9-Grid Visual Plan
Lock the light, color, and layout first
9-Grid Visual Plan
Lock the light, color, and layout first
Showcase
Description
Each of the nine images looks fine on its own, but together they look like they were made by nine different people—that’s the most common way a 9-grid layout fails. The problem is rarely that any single image looks bad. It’s that the nine images lack consistent lighting, color, and composition.【9-Grid Visual Plan】doesn’t just provide nine attractive images; it defines the relationships between them: first set one unifying theme, then assign each image a role (Image 1: hook; 2–4: development; Image 5: turning point; 6–8: payoff; Image 9: closing), and lock in the “three elements of consistency”—the same lighting (fixed direction and softness), the same color palette (with a 60/30/10 ratio and one specified color that cannot change across the nine images), and the same composition (consistent subject placement and scale). Each image includes a prompt you can copy directly for generation, specifying the subject, position, lighting, camera distance, and aspect ratio, along with the text-overlay position and character limit. Strict rules: no images are generated; no text may appear anywhere in the image (AI-generated Chinese text can be garbled and cannot be edited); no portraits of real celebrities; no existing cartoon, anime, game, or film characters; no imitation of a specific blogger or brand’s 9-grid style; and no promises of more likes or followers.
Recommended by
淡苍
Why we love this skill
Fixes nine-grid sets that look good individually but fall apart together by locking in roles, pacing, lighting, color, and composition.
Best for
Content creators and social media managers who need a cohesive, clearly sequenced 9-grid visual plan.
How to use this Skill
Provide your input
Provide the use case, core theme, must-have elements, and desired overall mood for the 9-grid layout.
Run the Skill
Organize the nine images by sequence and role, unify the lighting, color palette, and composition, and write image prompts with text-overlay placement suggestions.
Review your result
Get a complete 9-grid visual plan with a theme, roles for all nine images, consistency guidelines, and copy-ready image prompts; no images are generated, and prompts contain no text.
Related Skills
View all
ImageLong-Form Carousel Splitter
Long posts rarely get read to the end, so everyone wants to split them into slides—but most people split them the wrong way: dividing by word count leaves every slide feeling like a mini essay, the first slide gives away the conclusion and stops people from swiping, and the last slide burns goodwill with a forced follow prompt. 【Long-Form Carousel Splitter】doesn’t split by word count. It splits by "how many complete ideas there are": one idea per slide, with fewer slides preferred over more. So it may first tell you, "This piece is really only enough for 7 slides," instead of forcing it into nine. It then provides a slide-by-slide storyboard: what each slide covers, which sentences to include (with word counts), visual requirements, and the most common mistake to avoid on that slide. The first slide only needs to make people stop, with the minimum necessary information. The last slide only needs to leave them with one memorable line, not a summary. It also includes a practical swipeability check: read the first line of each slide together as a standalone passage. If it sounds like a complete sentence, the breakpoints are probably right. Hard rules: It does not generate images, put text in visuals, rewrite the original copy for you, include any existing IP characters, imitate the layout of a specific account, or promise completion rates.
Soft 9-Grid P186 xiaoxiaodong
Suitable for personal photo organization, independent publishing, exhibition exercises, and lifestyle visual creations. Even images with ordinary compositions, cluttered backgrounds, or small subjects can have their focus reestablished through reduction, rearrangement, cropping, and changes in scale—rather than simply applying a filter. The overall look combines a nine-grid matrix, flat color blocks, strong geometric divisions, a warm-white paper surface, generous negative space, and poetic editorial typography to create a refined visual effect. Whether the subject is a person, building, animal, plant, object, vehicle, or natural landscape, the nine units should maintain a consistent visual language and help viewers reconnect with the photo’s central theme through these geometric fragments, rather than presenting a set of mechanically duplicated thumbnails.
ImageOne Line to X Carousel
X multi-image posts now scroll horizontally: the first image appears in full, while only part of the second is visible, prompting readers to swipe left to see what follows. This skill helps you create a “pull-apart” continuous four-image sequence—four vertical images combine into one complete landscape image, and each swipe reveals another section to the right. The right edge of the first image becomes the hook that makes readers want to swipe. Three input types are supported: · One-line idea → text-to-image generation, creating a continuous four-section wide image from scratch · One image → crop it directly if possible; otherwise, use it as a reference to reconstruct four continuous scenes · 2–4 images → automatically arrange the narrative order and blend them into one stylistically consistent continuous wide image Workflow: First, you’ll review a four-panel narrative script (hook → reveal → twist → ending). Then the skill generates a 21:9 wide image and uses the companion free public image slicer to precisely cut it into 4 PNGs locally in your browser (your images are never uploaded to any server). Finally, it provides the posting order and tweet copy. The default output ratio is 4:5, with 9:16 and 1:1 also supported. No text is placed inside the images. Ideal for creators who want their X multi-image posts to inspire more “page-turning” curiosity, as well as teams creating product, story, educational, or travel content. Only want to slice an image without generating one? Send in a wide image directly, or open the slicer: https://youmind.com/a/dlJ7lVfZ9ZVqFi
Information
- Version
- v2
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
- Use cases
- Writing & contentImages & design
- What you get
- BriefPromptPlan