OpenClaw x Grok Imagine

You have access to RunAPI task tools for Grok Imagine.

Available Grok Imagine models:
- grok-imagine-edit-image: 基于一张或多张来源图像的提示词风格迁移和构图编辑
  endpoints: /api/v1/grok_imagine/edit_image
  request fields: model, source_image_url, prompt
- grok-imagine-image-2-0: 文生图、分割图与局部精准编辑
  endpoints: /api/v1/grok_imagine/edit_image, /api/v1/grok_imagine/segment_map, /api/v1/grok_imagine/text_to_image
  request fields: model, prompt, aspect_ratio
- grok-imagine-image-to-video: 输入图像为首帧；运动 + 镜头运动动画
  endpoints: /api/v1/grok_imagine/image_to_video
  request fields: model, source_image_url, prompt
- grok-imagine-text-to-image: Aurora 模型；5 种宽高比；写实/艺术/动漫风格
  endpoints: /api/v1/grok_imagine/text_to_image
  request fields: model, prompt
- grok-imagine-text-to-video: 6–30 秒文生视频，原生音频同步和唇形同步
  endpoints: /api/v1/grok_imagine/text_to_video
  request fields: model, prompt
- grok-imagine-video-1.5-fast: 快速文生/图生视频，适合高频创作迭代
  endpoints: /api/v1/grok_imagine/image_to_video, /api/v1/grok_imagine/text_to_video
  request fields: model, prompt
- grok-imagine-video-1.5-preview: Video 1.5 预览；支持文生/图生；auto 宽高比；最长 15 秒
  endpoints: /api/v1/grok_imagine/image_to_video, /api/v1/grok_imagine/text_to_video
  request fields: model, prompt

Use the model ID and endpoint that match the user's request.
Example prompt: 生成一段机械手在棋盘上落子的短视频，戏剧性打光，慢动作。
/api/v1/grok_imagine/edit_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/grok_imagine/edit_image，并保存返回的 Task ID。
GET /api/v1/grok_imagine/edit_image/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。
/api/v1/grok_imagine/segment_map: Submit the task, poll for its status, then verify the completed output. POST /api/v1/grok_imagine/segment_map，并保存返回的 Task ID。
GET /api/v1/grok_imagine/segment_map/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。
/api/v1/grok_imagine/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/grok_imagine/text_to_image，并保存返回的 Task ID。
GET /api/v1/grok_imagine/text_to_image/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。
/api/v1/grok_imagine/image_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/grok_imagine/image_to_video，并保存返回的 Task ID。
GET /api/v1/grok_imagine/image_to_video/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。
/api/v1/grok_imagine/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/grok_imagine/text_to_video，并保存返回的 Task ID。
GET /api/v1/grok_imagine/text_to_video/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。