GPT Image 2AI Prompt

Iron Mountain Shoulder Strike: Q-Style Anime Action Prompt

Create a hilarious Q-style anime action scene featuring a fierce red-haired girl executing a devastating shoulder strike on a terrified boy, complete with explosive manga effects.

Iron Mountain Shoulder Strike: Q-Style Anime Action Prompt
PROMPT · EN
一幅充满喜剧 Q 版风格的动态动漫动作插画,展示了一个娇小但凶猛的女孩对一个受惊男孩的侧面施展强力的中国武术肩部撞击——铁山靠。女孩是画面焦点:argcharacter name: 红发武术少女,长长的鲜艳 arghair color: 绯红色 头发向后剧烈飘动,有着锐利的红眼和坚定愤怒的表情。她正以极快的速度从右向左冲刺,身体低伏紧凑,一侧肩膀和上背部撞向男孩的躯干,一只拳头后拉,另一只手臂收拢以保持平衡,一只膝盖向前弯曲,另一条腿向后拖曳。她穿着一件短款红色中式旗袍,带有金色花卉刺绣、金色滚边、侧开叉和黑色平底鞋。男孩是一个黑发 Q 版少年,穿着深蓝色中式功夫装,配有金色滚边和黑色鞋子,因冲击而向后退缩,张着嘴露出震惊的表情,双眼翻白,带有汗滴,身体向左后方飞出。强调碰撞的瞬间,在他身侧产生明亮的爆炸冲击效果、飞溅的碎片、火花以及横跨整个背景的强烈速度线扭曲。在女孩拖曳的脚部附近添加尘云和地面划痕,以展现爆炸性的前进动能。采用漫画风格的构图,运用夸张的动作、透视缩短以及从右下到左上的对角线冲刺。画面中集成了 3 个大型日语拟声词文字元素:右侧一个垂直的标注文字“鉄山靠!!”,旁边一个较小的垂直注释“てつざんこう”,以及左下方一个巨大的撞击拟声词“ドガッ!!”。整体氛围快速、滑稽、具有攻击性和强烈的冲击感,采用精致的现代动漫渲染,具有光泽的头发高光、清晰的线条艺术以及戏剧性的红、白、黑对比。

About this prompt

Create a hilarious Q-style anime action scene featuring a fierce red-haired girl executing a devastating shoulder strike on a terrified boy, complete with explosive manga effects. Use it as a Concept Art 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 and hair color, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.

How to use this prompt

  1. Copy the prompt and paste it into your preferred AI image generator (e.g., Midjourney, DALL-E, or Stable Diffusion).
  2. Choose an anime-optimized model or style setting for best results.
  3. Customize the optional variables like character name and hair color to match your vision.
  4. Generate and iterate, adjusting the prompt if needed to fine-tune the action intensity and comic effects.

FAQ

More from GPT Image 2

Browse all

Create faster with Sora2Hub prompts.

Use curated prompt pages as searchable entry points, then jump straight into generation with the right model context.

Explore prompts