OpenAI Image Generator

This node allows you to generate or edit images using OpenAI's DALL-E 3 or GPT Image 1. GPT Image 1 also supports image editing, while DALL-E 3 does not.

To generate an image, provide a prompt and select the model you want to use. To edit images, provide an input table that contains image columns.

You can include multiple image columns in the table and choose which ones to use for editing. For example, one column could contain images of objects and another could contain backgrounds. After selecting both columns and providing a prompt, the model will generate a new image that combines the objects and backgrounds. Currently, the node only supports PNG images.

The use of GPT Image 1 may require your organization to be verified by OpenAI. To do so visit the OpenAI platform.

Generating images is significantly more expensive than text generation. Please refer to OpenAI Docs for more details on how the costs are calculated.


Note: If you use the Credentials Configuration node and do not select the "Save password in configuration (weakly encrypted)" option for passing the API key, the Credentials Configuration node will need to be reconfigured upon reopening the workflow, as the credentials flow variable was not saved and will therefore not be available to downstream nodes.

Options

Model

The model to use for image generation.

Available options:

  • GPT Image 1: State-of-the-art quality, excels at detailed and complex prompts (recommended).
  • DALL-E 3: Previous-generation model: faster outputs with solid everyday quality.
Prompt

The prompt the model uses to generate an image. A more descriptive prompt will usually generate a better image. The maximum length is 32000 characters for GPT Image 1 and 4000 characters for DALL-E 3.

DALL-E 3 Settings

Image size

The size of the image that will be generated by DALL-E-3. Generating images with higher resolution will increase the costs. Please refer to OpenAI Docs for more information about the pricing.

Quality

The quality of the produced image where hd creates images with finer details and greater consistency across the image. Generating higher quality images will increase the costs. Please refer to OpenAI Docs for more information about the pricing.

Style

The quality of the produced image where vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images.

GPT Image 1 Settings

Image dimension

The size of the image that will be generated by GPT Image 1. Generating images with higher resolution will increase the costs. Please refer to OpenAI Docs for more information about the pricing.

Available options:

  • Square: 1024x1024
  • Landscape: 1536x1024
  • Portrait: 1024x1536
Quality

The quality of the produced image.

Generating higher quality images will increase the costs. Please refer to OpenAI Docs for more information about the pricing.

Available options:

  • High: Generates images with the highest level of detail and consistency across the entire image.
  • Medium: Balances image quality and generation speed for general-purpose use.
  • Low: Produces lower quality images with faster generation time and reduced computational load.
Background

Allows to set transparency for the background of the generated image.

Available options:

  • Transparent: Generates images with a transparent background.
  • Opaque: Creates images with a solid, non-transparent background.
  • Auto: Automatically selects the most appropriate background type based on the image content.
Moderation

All prompts and generated images are filtered in accordance with OpenAI's content policy. This parameter sets the content moderation level for the generated image.

Available options:

  • Auto: Basic filtering that tries to block certain types of content that might not be appropriate for all ages
  • Low: Less restrictive filtering
Images to edit

Columns containing images to edit.

Input Ports

Icon

Validated authentication for OpenAI.

Icon

Table containing the images to edit.

Output Ports

Icon

The image generated by the model.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

View
View of the generated image.

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.