mj_fast_describe

Technical Specifications of mj-fast-describe

What is mj-fast-describe?

mj-fast-describe is a Midjourney-oriented image-to-text model endpoint exposed through CometAPI that is designed to inspect an input image and generate prompt-style textual descriptions. Based on Midjourney’s official Describe documentation, the underlying describe workflow is meant to help users generate creative prompts by analyzing an uploaded image and offering words and phrases that characterize it.

In practice, this kind of model is useful when you want to reverse-engineer an image into prompt ideas, bootstrap new generations from visual references, or discover stylistic language you might not have written manually. Midjourney’s official documentation also notes that Describe suggestions are inspiration-oriented rather than exact reconstruction instructions, and repeated runs on the same image can produce different prompt sets.

Main features of mj-fast-describe

• Image-to-text prompt extraction: mj-fast-describe is built for turning visual inputs into descriptive text prompts, making it useful for prompt engineering, reference analysis, and creative ideation.
• Creative prompt suggestion workflow: The describe process is intended to inspire new prompt directions rather than produce a perfect literal copy of the source image.
• Multiple prompt candidates: Midjourney’s Describe workflow generates four prompt suggestions for an uploaded image, which is a strong indicator of the expected user experience for this model category.
• Fast ideation for visual references: This model is well suited for quickly extracting style words, scene cues, and phrasing from an image so teams can iterate faster on downstream image-generation prompts. This is an inference from the documented Describe behavior and the model’s “fast describe” naming.
• Useful for prompt discovery and remixing: You can use the returned descriptions as-is, edit them, or use them as a starting point for broader creative exploration.
• API-ready through CometAPI: Instead of using the native Midjourney interface directly, developers can access this capability through CometAPI’s unified model access layer.

How to access and integrate mj-fast-describe

Step 1: Sign Up for API Key

Sign up on CometAPI and create your API key from the developer dashboard. Once your key is issued, store it securely and use it as your Bearer token for all requests to mj-fast-describe.

Step 2: Send Requests to mj-fast-describe API

Use CometAPI's Midjourney-compatible endpoint at POST /mj/submit/describe.

curl https://api.cometapi.com/mj/submit/describe \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_API_KEY" \
  -d '{
    "prompt": "a futuristic cityscape at sunset --v 6.1",
    "botType": "MID_JOURNEY",
    "accountFilter": {
      "modes": ["FAST"]
    }
  }'

Step 3: Retrieve and Verify Results

The API returns a task object with a task ID. Poll GET /mj/task/{task_id}/fetch to check generation status and retrieve the output image URL when the task reaches a terminal state.