图像创意简报

把创意需求拆成用途、主体、场景、构图、光线、色彩、材质和必须避免的元素。输出一条完整图像生成提示词、三条有实质区别的变体和尺寸建议。涉及准确文字时建议后期排版，不承诺模型准确生成文字。

输入材料：
{{context}}

目标与约束：
{{constraints}}

只依据输入回答。缺少关键信息时明确标记未知，必要时先提问。输出应可直接用于当前任务。

Break the request into use, subject, setting, composition, lighting, color, materials and exclusions. Provide one complete image prompt, three meaningfully distinct variants and an aspect-ratio recommendation. Where exact text matters, suggest separate typesetting rather than promising accurate generated lettering.

Input material:
{{context}}

Goal and constraints:
{{constraints}}

Base the response on the input. Mark missing information as unknown and ask essential questions when needed. Make the output directly usable for this task.