GPT Image 2AI 프롬프트
3D Grayscale Dance Reference Grid — Sora 2 Prompt
Generate a studio-lit 3D grayscale dance reference chart in a 4x4 grid, complete with Korean labels and motion arrows—ideal for animators and illustrators.
프롬프트 · EN
单色灰度插图，3D 渲染角色，简洁的说明性参考图。 白色背景，漫画风格网格布局，技术图表美学。 [布局] 4×4 网格布局（共 16 个面板）。 每个面板由细黑边框分隔。 面板大小均匀，对齐一致。 每个单元格均清晰标注数字 1 至 16。 [角色] argsubject: 年轻女性舞者，运动型身材，马尾辫发型，身穿短款上衣、宽松长裤和运动鞋。 同一角色必须在所有面板中保持一致。 [面板结构 – 每个单元格] 左上角：粗体数字徽标 + arglanguage: 韩语 标题文本 中心：全身角色动作插图 左下角：arglanguage: 韩语 说明文本（3–4 行） 叠加层：指示运动流向的箭头 [箭头 / 动作指示器] 曲线箭头、直线箭头和圆形旋转指示器。 箭头应放置在角色周围，以清晰展示运动方向和流向。 [渲染风格] 高度精细的 3D 雕刻风格。 柔和的摄影棚灯光，带有微妙的阴影。 无颜色 —— 仅限灰度。 干净的线条，精致的成品，游戏概念艺术质量。 [负面提示词] 无背景场景。 无色调。 无额外角色。 无杂乱或复杂的背景。
프롬프트 소개
Generate a studio-lit 3D grayscale dance reference chart in a 4x4 grid, complete with Korean labels and motion arrows—ideal for animators and illustrators. Use it as a 컨셉 아트 starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
Start by replacing subject and language, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.
이 프롬프트 사용법
- Copy the full prompt from the text area above.
- Choose a text-to-image AI model that supports detailed prompts, such as Sora, DALL-E 3, or Midjourney.
- (Optional) Customize the
subjectargument to match your character (e.g., "male boxer") andlanguagefor labels (e.g., "English"). - Paste the prompt and generate. For best grid compliance, use a model with strong instruction-following.
- If needed, tweak negative prompts to suppress any color or background leakage.
