Start now

Create with Midjourney

Loading workspace...

Authentication & Integration

Checking API access...

Sign in to claim free credits and create with this model.

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

POSThttps://api.apixo.ai/api/v1/generateTask/midjourneyCreate task

GEThttps://api.apixo.ai/api/v1/statusTask/midjourney?taskId={taskId}Poll status

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

Parameters

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose whether to create a new image or run a follow-up action on a previous Midjourney result.text-to-image · image-to-image · image-edit · vary · upscale

promptconditional

Typestring

Describe the subject, composition, style, lighting, and details you want in the final image.Only in mode=text-to-image | image-to-image | image-edit

aspect_ratioconditional

Typeselect

Choose the output frame ratio when creating new images.1:1 · 1:2 · 2:1 · 2:3 · 3:2 · 3:4 · 4:3 · 5:6 · 6:5 · 9:16 · 16:9Only in mode=text-to-image | image-to-image | image-edit

speedrequired

Typeselect

Choose generation speed. Draft is lowest cost, Fast is standard, and Turbo returns faster.draft · fast · turboOnly in mode=text-to-image | image-to-image | image-edit

versionconditional

Typeselect

Choose the Midjourney model version. Niji variants are best for anime and illustration styles.8.1 · 7 · 6.1 · 6 · niji7 · niji6Only in mode=text-to-image | image-to-image | image-edit

cwconditional

Typeslider

Controls how strongly Midjourney follows character references. Active only when character references are provided.Only in mode=text-to-image | image-to-image

swconditional

Typeslider

Controls style reference strength. Active only when style references are provided.Only in mode=text-to-image | image-to-image

svconditional

Typetext

Optional style reference version for compatible Midjourney routes.Only in mode=text-to-image | image-to-image

owconditional

Typeslider

Controls object reference strength. Active only when an object reference is provided.Only in mode=text-to-image | image-to-image

iwconditional

Typetext

Optional numeric weight for image prompts in text-to-image or image-to-image mode.Only in mode=text-to-image | image-to-image

negative_promptconditional

Typestring

Describe what to avoid. This maps to Midjourney negative prompting.Only in mode=text-to-image | image-to-image

varietyconditional

Typeslider

Controls result diversity. Higher values produce more varied and unexpected outputs.Only in mode=text-to-image | image-to-image | image-edit

stylizationconditional

Typeslider

Controls artistic stylization strength.Only in mode=text-to-image | image-to-image | image-edit

weirdnessconditional

Typeslider

Adds surreal or unconventional effects.Only in mode=text-to-image | image-to-image | image-edit

expconditional

Typeslider

Experimental Midjourney control for supported versions.Only in mode=text-to-image | image-to-image

is_hdconditional

Typeboolean

Enable optional 2K HD output for Midjourney v8.1 when supported.Only in mode=text-to-image | image-to-image + version=8.1

enableTranslationconditional

Typeboolean

Request prompt translation to English for compatible routes.Only in mode=text-to-image | image-to-image | image-edit

watermarkconditional

Typetext

Optional watermark text for compatible routes.Only in mode=text-to-image | image-to-image | image-edit

taskIdconditional

Typetext

Use the APIXO task ID from a previous successful Midjourney generation.Only in mode=vary | upscale

imageIndexconditional

Typeselect

Select one image from the previous four-image Midjourney result.0 · 1 · 2 · 3Only in mode=vary | upscale

typeconditional

Typeselect

For vary, 0 is subtle and 1 is strong. For upscale, 0 is standard, 1 is creative, 2 is 2x, and 3 is 4x.0 · 1 · 2 · 3Only in mode=vary | upscale

remixPromptconditional

Typestring

Optional text guidance for variation workflows on compatible routes.Only in mode=vary

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose whether to create a new image or run a follow-up action on a previous Midjourney result.text-to-image · image-to-image · image-edit · vary · upscale
`prompt`	string	conditional	Describe the subject, composition, style, lighting, and details you want in the final image.Only in mode=text-to-image \| image-to-image \| image-edit
`aspect_ratio`	select	conditional	Choose the output frame ratio when creating new images.1:1 · 1:2 · 2:1 · 2:3 · 3:2 · 3:4 · 4:3 · 5:6 · 6:5 · 9:16 · 16:9Only in mode=text-to-image \| image-to-image \| image-edit
`speed`	select	required	Choose generation speed. Draft is lowest cost, Fast is standard, and Turbo returns faster.draft · fast · turboOnly in mode=text-to-image \| image-to-image \| image-edit
`version`	select	conditional	Choose the Midjourney model version. Niji variants are best for anime and illustration styles.8.1 · 7 · 6.1 · 6 · niji7 · niji6Only in mode=text-to-image \| image-to-image \| image-edit
`cw`	slider	conditional	Controls how strongly Midjourney follows character references. Active only when character references are provided.Only in mode=text-to-image \| image-to-image
`sw`	slider	conditional	Controls style reference strength. Active only when style references are provided.Only in mode=text-to-image \| image-to-image
`sv`	text	conditional	Optional style reference version for compatible Midjourney routes.Only in mode=text-to-image \| image-to-image
`ow`	slider	conditional	Controls object reference strength. Active only when an object reference is provided.Only in mode=text-to-image \| image-to-image
`iw`	text	conditional	Optional numeric weight for image prompts in text-to-image or image-to-image mode.Only in mode=text-to-image \| image-to-image
`negative_prompt`	string	conditional	Describe what to avoid. This maps to Midjourney negative prompting.Only in mode=text-to-image \| image-to-image
`variety`	slider	conditional	Controls result diversity. Higher values produce more varied and unexpected outputs.Only in mode=text-to-image \| image-to-image \| image-edit
`stylization`	slider	conditional	Controls artistic stylization strength.Only in mode=text-to-image \| image-to-image \| image-edit
`weirdness`	slider	conditional	Adds surreal or unconventional effects.Only in mode=text-to-image \| image-to-image \| image-edit
`exp`	slider	conditional	Experimental Midjourney control for supported versions.Only in mode=text-to-image \| image-to-image
`is_hd`	boolean	conditional	Enable optional 2K HD output for Midjourney v8.1 when supported.Only in mode=text-to-image \| image-to-image + version=8.1
`enableTranslation`	boolean	conditional	Request prompt translation to English for compatible routes.Only in mode=text-to-image \| image-to-image \| image-edit
`watermark`	text	conditional	Optional watermark text for compatible routes.Only in mode=text-to-image \| image-to-image \| image-edit
`taskId`	text	conditional	Use the APIXO task ID from a previous successful Midjourney generation.Only in mode=vary \| upscale
`imageIndex`	select	conditional	Select one image from the previous four-image Midjourney result.0 · 1 · 2 · 3Only in mode=vary \| upscale
`type`	select	conditional	For vary, 0 is subtle and 1 is strong. For upscale, 0 is standard, 1 is creative, 2 is 2x, and 3 is 4x.0 · 1 · 2 · 3Only in mode=vary \| upscale
`remixPrompt`	string	conditional	Optional text guidance for variation workflows on compatible routes.Only in mode=vary

