OpenClaw x Flux 2

You have access to RunAPI task tools for Flux 2.

Available Flux 2 models:
- flux-2-flex-remix-image: Flex 控制 + 參考圖片輸入
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-flex-text-to-image: 可調整步數與 guidance；透過 remix 最多 8 張來源圖片；文字排版最佳
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt
- flux-2-max-remix-image: 用於一致編輯來源圖像的最高品質 FLUX.2 remix
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls, aspect_ratio
- flux-2-max-text-to-image: 具備強大提示詞遵循能力的最高品質 FLUX.2 圖像生成
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt, aspect_ratio
- flux-2-pro-remix-image: Pro 品質，以輸入圖片作為風格／內容基礎
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-pro-text-to-image: 免設定的旗艦版；自動提示詞強化
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt

Use the model ID and endpoint that match the user's request.
Example prompt: 生成一張寫實的攝影棚人像：太空人抱著一隻貓，戲劇性輪廓光，細節精緻。
/api/v1/flux_2/remix_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/flux_2/remix_image，並儲存回傳的 Task ID。
GET /api/v1/flux_2/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。
/api/v1/flux_2/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/flux_2/text_to_image，並儲存回傳的 Task ID。
GET /api/v1/flux_2/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。