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 + 参考图像输入
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-flex-text-to-image: 可调步数 + 引导；通过 remix 最多 8 张源图；最佳排版
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt
- flux-2-max-remix-image: 用于一致编辑源图的最高质量 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: 提示词遵循能力强的最高质量 FLUX.2 图像生成
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt, aspect_ratio
- flux-2-pro-remix-image: Pro 品质 + 输入图像作为风格/内容种子
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-pro-text-to-image: 零配置旗舰；自动提示词增强
  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: 生成一张写实风格的宇航员抱着猫的摄影棚人像，戏剧性轮廓光，精细细节。
/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，并保存返回的 Task ID。
GET /api/v1/flux_2/remix_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/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，并保存返回的 Task ID。
GET /api/v1/flux_2/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。