API Reference
Integration Guides
Errors
Pricing & Billing
Midjourney
Describe (Image to Text)
Use CometAPI POST /mj/submit/describe to extract an initial Midjourney prompt from an uploaded image for fast remixing and iteration.
POST
/
mj
/
submit
/
describe
Describe (image -> text)
curl --request POST \
--url https://api.cometapi.com/mj/submit/describe \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"base64": "data:image/png;base64,xxx"
}
'{
"code": 123,
"description": "<string>",
"properties": {},
"result": 123
}Use this endpoint to extract Midjourney-style prompt suggestions from an input image.
What this route is good for
- Turning an image into prompt candidates you can remix
- Extracting a visual direction before you start a fresh imagine task
- Building a faster authoring loop when you do not want to write the first prompt from scratch
Task flow
Submit the image
Upload or reference the image you want Midjourney to describe and store the returned task id.
Poll the describe task
Use Fetch Single Task until the task completes and returns prompt-like output.
Reuse the generated prompt
Take the best prompt candidate and continue with Imagine for a fresh generation pass.
Authorizations
Bearer token authentication. Use your CometAPI key.
Body
application/json
Base64-encoded image to describe. Use a data URI such as data:image/png;base64,xxx. Provide either base64 or link.
URL of the image to describe. Provide either link or base64.
Bot type to use. MID_JOURNEY for Midjourney (default), NIJI_JOURNEY for Niji.
Available options:
NIJI_JOURNEY, MID_JOURNEY Custom state string. Returned as-is in the task result and webhook callback for your own tracking.
⌘I
Describe (image -> text)
curl --request POST \
--url https://api.cometapi.com/mj/submit/describe \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"base64": "data:image/png;base64,xxx"
}
'{
"code": 123,
"description": "<string>",
"properties": {},
"result": 123
}