<div align="center">

Let the flowers, windows, roads, and wind inside a photograph become a visual poem you can truly read

<a href="README.md">简体中文</a> · <strong>English</strong> · <a href="README.ja.md">日本語</a> · <a href="README.ko.md">한국어</a> · <a href="README.ar.md">العربية</a>

</div>

Sample gallery

16:9 landscape left–right samples

| sample-05 | sample-06 | |---|---| | | | | | |

3:4 portrait top–bottom samples

| sample-09 | sample-10 | |---|---| | | | | | |

The eight works above comprise four 16:9 landscape left–right samples and four 3:4 portrait top–bottom samples. Every work was generated independently by Panel 107 from its own original brief; no artwork from another numbered Panel is reused. The samples use intelligent English copy.

<!-- xxd-human-intro:start -->

Best-fit situations and problems solved

Some photographic feelings cannot be explained by copy alone, and should not be buried under decorative miniatures. Panel 107 keeps the photograph on one side and turns the other into a genuinely readable visual sentence: when the sentence reaches a flower, window, road, or action, a hand-drawn image from the photograph replaces that word. Remove either text or image and the sentence is incomplete.

Best for

• One caption cannot hold what the photograph feels like: let source-derived subjects, actions, and motifs perform the missing words.
• You do not want “a complete headline plus a few pictures”: image words sit in the words' actual positions, so the reader must combine text and image.
• You want fresh, light image-and-type design without childish collage: use luminous soft blocks, modern hand-drawn editorial illustration, and generous whitespace.
• Flexible delivery in one consistent style: create top-bottom, left-right, design-only, multi-ratio, four-device wallpaper, or directory-batch outputs.

What it solves for you

• It turns “pictures beside copy” into “pictures that are words,” resolving the split between wording and imagery.
• It derives a short sentence from the current photograph's emotion, action, relationship, place, or memory, then chooses the words best suited to visualisation.
• A defined reading path prevents sticker walls, card grids, and chaotic collage while preserving an airy editorial finish.

Quick start

Use XXD Panel 107 on this image and recommend the most suitable composition and size first.

<!-- xxd-human-intro:end -->

<!-- xxd-panel-benefit:start -->

Quick fit check

| What you need to know | What this style gives you | |---|---| | What you get | A poster in which photograph and image-word poem are exactly paired, and only text plus image words reconstruct the full sentence | | Recognisable signature | Printed fragments and hand-drawn image words alternate along one reading path; the images sit on lively blocks instead of illustrating copy from the side | | How it respects the source | The reality region keeps identity, structure, pose, light, and colour; every visual word is distilled directly from that same photograph | | Where it works | Art posters, independent-publication covers, exhibition imagery, social content, design-only art, and four-device wallpaper sets | <!-- xxd-panel-benefit:end -->

Usage tips

• Start with one clear photo: choose a source whose subject, action, and relationships are easy to recognize before choosing the delivery format.
• Join the parameters in one sentence: say “top-bottom / left-right / design-only + 16:9 / 3:4 / phone wallpaper”; you can also name desktop, tablet, or smartwatch sizes.
• State what must stay: identify the people, objects, actions, relationships, and copy to preserve, while leaving room for the style to design the layout.
• Choose a text mode: let the model write from the image, lock exact wording with --text exact --copy, or remove text completely with --text none.
• Clarify reality and design regions: for top-bottom or left-right, say which region keeps the photograph and which region is redesigned; for design-only and wallpapers, say that the whole canvas is redesigned.
• Test one image before batching: confirm mode, ratio, text, and language on one source, then reuse the settings for a folder; change one variable per iteration.

Get started

git clone https://github.com/nevertoday/xxd-panel-107.git
mkdir -p ~/.codex/skills
ln -s "$(pwd)/xxd-panel-107" ~/.codex/skills/xxd-panel-107

You can also install it directly with npx skills:

npx skills add https://github.com/nevertoday/xxd-panel-107 

…