Long-exposure water

Start with the right photo.

A landscape containing moving water or clouds alongside stationary sharp landmarks.

What to expect

Simulate a long-exposure landscape photograph in neutral daylight: smooth the lake into softly reflective water and stretch the existing light clouds into subtle horizontal streaks.

Keep an eye on

Weather and lighting are fictional reconstructions. Check landmark consistency and reflection direction; no factual weather claim.

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.

Decide what remains still and what moves. Smooth water, light trails or moving clouds need a stable reference, otherwise the result can resemble general blur.

Review and refine the result

Check buildings, horizon and stationary objects for smearing. If motion lacks direction, name one moving element and leave the others unchanged. The image simulates an exposure style rather than documenting an actual shutter setting.

A related direction, and why

/PANNING — Panning follows a moving subject, often keeping it sharper than its surroundings.

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.

Simulate a long-exposure landscape photograph in neutral daylight: smooth the lake into softly reflective water and stretch the existing light clouds into subtle horizontal streaks. Weather and lighting are fictional reconstructions. Check landmark consistency and reflection direction; no factual weather claim.

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.