Image prompt
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.
Copy directly into the target model and adjust for your input assets.
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.
Original source details are kept for attribution and review.
GitHub source：YouMind-OpenLab/gpt-image-2-prompts-search
This page is adapted from YouMind OpenLab GitHub prompt libraries. License: MIT。