> ## Documentation Index > Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Créer une tâche imagine Midjourney > Utilisez POST /mj/submit/imagine dans CometAPI pour créer des tâches imagine Midjourney avec tous les paramètres Discord, suivre l’état du task_id et activer des effets de mouvement d’image vers vidéo. Utilisez ce endpoint pour démarrer le workflow principal de Midjourney. Chaque étape ultérieure, y compris l’upscale, la variation et le zoom personnalisé, commence par une tâche imagine réussie. ## Ce que la première réponse vous fournit * `result` est l’identifiant de tâche que vous interrogerez ensuite * `code` peut toujours être un code de réussite même lorsqu’il ne s’agit pas d’un `200` au format HTTP ## Workflow principal Envoyez le prompt et stockez l’identifiant de tâche renvoyé. Utilisez [Fetch Single Task](./task-fetching-api/fetch-single-task) jusqu’à ce que la tâche atteigne `SUCCESS`, `MODAL` ou `FAILURE`. Lorsque des boutons apparaissent, utilisez [Action](./action) pour l’upscale, la variation, le reroll, le zoom et les opérations de suivi similaires. ## Modèle facultatif de prompt vidéo Si vous souhaitez du mouvement à partir d’une image source, ajoutez une URL d’image ainsi que des flags vidéo Midjourney dans le prompt, comme `--video` et `--motion`. ## OpenAPI ````yaml api/openapi/image/midjourney/post-imagine.openapi.json POST /mj/submit/imagine openapi: 3.1.0 info: title: Imagine API version: 1.0.0 description: >- Create a Midjourney imagine task through CometAPI and receive a task id for later polling. servers: - url: https://api.cometapi.com security: - bearerAuth: [] paths: /mj/submit/imagine: post: summary: Create a Midjourney imagine task description: >- Submit the primary Midjourney generation request. Poll the returned task id with the fetch endpoint until the task reaches a terminal state. operationId: imagine requestBody: required: true content: application/json: schema: type: object required: - prompt properties: botType: type: string description: >- Bot type to use. `MID_JOURNEY` for Midjourney (default), `NIJI_JOURNEY` for Niji. default: MID_JOURNEY enum: - MID_JOURNEY - NIJI_JOURNEY prompt: type: string description: >- Text prompt for the generation. Supports standard Midjourney parameters such as `--v`, `--ar`, `--stylize`, etc. example: a paper boat floating on calm water at sunrise --v 6.1 accountFilter: type: object description: >- Filter which Midjourney account modes may be used for this task. properties: modes: type: array description: Allowed speed modes, e.g. `FAST`, `RELAX`, or `TURBO`. items: type: string base64Array: type: array description: >- Base64-encoded reference images. Each item should be a data URI such as `data:image/png;base64,xxx`. items: type: string state: type: string description: >- Custom state string. Returned as-is in the task result and webhook callback for your own tracking. default: botType: MID_JOURNEY prompt: a paper boat floating on calm water at sunrise --v 6.1 accountFilter: modes: - FAST examples: Default: summary: Default value: botType: MID_JOURNEY prompt: a paper boat floating on calm water at sunrise --v 6.1 accountFilter: modes: - FAST responses: '200': description: Task accepted. content: application/json: schema: type: object required: - code - description - result properties: code: type: integer description: >- Submission status code. `1` = submitted successfully (`result` carries the task id). `21` = the action opened a confirmation modal; continue with `/mj/submit/modal` using the returned task id. `4` = parameter error; `description` explains the cause. description: type: string properties: type: object properties: discordChannelId: type: string discordInstanceId: type: string result: type: string description: Task id returned after submission. example: code: 1 description: Submission successful result: '1773314942177684' properties: discordChannelId: 5e6ca8e1f40e4de6 discordInstanceId: 5e6ca8e1f40e4de6 x-codeSamples: - lang: Shell label: Default source: | curl https://api.cometapi.com/mj/submit/imagine \ -H "Authorization: Bearer $COMETAPI_KEY" \ -H "Content-Type: application/json" \ -d '{ "botType": "MID_JOURNEY", "prompt": "a paper boat floating on calm water at sunrise --v 6.1", "accountFilter": { "modes": [ "FAST" ] } }' - lang: Python label: Default source: > import os import requests response = requests.post( "https://api.cometapi.com/mj/submit/imagine", headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]}, json={ "botType": "MID_JOURNEY", "prompt": "a paper boat floating on calm water at sunrise --v 6.1", "accountFilter": { "modes": [ "FAST" ] } }, ) task = response.json() print(task["code"], task.get("result")) # code 1 means submitted; result is the task id - lang: JavaScript label: Default source: > const response = await fetch("https://api.cometapi.com/mj/submit/imagine", { method: "POST", headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "botType": "MID_JOURNEY", "prompt": "a paper boat floating on calm water at sunrise --v 6.1", "accountFilter": { "modes": [ "FAST" ] } }), }); const task = await response.json(); console.log(task.code, task.result); // code 1 means submitted; result is the task id components: securitySchemes: bearerAuth: type: http scheme: bearer description: Bearer token authentication. Use your CometAPI key. ````