File parameters (URL arrays)

image_urls[mode=text-to-image | image-to-image | image-edit]Image prompts for text-to-image or image-to-image, or exactly one source image for image-edit.Only in mode=text-to-image | image-to-image | image-edit

cref_urls[mode=text-to-image | image-to-image]Optional character reference images for text-to-image or image-to-image. Use these to preserve character identity across generations.Only in mode=text-to-image | image-to-image

sref_urls[mode=text-to-image | image-to-image]Optional style reference images for text-to-image or image-to-image. Uploaded files are sent as style reference URL objects.Only in mode=text-to-image | image-to-image

oref_urls[mode=text-to-image | image-to-image]Optional object reference image for text-to-image or image-to-image. At most one image is allowed.Only in mode=text-to-image | image-to-image

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/midjourney" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "a cozy cyberpunk cafe with neon lights, cinematic lighting",
      "speed": "fast",
      "aspect_ratio": "16:9",
      "version": "8.1",
      "sref_urls": [
        {
          "url": "https://example.com/style-reference.webp",
          "weight": 1
        }
      ],
      "cref_urls": [
        "https://example.com/character-reference.webp"
      ],
      "cw": 50,
      "stylization": 100,
      "is_hd": true
    }
  }'

Full API documentation

Midjourney Tips

Create image generation with Midjourney

Use Midjourney through APIXO to try prompts, inspect examples, compare costs, and keep useful settings ready for future generations.

Create

Start with an idea

Pick a model, tune the settings, and create in one place.

Write an idea

Describe what you want to make.

Use an example

Start from a ready-made style.

Adjust the look

Tune the key settings quickly.

Create

Generate when everything feels right.

Keep results

Save what you want to revisit.

Try again

Make the next version faster.

Midjourney API Technical Specs

Current Midjourney capabilities and important creation limits.

Midjourney Modes

Text-to-image, image-to-image, image-edit, plus Vary and Upscale result actions

Midjourney Output

4 variations per use

Midjourney Controls

Draft, Fast, and Turbo / v8.1 / v7 / niji7

Midjourney Latency

Typically 30-60 seconds

Capabilities

Key Midjourney capabilities

Midjourney image generation

Generate polished visuals with prompt, mode, aspect ratio, and resolution controls in one place.

Midjourney reference editing

Use supported image reference modes to steer composition, identity, or style without leaving the model page.

Midjourney creative iteration

Review examples, adjust settings, and keep exploring until the result fits your idea.

What can you build with Midjourney?

Midjourney marketing visuals

Create product shots, social assets, hero images, and campaign concepts.

Midjourney design iteration

Use prompt and reference controls to explore visual directions before choosing a favorite result.

Midjourney content pipelines

Make repeatable content for ecommerce, campaigns, and creative workflows.

Read FAQ

Midjourney notes and questions

Midjourney generations may take time to finish, especially for larger or more complex outputs.

Result quality depends on prompt clarity, input asset quality, and provider-side model behavior.

All requests must pass provider safety, moderation, and account access checks.

Reference-image modes require valid image inputs and may not preserve every detail exactly.

Yes. Use the Create tab to try prompts, upload supported inputs, and adjust settings directly in the browser.

APIXO

Create with Midjourney

Write a prompt, adjust the style, and generate your next image in one place.

Start creating View API docs

Midjourney

Create with Midjourney

Create image generation with Midjourney

Start with an idea

Write an idea

Use an example

Adjust the look

Create

Keep results

Try again

Midjourney API Technical Specs

Midjourney Modes

Midjourney Output

Midjourney Controls

Midjourney Latency

Key Midjourney capabilities

Midjourney image generation

Midjourney reference editing

Midjourney creative iteration

What can you build with Midjourney?

Midjourney marketing visuals

Midjourney design iteration

Midjourney content pipelines

Midjourney notes and questions

Can I try Midjourney in the browser?

Does Midjourney support async generation?

Where do the Midjourney parameters come from?

Can I replace the demo assets later?

Create with Midjourney