## Basic model info

- Model name: midjourney/midjourney v8.2
- Model description: Generate and edit images with Midjourney v8.2.
- Endpoint name: text-to-image


## Model schema

The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/midjourney/v8.2/latest.json)

### Model input schema

The model input schema is:



```json
{
  "description": "Input model for Midjourney v8.2 image generation.",
  "properties": {
    "prompt": {
      "description": "The text prompt for image generation. Inline -- parameters are ignored: the prompt is truncated at the first flag-like token. Use structured fields to set parameters. Curly braces/permutations are unsupported.",
      "pattern": "^(?:[^{}]*)$(?![\\s\\S])",
      "title": "Prompt",
      "type": "string",
      "x-sr-order": 201
    },
    "aspect_ratio": {
      "anyOf": [
        {
          "maxLength": 7,
          "pattern": "^(?![\\s\\S]*(?:-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]|(?<![^\\s])(?:(?=(?:[-‐‑‒–—―−﹘﹣－][­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*)*[‐‑‒–—―−﹘﹣－])[-‐‑‒–—―−﹘﹣－](?:[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[-‐‑‒–—―−﹘﹣－])+|[—―－−])[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]))(?![\\s\\S]*[\\x00-\\x1f\\x7f-\\x9f\\u2028\\u2029­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿])(?:(?!0{1,3}:)[0-9]{1,3}:(?!0{1,3}$(?![\\s\\S]))[0-9]{1,3})$(?![\\s\\S])",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--ar`) Image aspect ratio, e.g. '1:1', '16:9', '9:16', '3:4', '4:3', '2:3', '3:2'. Max 4:1 in HD mode",
      "title": "Aspect Ratio",
      "x-sr-order": 401
    },
    "seed": {
      "anyOf": [
        {
          "maximum": 4294967295,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--seed`) Seed number for reproducible results. Same seed + prompt produces similar images (99% identical)",
      "title": "Seed",
      "x-sr-order": 408
    },
    "chaos": {
      "anyOf": [
        {
          "maximum": 100,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--chaos`) How varied the four initial results will be. Range 0–100. Higher values produce more unusual, unexpected compositions",
      "title": "Chaos",
      "x-sr-order": 406
    },
    "exp": {
      "anyOf": [
        {
          "maximum": 100,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--exp`) Enhanced detail level. Range 0–100, sweet spot 10–25. Increases prompt adherence and fine detail",
      "title": "Exp",
      "x-sr-order": 405
    },
    "hd": {
      "default": false,
      "description": "hd=true bills $0.076 per request (2x the $0.038 standard FAST price). Available on Littercoder; ephone rejects hd=true because it charges HD but returns SD images.",
      "title": "Hd",
      "type": "boolean",
      "x-sr-order": 402
    },
    "image_references": {
      "anyOf": [
        {
          "items": {
            "pattern": "^(?![\\s\\S]*[\\x00-\\x1f\\x7f-\\x9f\\u2028\\u2029­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿])(?:[Hh][Tt][Tt][Pp][Ss]?://(?:\\[[0-9A-Fa-f:.]+\\]|[^\\s/:?#@\\[\\]\\\\\"'{}]+)(?::[0-9]+)?(?:[/?#](?:(?!::)[^\\s\\\\\"'{}])*)?|data:image/[A-Za-z0-9][A-Za-z0-9.+-]*;base64,(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{4}|[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=))$(?![\\s\\S])",
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "description": "Reference images for image prompting (垫图). Provide 1–5 image URLs to visually influence the generation",
      "title": "Image References",
      "x-sr-order": 301
    },
    "image_weight": {
      "anyOf": [
        {
          "maximum": 2,
          "minimum": 0,
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--iw`) How strongly reference images (image_references) influence the result. Range 0–2, default 1",
      "title": "Image Weight",
      "x-sr-order": 415
    },
    "personalize": {
      "anyOf": [
        {
          "maxLength": 8192,
          "pattern": "^(?![\\s\\S]*(?:-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]|(?<![^\\s])(?:(?=(?:[-‐‑‒–—―−﹘﹣－][­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*)*[‐‑‒–—―−﹘﹣－])[-‐‑‒–—―−﹘﹣－](?:[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[-‐‑‒–—―−﹘﹣－])+|[—―－−])[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]))(?![\\s\\S]*[\\x00-\\x1f\\x7f-\\x9f\\u2028\\u2029­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿])(?:(?:[A-Za-z0-9][A-Za-z0-9_]*(?:-[A-Za-z0-9_]+)*(?: +[A-Za-z0-9][A-Za-z0-9_]*(?:-[A-Za-z0-9_]+)*)*)?)$(?![\\s\\S])",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--p`) Personalization profile code to apply your custom aesthetic preferences. Leave empty for default personalization",
      "title": "Personalize",
      "x-sr-order": 414
    },
    "sref": {
      "anyOf": [
        {
          "maxLength": 8192,
          "pattern": "^(?![\\s\\S]*(?:-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*-[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]|(?<![^\\s])(?:(?=(?:[-‐‑‒–—―−﹘﹣－][­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*)*[‐‑‒–—―−﹘﹣－])[-‐‑‒–—―−﹘﹣－](?:[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[-‐‑‒–—―−﹘﹣－])+|[—―－−])[­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿]*[A-Za-z]))(?![\\s\\S]*[\\x00-\\x1f\\x7f-\\x9f\\u2028\\u2029­͏؀-؅؜۝܏࢐-࢑࣢᠎​-‏‪-‮⁠-⁤⁦--𑂽𑃍𓐰-𓐿𛲠-𛲣𝅳-𝅺󠀁󠀠-󠁿])(?:(?:(?:[Hh][Tt][Tt][Pp][Ss]?://(?:\\[[0-9A-Fa-f:.]+\\]|[^\\s/:?#@\\[\\]\\\\\"'{}]+)(?::[0-9]+)?(?:[/?#](?:(?!::)[^\\s\\\\\"'{}])*)?|[0-9]+)(?:::(?=[0-9.]*[1-9])(?:[0-9]+(?:\\.[0-9]+)?|\\.[0-9]+))?|random)(?: +(?:(?:[Hh][Tt][Tt][Pp][Ss]?://(?:\\[[0-9A-Fa-f:.]+\\]|[^\\s/:?#@\\[\\]\\\\\"'{}]+)(?::[0-9]+)?(?:[/?#](?:(?!::)[^\\s\\\\\"'{}])*)?|[0-9]+)(?:::(?=[0-9.]*[1-9])(?:[0-9]+(?:\\.[0-9]+)?|\\.[0-9]+))?|random))*)$(?![\\s\\S])",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--sref`) Style reference: URL of a reference image or a numeric sref code to apply its visual style",
      "title": "Sref",
      "x-sr-order": 411
    },
    "stop": {
      "anyOf": [
        {
          "maximum": 100,
          "minimum": 10,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--stop`) Stop generation early at the specified percentage. Range 10–100",
      "title": "Stop",
      "x-sr-order": 409
    },
    "style": {
      "anyOf": [
        {
          "const": "raw",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--style`) Style preset: 'raw' reduces Midjourney's default beautification for more photographic results",
      "title": "Style",
      "x-sr-order": 404
    },
    "style_weight": {
      "anyOf": [
        {
          "maximum": 1000,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--sw`) How strongly the style reference (sref) influences the result. Range 0–1000, default 100",
      "title": "Style Weight",
      "x-sr-order": 412
    },
    "stylize": {
      "anyOf": [
        {
          "maximum": 1000,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--stylize`) How strongly Midjourney's default aesthetic is applied. Range 0–1000, default 100. Higher values produce more artistic results",
      "title": "Stylize",
      "x-sr-order": 403
    },
    "sv": {
      "anyOf": [
        {
          "enum": [
            4,
            6,
            7
          ],
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--sv`) Style reference version. 7 is default (current), 4 and 6 enable legacy sref codes",
      "title": "Sv",
      "x-sr-order": 413
    },
    "tile": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--tile`) Generate seamlessly tiling patterns, useful for textures and wallpapers",
      "title": "Tile",
      "x-sr-order": 410
    },
    "weird": {
      "anyOf": [
        {
          "maximum": 3000,
          "minimum": 0,
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "description": "(`--weird`) Injects quirky and offbeat qualities into images. Range 0–3000",
      "title": "Weird",
      "x-sr-order": 407
    }
  },
  "required": [
    "prompt"
  ],
  "title": "TextToImageInput",
  "type": "object"
}
```



