GPT Image 2AI-Prompt
Dramatic Manga Woman Reaching Out — Sora 2 Prompt
Generate a cinematic, single-panel monochrome manga page of an intimidating woman reaching toward the viewer with a Japanese speech bubble.
1 / 2
PROMPT · EN
创作一张黑白漫画页面插图，采用单一的竖长、略微倾斜的矩形分镜，背景为纯白。画面展示了 argcharacter name: 一位优雅的年轻女性，采用戏剧性的低角度透视，她俯身向观众探出，右手向前伸展，呈现出极端的透视缩短效果，手指张开，可见锋利的深色指甲。她留着 arghair color: 浅灰色 的齐肩凌乱短发，长刘海和散乱的发丝拂过脸庞，有着细长的大型漫画眼，睫毛刻画细腻，表情冷静却极具压迫感，双唇微张。她身穿深色高领制服，外罩一件披风或羽织，带有纹理网点阴影，右下边缘处有醒目的深色火焰状图案。使用精致的墨水线条、铅笔般的排线、漫画网点、高对比度的黑色填充、稀疏的尘埃颗粒以及干净的白色留白。包含 1 个对话气泡：右上角有一个竖长的椭圆形气泡，其中的日语竖排文字为 argspeech bubble text: 風林火山を殺し進む。保持构图为单色、电影感且强烈，如同印刷版的少年/青年漫画分镜，无色彩，无额外分镜。
Über diesen Prompt
Generate a cinematic, single-panel monochrome manga page of an intimidating woman reaching toward the viewer with a Japanese speech bubble. Use it as a Konzeptkunst 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 character name, hair color, and speech bubble text, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.
So verwendest du diesen Prompt
- Copy the entire prompt text above.
- Choose a compatible AI image model that supports manga or anime styles (e.g., Sora 2, Stable Diffusion with anime checkpoints).
- Paste the prompt and adjust the
{argument}variables for the character's name, hair color, or speech bubble text to customize the scene. - Generate the image and refine as needed by re-running or adjusting parameters like composition or ink style.
