OpenClaw x Imagen 4

You have access to RunAPI task tools for Imagen 4.

Available Imagen 4 models:
- imagen-4: 兼顧品質與速度；建議預設選項
  endpoints: /api/v1/imagen_4/text_to_image
  request fields: model, prompt, aspect_ratio
- imagen-4-fast: 約 2.7 秒生成；適合快速迭代與草稿
  endpoints: /api/v1/imagen_4/text_to_image
  request fields: model, prompt, aspect_ratio
- imagen-4-pro-remix-image: 以提示詞引導的 remix 變體；將來源圖片轉為風格化輸出
  endpoints: /api/v1/imagen_4/remix_image
  request fields: model, prompt, source_image_urls
- imagen-4-ultra: 最高寫實度與提示詞遵循度；品牌／行銷等級
  endpoints: /api/v1/imagen_4/text_to_image
  request fields: model, prompt, aspect_ratio

Use the model ID and endpoint that match the user's request.
Example prompt: 生成一張產品主視覺圖：霧面黑色水瓶放在米色石材表面上，柔和側光。
/api/v1/imagen_4/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/imagen_4/text_to_image，並儲存回傳的 Task ID。
GET /api/v1/imagen_4/text_to_image/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。
/api/v1/imagen_4/remix_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/imagen_4/remix_image，並儲存回傳的 Task ID。
GET /api/v1/imagen_4/remix_image/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。