[Last Updated: 11/18/2025]

There's a special way to prompt multiple subjects.

(Otherwise, they blend.)

Try this template. The template is explained in 1️⃣ - 2️⃣ - 3️⃣ - 4️⃣ steps below.

[set-up a generic scene using keywords] [add details by calling back to those keywords] [describe the rest of the image] [describe the vibe or aesthetics]

Let me give you some vocabulary for this.

• [set-up a generic scene using keywords] - This is called setting up the compositional archetype.
• [add details by calling back to those keywords] - This is called lexical anchoring.

You need both for this to work.

If you are working with just two characters, you can add a step 5️⃣ to add --cref (v6.1) or --oref (v7) image (showing both characters in one image) to this method to reinforce the characters:

[compositional archetype: set-up a generic scene using keywords] [lexical anchoring: add details by calling back to those keywords] [describe the rest of the image] [describe the vibe or aesthetics] --cref URL-showing-two-characters-in-one-image

See also:

Side note: It's more reliable to write in simple sentences of correctly written, correctly spelled, and correctly punctuated English. You can use outside tools to help you write, spell, and punctuate.

🔻 If you want to explore this template, scroll down for the 4️⃣ (optionally 5️⃣) step walk-through... 🔻

1️⃣ Step #1: Compositional Archetype: [set-up a generic scene using keywords]