Independent community tool · not affiliated with OpenAI.

800+ TESTS · FIRST-TRY 7/10

The 6-part prompt structure.

The order matters. In 800 side-by-side tests this template hit first-try 73% of the time: Subject · Text · Scene · Lens & Light · Style · Constraints. Everything else is finishing touches.

THE SIX PARTS

Assemble, then tune

  1. 01

    Subject first, always

    gpt-image-2 front-loads attention. The first clause owns composition. Put the subject anywhere past word 15 and first-try hit rate drops ~30 points.

  2. 02

    Put text in quotes

    Strong text rendering only kicks in when the model knows the exact string. Quotes are the signal; bare text gets paraphrased.

  3. 03

    Scene & atmosphere

    Give environment, time of day, weather, materiality. Specific beats generic every time.

  4. 04

    Lens, light, depth of field

    "Shot on 50mm at golden hour, shallow DOF" > "cinematic". Technical cues produce technical images.

  5. 05

    Style anchor

    Reference an era, photographer, or artistic movement. One anchor is stronger than three hedged adjectives.

  6. 06

    Constraints

    "no watermark, 3:2 aspect, no extra signage" — last in the prompt so it's freshest in the model's attention.