Overview
This node integrates with the Midjourney AI service to generate and manipulate images based on textual prompts or existing images. It supports multiple actions such as generating new image grids, describing images, upscaling selected images, creating variations, zooming out images, and executing custom commands.
Common scenarios where this node is beneficial include:
- Creating AI-generated artwork or concept images from text prompts.
- Enhancing image resolution by upscaling.
- Generating variations of an existing image for creative exploration.
- Obtaining descriptive metadata about an image.
- Zooming out images to reveal more context or detail.
- Running custom commands supported by the Midjourney API.
Practical examples:
- A designer uses the "Imagine" action to create four concept images from a prompt describing a futuristic cityscape.
- A content creator uses "Upscale" to improve the quality of a selected image before publishing.
- An artist uses "Variation" to explore different styles based on an initial image.
- A developer uses "Describe" to extract textual descriptions from an image for accessibility purposes.
Properties
| Name | Meaning |
|---|---|
| Action | The operation to perform. Options: Custom, Describe, Imagine, Upscale, Variation, Zoom Out. |
| Prompt | Text prompt used to generate or vary images (required for Imagine and Variation actions). |
| Image URI | URI of the image to describe (required for Describe action). |
| Message ID | Identifier of the message/image to act upon (required for Variation, Upscale, Zoom Out, Custom). |
| Message Hash | Hash associated with the message/image (required for Variation, Upscale, Zoom Out). |
| Message Flags | Numeric flags related to the message/image (required for Variation, Upscale, Zoom Out, Custom). |
| Index | Index number specifying which image in a grid to target (required for Variation and Upscale). |
| Custom ID | Identifier for a custom command (required for Custom action). |
| Zoom Level | Zoom intensity level for zooming out. Options: High, Low, 2x, 1.5x (required for Zoom Out). |
Output
The node outputs JSON data containing key information returned from the Midjourney API for each action. The typical fields included are:
id: Unique identifier of the generated or processed image/message.hash: Hash string representing the image/message state.content: Textual content or prompt related to the image.uri: URI pointing to the generated or described image.flags: Numeric flags associated with the image/message.options: Additional options or metadata returned by the API.
For the "Describe" action, the output includes:
descriptions: Array of textual descriptions extracted from the image.uri: URI of the described image.
The node does not explicitly output binary data but provides URIs to access images.
Dependencies
- Requires an active Midjourney API credential with necessary authentication tokens and identifiers (e.g., server ID, channel ID, and API token).
- Uses the official Midjourney SDK/library to interact with the API.
- Requires network connectivity to communicate with the Midjourney service.
Troubleshooting
Common issues:
- Invalid or missing credentials can cause authentication failures.
- Incorrect or missing required parameters for specific actions will result in errors.
- Network issues may prevent communication with the Midjourney API.
- Using invalid message IDs, hashes, or indexes may cause the API to reject requests.
Error messages and resolutions:
- Authentication errors: Verify that the API credentials are correctly configured and valid.
- Missing parameter errors: Ensure all required properties for the chosen action are provided.
- API rate limits or timeouts: Retry after some time or check API usage quotas.
- Unexpected response structure: Confirm compatibility between the node version and the Midjourney API.
The node supports continuing execution on failure if enabled, allowing partial processing of multiple inputs.