist a human can use when comparing A and B.
7. Add practical notes (what fal flux ultra tends to drop if buried late; keep key objects in the first sentence; under ~200 words per image prompt).

Rules:
- No people, no readable text, no logos.
- Prefer specific measurable details over adjectives alone.
- If I left a detail vague, choose one clear option and mark it as your choice.
- Output in clear Markdown sections.

개선안

원문과 같은 언어로 보완한 프롬프트입니다. 점수는 명확성 · 구체성 · 출력 형식 · 재사용성 기준의 AI 평가입니다.

You are an expert Architectural Concept Brief Builder and AI Image Prompt Engineer specializing in FLUX Ultra. Your task is to translate a vague architectural mood into a set of fixed, precise visual details to maintain strict visual consistency across multiple generated image prompts.

### Inputs:
- Setting: [a quiet mountain lake in early autumn, forested shores, soft fog]
- Scale & Use: [intimate, seats 6 to 8 on floor cushions, ceremonial tea for small groups]
- Architectural Vibe: [Japanese-inspired cedar, authentic craftsmanship, slightly weathered]
- Required Features: [hipped cedar shingle roof, sliding paper shoji, narrow engawa deck, two stone lanterns on dock, small tied wooden boat]
- Exclusions: [neon signs, modern glass curtain walls, human figures, readable text, logos]
- Mood & Tone: [hushed, misty, warm wood lighting, contemplative]
- Target Views: [Prompt A: morning shore path approach; Prompt B: dusk interior looking out to lake]

### Instructions:
Please generate the brief in clear Markdown sections following this structure:

1. **Architectural Concept**: Write a 1-paragraph synthesis of the structure and context.
2. **Material & Color Palette**: Specify precise material finishes, wood tones, paper translucency, metal accents, and environmental hues.
3. **Fixed Design Identifiers**: List 10 to 14 immutable design details (roof pitch, bay count, timber dimensions, lantern style, boat placement) required for identical cross-prompt rendering.
4. **Image Prompt A (Exterior Morning)**: 16:9 photoreal exterior view. Place all key fixed details in the first sentence to suit FLUX Ultra attention weighting. Keep under 200 words.
5. **Image Prompt B (Interior Dusk)**: 16:9 photoreal interior view looking outward. Explicitly restate exterior-visible details so the building matches Prompt A seamlessly. Keep under 200 words.
6. **Consistency Checklist**: Provide a concise 5-point manual audit checklist for evaluating rendered images.
7. **Model Execution Notes**: Outline specific FLUX Ultra prompt behaviors, word count limits, and key object positioning tips.

### Strict Constraints:
- Absolutely no people, text, or modern architectural elements.
- Replace subjective adjectives with specific, concrete visual descriptions.
- If any detail is left open, select one definitive option and mark it clearly as your choice.