X-ray illustration

Start with the right photo.

Use an unobstructed subject with a clear outline; a full-body view can help show the complete illustrative structure.

What to expect

Create a fictional X-ray style illustration. Internal structures are illustrative, not factual.

Keep an eye on

Recognizable identity, silhouette and important visible details. Compare the output to the original before using it.

Make it yours, step by step.

1. Adjust the recipe to describe your subject and preferred background.
2. Copy the complete recipe, then open ChatGPT.
3. Upload your photo in ChatGPT and paste the recipe. The short code alone is not an official command.
4. Inspect identity, text and proportions. Ask for a targeted correction if needed.

Choose the change deliberately.

Use this for an imagined internal-structure illustration, especially where a simple outline can frame a few legible components. The source photograph contains no scan data. Bones, wiring and hidden cavities are generated suggestions, even when they look convincing.

Review and refine the result

Start with sparse internal detail and check that the outer silhouette still identifies the subject. Reduce overlapping lines if the result becomes a luminous tangle. Never use generated structures to infer anatomy, damage or a product's construction.

A related direction, and why

/CUTAWAY — A cutaway exposes a selected section with opaque surfaces; it can explain a fictional mechanism more clearly than overlapping transparent layers.

These are editing suggestions, not additional test observations. Read the practical guide or use the before/after checklist.

Where this effect helps — and its limits.

Useful for fictional science-inspired artwork. This is not a factual or medical scan, and generated internal structures must not be interpreted anatomically.

Input advice and use cases are editorial guidance, not additional test results.

Notes from recorded tests.

These notes describe the named runs, which may use a different subject from the comparison above. They do not guarantee results on another input or a future model. See our testing method.