OpenClaw x Seedream

You have access to RunAPI task tools for Seedream.

Available Seedream models:
- seedream-4.5-edit: 同等写实度 + 蒙版/画笔区域编辑
  endpoints: /api/v1/seedream/edit_image
  request fields: model, prompt, aspect_ratio, output_quality, source_image_urls
- seedream-4.5-text-to-image: 写实输出；稳定人体结构
  endpoints: /api/v1/seedream/text_to_image
  request fields: model, prompt, aspect_ratio, output_quality
- seedream-5-lite-edit: 比 4.5 更强的参考遵循 + 双语排版；更快
  endpoints: /api/v1/seedream/edit_image
  request fields: model, prompt, aspect_ratio, output_quality, source_image_urls
- seedream-5-lite-text-to-image: 实时网络搜索适应时效性提示
  endpoints: /api/v1/seedream/text_to_image
  request fields: model, prompt, aspect_ratio, output_quality
- seedream-5-pro-edit: 面向精致成片的高质量写实图像编辑
  endpoints: /api/v1/seedream/edit_image
  request fields: model, prompt, aspect_ratio, output_quality, source_image_urls
- seedream-5-pro-layer-decomposition: 将单张图片拆分为可编辑底图和透明 PNG 图层
  endpoints: /api/v1/seedream/decompose_layers
  request fields: model, image_url, size, output_format
- seedream-5-pro-text-to-image: 面向精致成片的高质量写实图像生成
  endpoints: /api/v1/seedream/text_to_image
  request fields: model, prompt, aspect_ratio, output_quality
- seedream-v4-edit: 最多 10 张参考图的多图编辑；支持 4K 输出
  endpoints: /api/v1/seedream/edit_image
  request fields: model, prompt, aspect_ratio, output_quality, source_image_urls
- seedream-v4-text-to-image: 1K-4K 写实批量生成；单次最多 6 张
  endpoints: /api/v1/seedream/text_to_image
  request fields: model, prompt, aspect_ratio, output_quality

Use the model ID and endpoint that match the user's request.
Example prompt: 创建一张咖啡店促销社交媒体图，粗体写上 '半价优惠'，暖色调，4K。
/api/v1/seedream/edit_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/seedream/edit_image，并保存返回的 Task ID。
GET /api/v1/seedream/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/seedream/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/seedream/text_to_image，并保存返回的 Task ID。
GET /api/v1/seedream/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/seedream/decompose_layers: Submit the task, poll for its status, then verify the completed output. POST /api/v1/seedream/decompose_layers，并保存返回的 Task ID。
GET /api/v1/seedream/decompose_layers/<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。