Midjourney AI Image Generator API documentation

Generate images with Midjourney AI Image Generator (Midjourney).

Endpoints

Contract item	Value
Capability	`midjourney-ai-image-generator`
Submit	`POST https://vidmage.ai/api/v1/midjourney-ai-image-generator/submit`
Query	`POST https://vidmage.ai/api/v1/midjourney-ai-image-generator/query`
Task identifier	`taskId`
Result field	`imageUrl`

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Product guide: Midjourney Image API

Parameters and input rules

Field	Type	Required	Default	Meaning and limits
`prompt`	`string`	Yes	Not specified	Text prompt describing the image to generate (max 8192 chars). For an unspecified character or figurine, use an original non-branded character with no logos and no resemblance to existing copyrighted superheroes; preserve any character the user explicitly names. Minimum characters: `1` Maximum characters: `8192`
`aspectRatio`	`string`	No	`"1:1"`	Output aspect ratio. Values: `"1:1"`, `"4:3"`, `"3:2"`, `"16:9"`, `"3:4"`, `"2:3"`, `"9:16"`
`negativePrompt`	`string`	No	Not specified	Describe content that should not appear in the image. Maximum characters: `2000`
`chaos`	`integer`	No	`0`	Increase variation and unpredictability. Minimum: `0` Maximum: `100` Multiple of: `1`
`quality`	`string`	No	`"1"`	Rendering quality level. Values: `"1"`, `"2"`, `"4"`
`stylize`	`integer`	No	`0`	Control the strength of Midjourney styling. Minimum: `0` Maximum: `1000` Multiple of: `1`
`weird`	`integer`	No	`0`	Control unconventional and experimental aesthetics. Minimum: `0` Maximum: `3000` Multiple of: `1`
`raw`	`boolean`	No	`false`	Reduce automatic styling for more literal prompt control.
`imageUrl`	`string`	No	Not specified	Optional base image prompt.
`iw`	`integer`	No	`1`	Control the influence of the base image prompt. Requires imageUrl when supplied. Minimum: `0` Maximum: `3` Multiple of: `1` Requires `imageUrl` when supplied.
`sref`	`string`	No	Not specified	Optional style reference image.
`sw`	`integer`	No	`100`	Control the influence of the style reference. Requires sref when supplied. Minimum: `0` Maximum: `1000` Multiple of: `1` Requires `sref` when supplied.
`sv`	`integer`	No	`4`	Style reference model version. Requires sref when supplied. Minimum: `1` Maximum: `6` Multiple of: `1` Requires `sref` when supplied.
`oref`	`string`	No	Not specified	Optional Omni reference image.
`ow`	`integer`	No	`100`	Control the influence of the Omni reference. Requires oref when supplied. Minimum: `1` Maximum: `1000` Multiple of: `1` Requires `oref` when supplied.
`tile`	`boolean`	No	`false`	Create a seamless repeating pattern.

text to image

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–8192 characters.
`aspectRatio`	Values: `"1:1"`, `"4:3"`, `"3:2"`, `"16:9"`, `"3:4"`, `"2:3"`, `"9:16"`. Default: `1:1`.
`resolution`	Not used in this mode.
`negativePrompt`	Describe content that should not appear in the image. Maximum characters: `2000`
`chaos`	Increase variation and unpredictability. Minimum: `0` Maximum: `100` Multiple of: `1` Default: `0`
`quality`	Rendering quality level. Values: `"1"`, `"2"`, `"4"` Default: `"1"`
`stylize`	Control the strength of Midjourney styling. Minimum: `0` Maximum: `1000` Multiple of: `1` Default: `0`
`weird`	Control unconventional and experimental aesthetics. Minimum: `0` Maximum: `3000` Multiple of: `1` Default: `0`
`raw`	Reduce automatic styling for more literal prompt control. Default: `false`
`imageUrl`	Optional base image prompt.
`iw`	Control the influence of the base image prompt. Minimum: `0` Maximum: `3` Multiple of: `1` Requires `imageUrl` when supplied. Default: `1`
`sref`	Optional style reference image.
`sw`	Control the influence of the style reference. Minimum: `0` Maximum: `1000` Multiple of: `1` Requires `sref` when supplied. Default: `100`
`sv`	Style reference model version. Minimum: `1` Maximum: `6` Multiple of: `1` Requires `sref` when supplied. Default: `4`
`oref`	Optional Omni reference image.
`ow`	Control the influence of the Omni reference. Minimum: `1` Maximum: `1000` Multiple of: `1` Requires `oref` when supplied. Default: `100`
`tile`	Create a seamless repeating pattern. Default: `false`

Example request

{
  "imageUrl": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "prompt": "A serene mountain observatory above the clouds at sunrise, cinematic wide-angle landscape photography",
  "aspectRatio": "1:1",
  "chaos": 0,
  "quality": "1",
  "stylize": 0,
  "weird": 0,
  "raw": false,
  "iw": 1,
  "sref": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "sw": 100,
  "sv": 4,
  "oref": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "ow": 100,
  "tile": false
}

# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/midjourney-ai-image-generator/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"imageUrl":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","prompt":"A serene mountain observatory above the clouds at sunrise, cinematic wide-angle landscape photography","aspectRatio":"1:1","chaos":0,"quality":"1","stylize":0,"weird":0,"raw":false,"iw":1,"sref":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","sw":100,"sv":4,"oref":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","ow":100,"tile":false}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the generated image. Read imageUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/midjourney-ai-image-generator/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "imageUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Credits

Component / option	Rate	Minimum
Base rate	15 credits / generation	—

Base charge is per generation at the selected resolution.

Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.

Integration guides

Authentication · File uploads · Task lifecycle · Error recovery · MCP

Endpoints

Contract item	Value
Capability	`midjourney-ai-image-generator`
Submit	`POST https://vidmage.ai/api/v1/midjourney-ai-image-generator/submit`
Query	`POST https://vidmage.ai/api/v1/midjourney-ai-image-generator/query`
Task identifier	`taskId`
Result field	`imageUrl`

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Parameters and input rules

Field	Type	Required	Default	Meaning and limits
`prompt`	`string`	Yes	Not specified	Text prompt describing the image to generate (max 8192 chars). For an unspecified character or figurine, use an original non-branded character with no logos and no resemblance to existing copyrighted superheroes; preserve any character the user explicitly names. Minimum characters: `1` Maximum characters: `8192`
`aspectRatio`	`string`	No	`"1:1"`	Output aspect ratio. Values: `"1:1"`, `"4:3"`, `"3:2"`, `"16:9"`, `"3:4"`, `"2:3"`, `"9:16"`
`negativePrompt`	`string`	No	Not specified	Describe content that should not appear in the image. Maximum characters: `2000`
`chaos`	`integer`	No	`0`	Increase variation and unpredictability. Minimum: `0` Maximum: `100` Multiple of: `1`
`quality`	`string`	No	`"1"`	Rendering quality level. Values: `"1"`, `"2"`, `"4"`
`stylize`	`integer`	No	`0`	Control the strength of Midjourney styling. Minimum: `0` Maximum: `1000` Multiple of: `1`
`weird`	`integer`	No	`0`	Control unconventional and experimental aesthetics. Minimum: `0` Maximum: `3000` Multiple of: `1`
`raw`	`boolean`	No	`false`	Reduce automatic styling for more literal prompt control.
`imageUrl`	`string`	No	Not specified	Optional base image prompt.
`iw`	`integer`	No	`1`	Control the influence of the base image prompt. Requires imageUrl when supplied. Minimum: `0` Maximum: `3` Multiple of: `1` Requires `imageUrl` when supplied.
`sref`	`string`	No	Not specified	Optional style reference image.
`sw`	`integer`	No	`100`	Control the influence of the style reference. Requires sref when supplied. Minimum: `0` Maximum: `1000` Multiple of: `1` Requires `sref` when supplied.
`sv`	`integer`	No	`4`	Style reference model version. Requires sref when supplied. Minimum: `1` Maximum: `6` Multiple of: `1` Requires `sref` when supplied.
`oref`	`string`	No	Not specified	Optional Omni reference image.
`ow`	`integer`	No	`100`	Control the influence of the Omni reference. Requires oref when supplied. Minimum: `1` Maximum: `1000` Multiple of: `1` Requires `oref` when supplied.
`tile`	`boolean`	No	`false`	Create a seamless repeating pattern.

text to image

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–8192 characters.
`aspectRatio`	Values: `"1:1"`, `"4:3"`, `"3:2"`, `"16:9"`, `"3:4"`, `"2:3"`, `"9:16"`. Default: `1:1`.
`resolution`	Not used in this mode.
`negativePrompt`	Describe content that should not appear in the image. Maximum characters: `2000`
`chaos`	Increase variation and unpredictability. Minimum: `0` Maximum: `100` Multiple of: `1` Default: `0`
`quality`	Rendering quality level. Values: `"1"`, `"2"`, `"4"` Default: `"1"`
`stylize`	Control the strength of Midjourney styling. Minimum: `0` Maximum: `1000` Multiple of: `1` Default: `0`
`weird`	Control unconventional and experimental aesthetics. Minimum: `0` Maximum: `3000` Multiple of: `1` Default: `0`
`raw`	Reduce automatic styling for more literal prompt control. Default: `false`
`imageUrl`	Optional base image prompt.
`iw`	Control the influence of the base image prompt. Minimum: `0` Maximum: `3` Multiple of: `1` Requires `imageUrl` when supplied. Default: `1`
`sref`	Optional style reference image.
`sw`	Control the influence of the style reference. Minimum: `0` Maximum: `1000` Multiple of: `1` Requires `sref` when supplied. Default: `100`
`sv`	Style reference model version. Minimum: `1` Maximum: `6` Multiple of: `1` Requires `sref` when supplied. Default: `4`
`oref`	Optional Omni reference image.
`ow`	Control the influence of the Omni reference. Minimum: `1` Maximum: `1000` Multiple of: `1` Requires `oref` when supplied. Default: `100`
`tile`	Create a seamless repeating pattern. Default: `false`

Example request

{
  "imageUrl": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "prompt": "A serene mountain observatory above the clouds at sunrise, cinematic wide-angle landscape photography",
  "aspectRatio": "1:1",
  "chaos": 0,
  "quality": "1",
  "stylize": 0,
  "weird": 0,
  "raw": false,
  "iw": 1,
  "sref": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "sw": 100,
  "sv": 4,
  "oref": "https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp",
  "ow": 100,
  "tile": false
}

# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/midjourney-ai-image-generator/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"imageUrl":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","prompt":"A serene mountain observatory above the clouds at sunrise, cinematic wide-angle landscape photography","aspectRatio":"1:1","chaos":0,"quality":"1","stylize":0,"weird":0,"raw":false,"iw":1,"sref":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","sw":100,"sv":4,"oref":"https://vidmage.ai/assets/images/samples/blue-eyed-woman-sunlight.webp","ow":100,"tile":false}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the generated image. Read imageUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/midjourney-ai-image-generator/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "imageUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Component / option

Rate

Minimum

Base rate

15 credits / generation

—