What's the best AI model to use with this prompt?

This prompt is optimized for Sora 2 but works well with other models like DALL-E 3 and Midjourney that support image-to-image and stylistic transformations.

Can I change the background color or remove the anonymity effect?

Yes! You can modify the prompt to specify a different background (e.g., 'pure white background') or request 'detailed faces' instead of the anonymized blocks.

What kind of input image works best?

A clear, front-facing selfie with two people in a standard composition yields the best results, ensuring the gestures and relative positions are accurately preserved.

MS Paint Selfie Doodle — AI Art Prompt | sora2hub

GPT Image 2AI 提示词

MS Paint Selfie Doodle — Sora 2 Prompt

Transform any selfie into a fun, minimalist MS Paint cartoon with bold outlines, flat colors, and anonymized faces for a charming, sketchy look.

提示词 · EN

使用提供的参考图像，在相同的自拍构图中重现前景中的两个人，保留他们的服装、发型轮廓、手势和相对位置，但将照片转换为粗糙的手绘数字涂鸦。使其看起来像简单的 MS Paint 卡通画，具有粗黑轮廓、纯色填充、刻意粗糙的比例、极简的细节以及纯浅灰色背景。移除水岸、天空和所有背景人物，仅保留 2 位主要主体。将面部区域处理为模糊的大型矩形块以实现匿名化。

关于这个提示词

Transform any selfie into a fun, minimalist MS Paint cartoon with bold outlines, flat colors, and anonymized faces for a charming, sketchy look. 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 full prompt from the page.
Select your preferred AI model (e.g., Sora 2, DALL-E 3).
Upload your reference selfie image.
Adjust the style keywords (e.g., 'rougher outlines' or 'brighter colors') if desired.
Generate and download your unique doodle!