Openai Dall-E Image

How to use the Openai Dall-E Image robot skill

Integrate state-of-the-art image generation capabilities directly into your robot apps and products. OpenAI's GPT Image models create realistic images and art from natural language descriptions, and can edit an existing image to match a prompt.

Have your robot programmatically generate images from speech recognition robot skill descriptions. Or, have the image from the camera sent to OpenAI to be edited with a prompt. Experience the whacky world of AI image generation with your Synthiam-powered robot or webcam.

*Note: OpenAI retired the DALLE 2 and DALLE 3 models on May 12, 2026. This robot skill now uses the GPT Image model family (gpt-image-2, gpt-image-1.5, gpt-image-1, and gpt-image-1-mini), which you select in the configuration menu.

How Does It Work?

The GPT Image models have learned the relationship between images and the text used to describe them. From a text description, they can create original, realistic photos and art, combining concepts, attributes, and styles. They can also edit an existing image (such as a camera frame) to apply a prompt you provide.

Main Window

1) Generate From Description

Prompts a dialog for you to enter a description of the image you would like generated. Be as detailed as possible because anything is possible. The generated image is displayed in the preview box.

2) Modify the Camera Image

Takes an image from the camera device and edits it with a prompt that you provide. A dialog asks how you would like the camera image modified (for example, "Make it look like a watercolor painting"), and OpenAI returns an edited version of that image.

*Note: The GPT Image models edit an image against a prompt; they do not create prompt-less "variations" like the retired DALLE 2 model did. A prompt is therefore required when modifying the camera image.

3) Save Image

Saves the most recently generated or edited image to a file on your computer. A save dialog lets you choose the location and format (PNG, JPEG, or BMP). Generating or modifying an image again replaces the result, so save it before re-running if you want to keep it.

Configuration

1) API Settings

Developer API Key - Enter the API Key from OpenAI's website here. This value will be saved locally on the current user account and used for any OpenAI robot skills. This value will not be distributed with your project.

Image Model - Select which OpenAI image model to use:

• gpt-image-2 - Newest and highest quality, with the largest output sizes. Slower and the most expensive.
• gpt-image-1.5 - A balanced default for quality, speed, and cost.
• gpt-image-1 - The original GPT Image model. A lower-cost option.
• gpt-image-1-mini - The fastest and least expensive option.

Control Commands

There are a few ControlCommand() that allow programmatic usage of this robot skill from other robot skills. For example, send the description from the result of a speech recognition request to be generated as an image. The camera image modification uses the camera device robot skills, so they are automatically queried for the control command. If no camera device name is specified, the first camera device is used.

- GetImageFromText

Example: ControlCommand("OpenAI Dall-e Image", "GetImageFromText", "description of the image to generate");

Generate an image based on the provided description.

- GetImageVariation

Example #1: ControlCommand("OpenAI Dall-e Image", "GetImageVariation", "Make it look like a watercolor painting");

Example #2: ControlCommand("OpenAI Dall-e Image", "GetImageVariation", "Make it look like a watercolor painting", "Camera");

Edit the camera image using the supplied prompt. The first parameter is the prompt describing how to modify the image (required). The optional second parameter is the camera device name.

*Note: When no camera device name is specified, the first camera device will be used.

- SaveImage

Example: ControlCommand("OpenAI Dall-e Image", "SaveImage", "c:\temp\image.png");

Saves the most recently generated or edited image to the specified file path. The file format is chosen from the file extension (.png, .jpg/.jpeg, or .bmp), and the destination folder is created if it does not exist.

API Key

An account is required on the OpenAI website to use the service. Once an account is created, you will have an API key to use in the robot skill.

Visit the OpenAI website and select the API option from the menu.

Press the SIGNUP option to create an account

Once the account is created, press your Username icon to view the drop-down. And select the View API Keys option.

Copy your API key

Paste the API key in the robot skill configuration menu

Control Commands for the Openai Dall-E Image robot skill

There are Control Commands available for this robot skill which allows the skill to be controlled programmatically from scripts or other robot skills. These commands enable you to automate actions, respond to sensor inputs, and integrate the robot skill with other systems or custom interfaces. If you're new to the concept of Control Commands, we have a comprehensive manual available here that explains how to use them, provides examples to get you started and make the most of this powerful feature.

GetImageFromText", "A goldfish driving a car

Example: controlCommand("OpenAI Dall-e Image", "GetImageFromText", "A goldfish driving a car")

GetImageVariation", "Make it look like a watercolor painting

Example: controlCommand("OpenAI Dall-e Image", "GetImageVariation", "Make it look like a watercolor painting")

SaveImage", "c:\temp\image.png

Example: controlCommand("OpenAI Dall-e Image", "SaveImage", "c:\temp\image.png")