HERMES AGENT + MIDJOURNEY

在 Hermes Agent 中使用 Midjourney。

Midjourney 擅长高质量 AI 绘画、文生图、图片编辑和把静态图转成短视频。Hermes Agent 通过 RunAPI custom provider 直接调用标准 API,复用聊天用的同一个密钥,无需 Discord bot、浏览器自动化或 ComfyUI。

one API key · Midjourney API · image and video tasks
在 Hermes Agent 中使用 RunAPI 生成 Midjourney 图片。

Requirements:
- Read the API key from RUNAPI_API_KEY.
- Call POST https://runapi.ai/api/v1/midjourney/text_to_image
- Set model to "midjourney-v8.1".
- Set prompt to describe the image.
- The task is async. Poll the returned task_id until status is "completed".
- When done, read the image URL from the response output.
curl -X POST https://runapi.ai/api/v1/midjourney/text_to_image \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "midjourney-v8.1",
    "prompt": "A cinematic product photo of a translucent AI compass on a black desk, dramatic lighting"
  }'
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "midjourney-v8.1"
}
Copy the curl command to test midjourney
HOW IT WORKS

三步在 Hermes Agent 中使用 Midjourney

1

Configure RunAPI

Set RUNAPI_API_KEY in your environment. If Hermes Agent already uses the custom:runapi provider for chat, the same key works for Midjourney image and video tasks.

export RUNAPI_API_KEY=runapi_xxx
2

Call Midjourney

Send a POST request to the Midjourney text_to_image endpoint with model midjourney-v8.1 and a prompt. For editing or animation, switch to edit_image or image_to_video and include a source image URL.

POST /api/v1/midjourney/text_to_image
3

Poll for media

The create endpoint returns a task_id immediately. Poll the task status endpoint or use a callback_url until the generated image or video URL is ready.

GET /api/v1/midjourney/text_to_image/tsk_abc123
PARAMETERS

Midjourney API parameters

参数 类型 说明
model string Required. Use midjourney-v8.1 for text-to-image, midjourney-edit-image for editing, or midjourney-image-to-video for animation.
prompt string Text instruction for image generation, editing, or motion guidance.
source_image_url string Source image URL. Required for edit_image, image_to_video, and image_to_prompt.
image_id string Required for get_seed. The Midjourney image id returned in a completed image response.
callback_url string Optional. Webhook URL that receives a POST when an asynchronous task completes.

Hermes Agent 上的 Midjourney 是什么?

Midjourney is a creative AI image model line known for polished art direction, strong aesthetics, and cinematic visual composition. Through RunAPI, agents can use Midjourney as a normal API: create images from prompts, edit a source image, animate a still frame into video, ask for prompt suggestions from an image, or retrieve a seed for reproducibility.

Midjourney use cases

Creative concept art

Generate cinematic concept art, mood boards, and style exploration images directly from an agent workflow.

Marketing image variations

Create polished campaign visuals, thumbnails, product scenes, and social creatives from a written brief.

Image-to-video motion tests

Animate a selected image into a short video with motion guidance, then hand the result to downstream editing or publishing steps.

常见问题

Midjourney + Hermes Agent questions

Hermes Agent general setup

Not configured yet? Start with the RunAPI setup guide for Hermes Agent.

Hermes Agent setup guide →

Midjourney model catalog

See Midjourney variants, pricing, and API docs.

Midjourney on RunAPI →

今天就在 Hermes Agent 中试用 Midjourney。

Get a free RunAPI key, paste the prompt into Hermes Agent, and generate Midjourney images or videos from your agent workflow.