LLM Test Prompts

All prompts › Apps

PixelForge Studio: an image editor in one HTML file

Appsvery hardbuild testPrompt in Englishsingle-file HTMLapplong output

What it tests: A real application rather than a demo: layer compositing with per-layer canvases, many tools, filters on the active layer only, undo/redo and export.

Prompt length: 3,752 characters, roughly 940 tokens (estimate).

Build a fully functional, standalone image editor inspired by Photoshop. The final output must be a single self-contained HTML file that runs locally in the browser without any backend. Do not use Adobe branding, logos, names, or …

The source has no licence that allows copying, so only a short excerpt is shown here. The full prompt is one click away at the source.

How to grade it

Opens from disk with no backend; new project with a custom size; image import onto a new, fitted layer; layers can be added, deleted, renamed, reordered, hidden, merged, and get opacity and blend modes; brush, eraser, selections, crop, text, shapes, eyedropper, fill, zoom and pan all work; filters affect only the active layer; undo and redo; PNG and JPEG export; no Adobe branding.

Scorecard tick what the model got right: 0/9

Runs in your browser; nothing is saved or sent.

0/9

Where models usually fail

One canvas pretending to have layers; filters applied to the whole image; undo that only covers some tools; output cut off because the spec is long.

Running it

Run it one-shot and judge the first answer. Open the result exactly as delivered (double-click for HTML). Give the model a large output budget: long specs get cut off on small context settings.

Source

Author
Arnie (GitHub @Arnie936)
From
Arnie936 / llm-prompting-tests
Exact file or post
https://github.com/Arnie936/llm-prompting-tests/blob/03445cf074852ec5535ece9d123bdff442e63ef5/README.md#14-photoshop-klon
Licence
No license file (all rights reserved)
How we use it
Excerpt only: open the full prompt at the source

Testing a local model? Check first whether it fits your hardware with Can I run this LLM?

More in Apps