Vertical Split Canvas Composition

A vertical 3:4 composition featuring a realistic photograph on the top half transitioning into a minimalist, hand-drawn paper collage on the bottom half.

Vertical Split Canvas Composition

Prompt

Copy and customize

Vertical 3:4 canvas split into two strictly equal horizontal halves: top 50% and bottom 50%. The upper half stays photographic; the lower half becomes the continued Second World. Together they must read as one scene. UPPER HALF Keep the photo faithful. Preserve the subject, pose, spatial relationships, color atmosphere, and natural light. Do not redesign, repaint, replace, or restage it. Only necessary proportional cropping is allowed. CONTINUITY (highest priority) Identify one source structure that naturally reaches the center split: a road, shoreline, water, reflection, branch, beam of light, piece of architecture, or body movement. This structure must cross the boundary and continue into the lower half. The Second World begins from the photograph itself, so the same scene passes through the seam and simply changes its physical rules. TRANSITION EDGE The center may use an irregular torn-paper edge, but the tear must follow the source structure, never act as decoration. Source elements may touch, follow, break through, or extend beyond edge. Never force the same tear shape onto every image. LOWER HALF Ivory paper with subtle fibers and abundant negative space. Continue the chosen structure downward from the exact point where it meets the split, then reinterpret it with restrained photo fragments, cut-paper forms, and minimal black hand-drawn lines. The lower world must stay visibly attached. Never isolate it as a separate portal, window, stage, platform, or floating vignette unless it clearly comes from the photo. SECOND WORLD LOGIC Ask: if this structure became touchable, usable, enterable, or changeable, what would it naturally become? Create one image-specific interaction. For example, water may stay attached while being pulled, a road may continue as a drawn path, or light may become something held. Do not repeat actions mechanically. FIGURES Add 0-3 tiny black line figures only when useful. They must physically interact with the continued structure. If the photo already contains strong human action, add none. Never use figures as decoration. CAPTION One short handwritten English caption (2-6 words) based on the action. Natural, light, slightly witty. Spell it correctly. No inspirational quotes and no fixed "Same..., different..." phrasing. STYLE Real photography above, warm paper below, minimal black line doodles, subtle handmade collage texture, independent-magazine mood. Bright, airy, restrained. It should feel as if the Second World was already hidden inside the photo and simply continued downward. NEGATIVE No detached lower-half illustration, no generic torn-paper template, no isolated portal, no unrelated vignette, no broken continuity, no dense illustration, no random decoration, no crowd, altered photo colors, no redesign of the upper image, no glossy 3D, no scrapbook clutter, no gibberish text, no watermark, no logo, no UI.

Best for

Creative visual storytellingMinimalist collage artMixed media conceptsArtistic layout design

Tips

Ensure the primary subject crosses the center boundary to maintain visual continuity between the photographic top and the illustrated bottom section.

Select a source structure like a road, shoreline, or light beam that naturally extends from the photograph into the lower paper-textured half.

How to use this GPT Image 2.5 prompt

1

Copy the ready-to-use GPT Image 2.5 prompt from this page.

2

Paste it into GoEnhance AI or another generator that supports GPT Image 2.5.

3

Click generate and get your image quickly. You can edit the prompt first if needed.

Copy the prompt, try it with GoEnhance AI or another tool that supports GPT Image 2.5, and generate your image in just a few simple steps.

Overview

Everything you need to master AI prompts

From quick copy-paste prompts to advanced techniques, build stunning visuals faster.

20000+ prompts
All major models
Updated Daily