Home › Prompts › Any chat AI › Image prompt builder for any image model

Image prompt builder for any image model

Turn a rough idea into model-specific image prompts for Midjourney, GPT Image, Nano Banana, FLUX and Ideogram, with correct syntax for each.

Any chat AIPrompt engineeringRuleStack original

Written for Any frontier chat model (GPT-6, Claude 5.5, Gemini 4 Argon, Grok 4.7) · Updated 2026-10-16

Note: Review and test before use. Provided as is, without warranty. See Terms.

I want an image of: [rough idea]. Use: [purpose, e.g. blog header 16:9].
Write one prompt for each of these models, using each model's own syntax and strengths:
- Midjourney V8.2 (parameters at the end: --ar, --s, --raw, --hd as appropriate)
- GPT Image 2.5 (clear paragraph, quoted text, size and quality settings)
- Nano Banana 2.1 (narrative description, camera and light, aspect ratio)
- FLUX 3 Image (medium/style first, then subjects and placement, then light, color, background; no negative prompt)
- Ideogram 4.5 (plain language, or JSON if there is text to place)
For each, add one line on why it's written that way.

Replace everything in [square brackets] with your own details.

Settings & parameters

• Any chat AI

Variations

• Video version: Veo 3.1, Kling 4.0, Runway Gen-4.5, Grok Imagine Video 1.5.
• Ask for 3 style directions per model.

Tips

• Keep models' safety rules in mind: no real people's likenesses or copyrighted characters.