### Model output schema

The model output schema is:



```json
{
  "properties": {
    "action_type": {
      "title": "Action Type",
      "type": "string"
    },
    "images": {
      "items": {
        "properties": {
          "actions": {
            "items": {
              "properties": {
                "custom_id": {
                  "title": "Custom Id",
                  "type": "string"
                },
                "label": {
                  "title": "Label",
                  "type": "string"
                },
                "task_id": {
                  "title": "Task Id",
                  "type": "string"
                }
              },
              "required": [
                "task_id",
                "custom_id",
                "label"
              ],
              "title": "ImageS1OutputActionItem",
              "type": "object"
            },
            "title": "Actions",
            "type": "array"
          },
          "content_type": {
            "description": "The mime type of the file.",
            "title": "Content Type",
            "type": "string"
          },
          "file_name": {
            "description": "The name of the file. It will be auto-generated if not provided.",
            "title": "File Name",
            "type": "string"
          },
          "file_size": {
            "description": "The size of the file in bytes.",
            "title": "File Size",
            "type": "integer"
          },
          "url": {
            "description": "The URL where the file can be downloaded from.",
            "title": "Url",
            "type": "string"
          }
        },
        "required": [
          "content_type",
          "file_name",
          "file_size",
          "url",
          "actions"
        ],
        "title": "ImageS1ImageOutputItem",
        "type": "object"
      },
      "title": "Images",
      "type": "array"
    },
    "mode": {
      "title": "Mode",
      "type": "string"
    },
    "units_used": {
      "title": "Units Used",
      "type": "integer"
    }
  },
  "required": [
    "images",
    "action_type",
    "mode",
    "units_used"
  ],
  "title": "ImageS1Output",
  "type": "object"
}
```



## Example inputs and outputs

Use the following example inputs and outputs to understand the model.

