← All nodes
Transforms a_generate_image

Generate Image

Text-to-image or image-edit via nano-banana / DALL-E. Persists to R2 by default.

What does it do?

Creates a completely new image from a text description.

How does it work?

Sends your prompt (e.g. "an astronaut cat") to an image generation model like DALL-E or Stable Diffusion and returns the visual file.

Why use it?

Great for creative flows, automatic avatar creation or sending instant previews generated to your customers.

Inputs

nametype
prompt string

Outputs

nametype
url string
provider string
model string
width number
height number
bytes number

Branches

Fixed branches

  • out — Output

Configuration

model string required default: "google/gemini-2.5-flash-image"
prompt_field string required default: "prompt"
source_image_url_field string optional
source_image_base64_field string optional
source_images_urls_field string optional
source_images_base64_field string optional
size "1024x1024" | "1024x1792" | "1792x1024" required default: "1024x1024"
persist_to_r2 boolean required default: true
memory_key string optional

Default configuration

{
  "model": "google/gemini-2.5-flash-image",
  "prompt_field": "prompt",
  "size": "1024x1024",
  "persist_to_r2": true
}

Emitted events

This node does not publish events on the pubsub channel.