GPT Image 2AI 提示词
Accidental Selfie Snapshot — Sora 2 Prompt
Create hyper-realistic 'accidental selfie' photos for AI personas with motion blur, uneven lighting, and a candid handheld feel.
提示词 · EN
ChatGPT, you've been with me for a while, and I want to see what you look like. Please generate a photo similar to an iPhone snapshot: no clear subject, no deliberate composition, just a very ordinary, even slightly failed snapshot. The photo should have slight motion blur, uneven lighting, slight overexposure, an awkward angle, and chaotic composition, presenting an overall 'too real' feeling of a casual snap, as if you accidentally pressed the shutter while taking your phone out of your pocket.
关于这个提示词
Create hyper-realistic 'accidental selfie' photos for AI personas with motion blur, uneven lighting, and a candid handheld feel. 它更适合作为 GPT Image 2 的概念艺术起点：先保留画面结构、主体关系和风格约束，再替换成你的品牌、人物或场景。
使用时建议先小幅修改主体、场景、镜头和色调，再生成多个版本对比构图与细节。这样页面内容对用户有实际帮助，也避免把模型名或标签机械堆在正文里。
如何使用这个提示词
- Copy the prompt and paste it into your preferred AI model interface.
- Choose a compatible image generation model like Sora 2 or DALL-E.
- Adjust variables like 'blur intensity' or 'overexposure level' to fine-tune the look.
- Generate the image and iterate on the prompt for different angles or lighting.
- Use the output as a unique, human-like avatar for AI assistants.