### Input example



```json
{
  "prompt": "",
  "aspect_ratio": null,
  "seed": null,
  "chaos": null,
  "exp": null,
  "hd": false,
  "image_references": null,
  "image_weight": null,
  "personalize": null,
  "sref": null,
  "stop": null,
  "style": null,
  "style_weight": null,
  "stylize": null,
  "sv": null,
  "tile": null,
  "weird": null
}
```



### Output example



```json
{
}
```



## Model code examples

### JavaScript



```javascript
import { sunra } from "@sunra/client";

const result = await sunra.subscribe("midjourney/v8.2/text-to-image", {
  input: {
  	prompt: '',
  	image_references: null,
  	aspect_ratio: null,
  	hd: false,
  	stylize: null,
  	style: null,
  	exp: null,
  	chaos: null,
  	weird: null,
  	seed: null,
  	stop: null,
  	tile: null,
  	sref: null,
  	style_weight: null,
  	sv: null,
  	personalize: null,
  	image_weight: null
  },
  logs: true,
  onQueueUpdate: (update) => {
    console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`);
  },
});
console.log(result.data);
console.log(result.requestId);
```



### Python



```python
import sunra_client

result = sunra_client.subscribe(
    "midjourney/v8.2/text-to-image",
    arguments={
        "prompt": "",
        "image_references": None,
        "aspect_ratio": None,
        "hd": False,
        "stylize": None,
        "style": None,
        "exp": None,
        "chaos": None,
        "weird": None,
        "seed": None,
        "stop": None,
        "tile": None,
        "sref": None,
        "style_weight": None,
        "sv": None,
        "personalize": None,
        "image_weight": None
    },

    with_logs=True,
    on_enqueue=print,
    on_queue_update=print,
)
print(result)
```



### Java



```java
import ai.sunra.client.*;
import java.util.Map;
import com.google.gson.JsonObject;

var client = SunraClient.withEnvCredentials();

var response = client.subscribe(
    "midjourney/v8.2/text-to-image",
    SubscribeOptions.<JsonObject>builder()
        .input(Map.of(
            "prompt", "",
            "image_references", null,
            "aspect_ratio", null,
            "hd", false,
            "stylize", null,
            "style", null,
            "exp", null,
            "chaos", null,
            "weird", null,
            "seed", null,
            "stop", null,
            "tile", null,
            "sref", null,
            "style_weight", null,
            "sv", null,
            "personalize", null,
            "image_weight", null))

        .resultType(JsonObject.class)
        .onQueueUpdate(update -> System.out.printf(
            "\nStatus Update: %s, Request ID: %s%n",
            update.getStatus(),
            update.getRequestId()
        ))
        .logs(true)
        .build()
);

System.out.println("Completed!");
System.out.println(response.getData());
  
```



### Kotlin



```kotlin
import ai.sunra.client.kt.*
import com.google.gson.JsonObject

val client = createSunraClient()

val response = client.subscribe<JsonObject>(
    endpointId = "midjourney/v8.2/text-to-image",
    input = mapOf(
            "prompt" to "",
            "image_references" to null,
            "aspect_ratio" to null,
            "hd" to false,
            "stylize" to null,
            "style" to null,
            "exp" to null,
            "chaos" to null,
            "weird" to null,
            "seed" to null,
            "stop" to null,
            "tile" to null,
            "sref" to null,
            "style_weight" to null,
            "sv" to null,
            "personalize" to null,
            "image_weight" to null),
    options = ai.sunra.client.kt.SubscribeOptions(logs = true),
    onUpdate = { update ->
        println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}")
    }
)

println("Completed!")
println(response.data)
  
```



### Curl



```bash

curl --request POST \
  --url https://api.sunra.ai/v1/queue/midjourney/v8.2/text-to-image \
  --header "Authorization: Key $SUNRA_KEY" \
  --header "Content-Type: application/json" \
  --data '{"prompt":"","image_references":null,"aspect_ratio":null,"hd":false,"stylize":null,"style":null,"exp":null,"chaos":null,"weird":null,"seed":null,"stop":null,"tile":null,"sref":null,"style_weight":null,"sv":null,"personalize":null,"image_weight":null}'
    
```



## Model readme

>