Enhance Prompt

Enhance text prompts for text-to-image models

Try Enhance Prompt in the playground

Last updated View as MarkdownAgent setup

Enhance Prompt

Node type: llm:enhance_prompt
Category: llm

Description

Enhance Prompt enhances text prompts for text-to-image models: connect your text to the Prompt port, which is required, wire multiline text into System Prompt or images into Frames and Image 1 if you want them, pick a Model, and the text comes out of Enhanced Prompt. Model is also required and appears in the right-side config panel when the node is selected, with five options: anthropic/claude-sonnet-5, anthropic/claude-sonnet-4.5, anthropic/claude-haiku-4.5, openai/gpt-4o and deepseek/deepseek-v3.2-exp. The same panel holds Max Tokens, Reasoning and Temperature, which runs from 0 to 2. It costs about 3 credits per unit.

Pricing

  • Cost: ~3 credits per unit

Variant family

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required)
frames Frames IMAGE
image1 Image 1 IMAGE
system_prompt System Prompt TEXT · multiline

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
model Model TEXT (required) · options: anthropic/claude-sonnet-5, anthropic/claude-sonnet-4.5, anthropic/claude-haiku-4.5, openai/gpt-4o, deepseek/deepseek-v3.2-exp
max_tokens Max Tokens NUMBER · 1…∞
reasoning Reasoning BOOLEAN
temperature Temperature NUMBER · 0…2

Outputs

ID Label Type
text Enhanced Prompt TEXT

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.