comfyui
由 xtopher86 提供
Image & Video Generation简介
Send a workflow request to ComfyUI and return image results.
描述
该技能的功能
Sends a JSON workflow to a running ComfyUI server and returns the generated image as a URL or base64 string. Connects over HTTP using configurable host, port, and optional basic auth credentials.
Lets agents drive ComfyUI image generation without manual UI interaction, making it composable with other automated steps.
何时使用
- Triggering image generation from an AI agent conversation
- Automating batch image workflows without opening the ComfyUI UI
- Integrating ComfyUI output into a larger multi-step pipeline
- Testing workflow JSON changes programmatically
- Retrieving generated images for downstream processing or storage
示例工作流
User asks: Run this ComfyUI workflow and give me the output image
- 1
Load the workflow JSON object
- 2
POST the workflow to the ComfyUI /run endpoint at the configured host and port
- 3
Receive the JSON response from the server
- 4
Extract the image field containing the URL or base64 string
Image URL or base64 string ready for display or further processing
前置要求
- ComfyUI server installed and running with the /run endpoint exposed
- COMFYUI_USER and COMFYUI_PASS credentials if the server requires basic auth
安装
clawhub install xtopher86/comfyui-request运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。