midjourney_imagine
Generate AI images by describing your vision in a text prompt, producing a 2x2 grid of four image variations for your creative projects.
Instructions
Generate AI images from a text prompt using Midjourney.
This is the primary way to create images - describe what you want and Midjourney
will generate a 2x2 grid of 4 image variations.
Use this when:
- You want to create new images from a text description
- You have a creative vision to visualize
- You need AI-generated artwork or illustrations
For image transformations like upscaling or variations, use midjourney_transform instead.
Returns:
Task ID and generated image information including URLs, dimensions, and available actions.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Description of the image to generate. Be descriptive about style, subject, lighting, and composition. Examples: 'A majestic lion in a savanna at sunset, cinematic lighting', 'Cyberpunk city street at night, neon lights, rain, photorealistic', 'Abstract watercolor painting of mountains and clouds' | |
| mode | No | Generation mode. 'fast' is recommended for most use cases. 'turbo' is faster but uses more credits. 'relax' is slower but cheaper. | fast |
| translation | No | If true, automatically translate non-English prompts to English for better results. | |
| split_images | No | If true, split the 2x2 grid result into 4 separate images returned via sub_image_urls. | |
| timeout | No | Timeout in seconds for the API to return data. Default is 480. | |
| callback_url | No | Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the image is generated. | |
| version | No | Midjourney model version to use, e.g. '8.1', '8', '7', '6.1'. '8.1' is the latest version and is recommended. Leave unset to use Midjourney's default. | |
| hd | No | Enable HD mode (V8/V8.1). Generates higher resolution images at 4x cost. | |
| quality | No | Image quality level. Values: '.25', '.5', '1', '2', '4'. Quality '4' is V8/V8.1 only. | |
| style_reference | No | Whether the prompt includes --sref style reference. In V8 this incurs 4x cost. | |
| moodboard | No | Whether using moodboard feature (V8 only, multiple reference images). Incurs 4x cost. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |