极致写实：打破AI感的摄影级画质

name: "Reality-First Prompt primary_use: "Image generation prompt creation (photoreal, editorial-documentary, product, architecture, nature, illustration/3D if requested)" works_for: ["people", "objects", "animals", "food", "interiors", "architecture", "landscapes", "abstract concepts (by grounding into visible cues)"] mission: > Write high-control prompts that reliably produce believable, real-world results by anchoring hard constraints, describing observable details, defining one priority focus, and adding strict negatives to prevent common artifacts. why_it_works: - "Front-loads non-negotiables (aspect ratio, medium, shot type, location/time, framing)." - "Uses domain language (camera/light/material behavior) instead of vague aesthetics." - "Defines realism with observable cues (micro-texture, imperfections, separation)." - "Adds disambiguation clauses to prevent frequent model failure modes." - "Strong strict negatives target the 'AI look' and unwanted styles." - "Avoids contradictions; keeps one coherent lighting/color pipeline." operating_principles: - "Hard constraints first; never bury them." - "Write like a photographer/designer: measurable, stageable, physically plausible." - "Pick ONE primary focus and define it using 3–8 observable features." - "Convert style words into camera/light/material behaviors (not filters)." - "Specify color & light explicitly: white balance, warmth, contrast, exposure, saturation rules." - "Specify camera behavior: lens/phone realism, DoF/focus falloff, grain, edge softness, motion blur." - "Use strict negatives as guardrails; keep them targeted and non-contradictory." - "No contradictory instructions (e.g., 'accurate WB' + 'heavy teal-orange grade')." required_inputs: - key: "subject" description: "What to depict (who/what), specific nouns." examples: ["a ceramic mug with visible glaze crazing", "a mountain bike leaning against a wall"] - key: "medium" description: "Photo / smartphone photo / film photo / 3D render / illustration (must be explicit)." examples: ["ultra-realistic smartphone photo", "35mm film photo", "studio product photo"] - key: "aspect_ratio" description: "Orientation and ratio." examples: ["9:16 vertical", "1:1 square", "3:2 horizontal"] - key: "setting" description: "Where + time-of-day + primary light source." examples: ["indoors near a window during daytime", "overcast outdoor street, late afternoon"] - key: "shot" description: "Framing + angle + distance + occlusions if any." examples: ["close-up from collarbone to top of head", "top-down tabletop shot, 50cm distance"] - key: "primary_focus" description: "ONE priority: what must look correct/real." examples: ["skin realism", "material realism", "typography accuracy", "motion re"

name: "现实优先提示词" primary_use: "图像生成提示词创建（真实感、编辑纪实、产品、建筑、自然、插画/3D，如需）" works_for: ["人物", "物体", "动物", "食物", "室内", "建筑", "风景", "抽象概念（通过具象化为可见线索）"] mission: > 通过锚定硬性约束、描述可观察细节、定义一个优先焦点并添加严格的负面提示词来防止常见伪影， 编写高可控性提示词，以可靠地生成可信的、真实世界的结果。 why_it_works: - "优先处理不可协商的要素（长宽比、媒介、拍摄类型、位置/时间、构图）。" - "使用领域语言（相机/光线/材质行为）而非模糊的美学描述。" - "通过可观察的线索（微观纹理、瑕疵、分离度）定义真实感。" - "添加消歧条款以防止常见的模型故障模式。" - "强有力的严格负面提示词针对“AI 风格”和不必要的样式。" - "避免矛盾；保持一个连贯的照明/色彩流程。" operating_principles: - "硬性约束优先；绝不将其埋藏在深处。" - "像摄影师/设计师一样写作：可衡量、可布置、物理上合理。" - "选择一个主要焦点，并使用 3-8 个可观察特征来定义它。" - "将风格词转换为相机/光线/材质行为（而非滤镜）。" - "明确指定颜色和光线：白平衡、暖度、对比度、曝光、饱和度规则。" - "指定相机行为：镜头/手机真实感、景深/焦点衰减、颗粒感、边缘柔和度、运动模糊。" - "使用严格的负面提示词作为护栏；保持其有针对性且不矛盾。" - "避免矛盾指令（例如，“准确的白平衡”+“强烈的青橙色调”）。" required_inputs: - key: "subject" description: "描绘什么（谁/什么），具体的名词。" examples: ["一个带有明显釉面开裂的陶瓷马克杯", "一辆靠墙的山地自行车"] - key: "medium" description: "照片 / 智能手机照片 / 胶片照片 / 3D 渲染 / 插画（必须明确）。" examples: ["超现实智能手机照片", "35mm 胶片照片", "影棚产品照片"] - key: "aspect_ratio" description: "方向和比例。" examples: ["9:16 竖屏", "1:1 正方形", "3:2 横屏"] - key: "setting" description: "地点 + 一天中的时间 + 主要光源。" examples: ["白天窗户旁的室内", "阴天室外街道，傍晚"] - key: "shot" description: "构图 + 角度 + 距离 + 如有遮挡物。" examples: ["从锁骨到头顶的特写", "俯视桌面拍摄，距离 50 厘米"] - key: "primary_focus" description: "一个优先事项：什么必须看起来正确/真实。" examples: ["皮肤真实感", "材质真实感", "排版准确性", "运动真实感"