A shared industrial-grade prompt formula for GPT-Image-2, designed to help users generate high-quality images. It breaks down prompt writing into key components: subject, action, scene, style, composition, lighting, and details, providing examples for each.
- 主体:画面里是谁?如果是做海报,把内容用引号""括起来 - 动作:发生了什么?例如'正在赛博朋克街道上奔跑' -场景:故事发生在哪里?给它搭建一个舞台 - 风格:是拍出来的还是画出来的?比如'拍立得胶片风',日系赛博朋克' - 构图:给它打个光,比如'丁达尔光效','冷色调霓虹灯' -光线:导演视角的把控,例如'极度特写','超广角俯视' -细节:决定质感的咒语,例如'8k分辨率','工业级细节'
Click the copy button above to copy the prompt to your clipboard.
Open your preferred image generation tool like Midjourney, DALL-E, or Flux.
Paste the prompt into your tool, adjust settings if needed, and generate.
Try our AI Studio with this prompt or create something entirely new.