图像提示词
A multi-step instruction for gpt-image-2 to transform a photo into a cute cartoon illustration with imaginative hand-drawn doodles while preserving the original subject's identity and lighting.
可直接复制后粘贴到对应模型，按素材输入情况微调。
Analyze the uploaded image, preserving the main subject, composition, and lighting of the original. Do not change the identity or facial structure of the protagonist. Add some {argument name="doodle elements" default="fun hand-drawn doodle elements"} that directly interact with the subject of the photo. These doodles can mimic, follow, or exaggerate existing shapes, poses, or movements—such as outlining poses, extending arms or legs, adding dynamic lines, or creating imaginative elements that 'interact' with the subject; be bold with the imagination.
Transform the entire image into a {argument name="illustration style" default="cute cartoon-style illustration"} with a lovable doodle aesthetic. Maintain the original scene and character details while applying a vivid, soft, and playful cartoon look.
保留原始来源，方便运营复核版权、作者和传播数据。
GitHub 来源：YouMind-OpenLab/gpt-image-2-prompts-search
本页根据 YouMind OpenLab GitHub 开源提示词库重新整理，许可证： MIT。