Prompts
EN

Image prompt Illustration & Characters Customizable

Nine-Frame Doodle Action Storyboard Collage

A 3x3 grid of one subject shot from low angles in varied crops, with childlike white doodle lines, dashes and bouncing words layered over bright, sunny color blocks. The result reads like a playful social meme sequence with a clear story.

Model
GPT Image 2
Type
2 images
Shared
18 Jul 2026
Likes on X
65
Make it yoursSwap in your own details: 2 blanks to fill

Person nameMain subject

Image prompt

2,786 characters

Develop a three-by-three continuous-action storyboard around any theme subject, on a base of real photographic quality, keeping the same core subject clearly recognizable across nine borderless cells while varying the action, viewing angle, near/far cropping, and interaction with small theme-derived props. The whole should feel like a light, improvised sampling of shots: most frames are shot from a low position looking up, with the ground or supporting edge appearing only briefly at the bottom of a few cells and the rest surrounded by an open, clean color field; the subject jumps between a large close crop, a full long shot, a half-body seated pose, and a strong-perspective close-up with something reaching toward the lens, so the nine cells form an alternating rhythm of big/small and tight/loose. Let the center cell carry the most intimate interaction moment, with a theme symbol reaching toward the lens forming the perspective focus; the corner cells build a circular echo through actions like glancing sideways, jumping, crouching, lifting, or leaning close to the face — human themes keep naturally playful expressions, non-human themes convey equivalent emotion through orientation, tilt, suspension, closeness to the lens, and the position of accessory elements. Overlay a hand-drawn graphic language with a childlike doodle feel: thick round-tipped white lines partially outline the silhouettes, leaving breathing room where the line has not yet closed; use curved action lines, dashed outlines, exclamation marks, short dashes, dots, ripples, and very few crooked handwritten words to create reactions and beat, with loose letterforms, uneven sizes, and a bouncing baseline, hugging the action but never covering the face or key identifying areas. Colors derive from the theme's semantics without fixing a specific hue: the background occupies most of the area, using a high-brightness, high-saturation, even and clean main color that conveys a sunny, open feeling; the subject is identified by two or three clearly divided light/dark color blocks, plus one warm, high-purity accent; white carries the main doodle information, and a few theme-related bright colors appear only in scattered dots and partial outlining. Keep highlights lively, the sunlight direction clear, shadows short and clean, skin or materials natural, the photographic layer's edges sharp, and the graphic layer flat-filled without volume with a slight hand-drawn wobble. Cells are separated only by neat seams, with no decorative frame; preserve large blocks of negative space, letting each cell show only one clear action and a little doodling, ultimately producing a youthful, sunny, mischievous social visual collage with a coherent sense of story. Theme: Gao Yuanyuan meme pack Ratio 9:10

How to use it

Start with your own subject, such as a person, animal or object, and keep the theme-related props in the center cell where the interaction happens. Keep the instruction for nine cells with alternating close and long shots, since that rhythm is what makes the grid work. It was shared as a GPT Image 2 prompt, so the three-by-three layout and doodle overlays may need a second try if the first grid comes out loose.

#Social Media#Character Design#Cute#Collage#Pop Art

Shared publicly on X on 18 Jul 2026. All credit for this prompt and its result goes to its creator. Is this yours? Ask for an update or removal.

2,786 characters

Questions about this prompt

Which AI model was this prompt made with?

It was shared as a GPT Image 2 prompt, and the image on this page is the result the creator got with it. Other models can read the same text, but the result will look different.

Can I change the details in this prompt?

Yes. It has 2 parts you can swap: person name, main subject. Open the prompt studio, fill them in and copy your version; anything you leave empty keeps the original wording.

Who made this prompt?

It was shared publicly on X by @xiaoxiaodong01 on 18 Jul 2026. The prompt and its result belong to them, and this page links to the original post.

More from @xiaoxiaodong01