editorial-poster

Produces the prompt, not the image. The deliverable is a text prompt the user pastes into an image model together with the photo as a reference image. One photo in, one prompt out; several photos in, several separate prompts out — the format forbids collages, so never merge photos into one prompt.

The template is tuned to fit a 2000-character input box (verified with GPT Image 2.5 Pro). It stays under that limit with roughly 70 characters spare for the user's text.

Step 1 — Collect input

• Photo(s) — attached to the message, or described in words if the user cannot attach.
• Text to include (optional) — a title, place, year, or short phrase the user wants on the poster. If nothing is given, use none.

Do not ask for anything else. Aspect ratio, split ratio, and style are fixed by the template; only change them if the user explicitly overrides.

Step 2 — Emit the prompt

Output the template below verbatim, replacing only <text or none>. Put each prompt in its own fenced code block. For multiple photos, label the blocks Photo 1, Photo 2, … in the order received.