Prompt Node

The Prompt node holds the text you’ll send to a generation model. It’s the verbal half of the flow — the Image node is the visual half.

Writing a prompt

There’s no enforced format — different models prefer different styles. As a loose guide:

• Lead with the subject and context: A black-and-white film still of a fox sitting on a windowsill
• Then style and lighting: soft morning light, 35mm grain
• Then technical hints if needed: shallow depth of field

For prompt tips per model, see Image Models and Video Models.

Wildcards (bulk generation)

Prompt nodes support {option1|option2|option3} wildcards. The instant the prompt contains a wildcard, any connected Output node will auto-route the next generation through the bulk pipeline — there’s no toggle to flip.

A {watercolor|oil|charcoal} portrait of a {cat|fox|owl} in a {forest|library|cafe}

That single prompt expands to 27 variations. The Output node shows a small chip below the prompt with the count and total credit cost so you know what you’re committing to before clicking Generate. See the Bulk Generation tutorial for details.

Connecting downstream

The Prompt node’s right handle connects into the prompt target of Output and Video nodes.

You can connect a single Prompt node into multiple downstream nodes — useful for running the same prompt through different models side by side.