← 返回 Skills 市场
dihan

ComfyUI Skill

作者 Dihan · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
912
总下载
3
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install comfy-ui
功能描述
Generate high-quality images using a local ComfyUI instance. Use when the user wants private, powerful image generation via their own hardware and custom wor...
使用说明 (SKILL.md)

ComfyUI Local Skill

This skill allows OpenClaw to generate images by connecting to a ComfyUI instance running on the local network.

Setup

  1. Server Address: Set the COMFYUI_SERVER_ADDRESS environment variable to your PC's IP and port (e.g., http://192.168.1.119:8189).
  2. API Mode: Ensure "Enable Dev mode" is turned on in your ComfyUI settings to allow API interactions.

Usage

Generate an Image

Run the internal generation script with a prompt:

python3 {skillDir}/scripts/comfy_gen.py "your image prompt" $COMFYUI_SERVER_ADDRESS

Use a Custom Workflow

Place your API JSON workflows in the workflows/ folder, then specify the path:

python3 {skillDir}/scripts/comfy_gen.py "your prompt" $COMFYUI_SERVER_ADDRESS --workflow {skillDir}/workflows/my_workflow.json

Features

  • SDXL Default: Uses a high-quality SDXL workflow (Juggernaut XL) by default.
  • Auto-Backup: Designed to save images to image-gens/ and can be configured to sync to local document folders.
  • Custom Workflows: Supports external API JSON workflows saved in the workflows/ folder. The script will automatically try to inject your prompt and a random seed into the workflow nodes.

Implementation Details

The skill uses a Python helper (scripts/comfy_gen.py) to handle the WebSocket/HTTP handshake with the ComfyUI API, queue the prompt, and download the resulting image.

ComfyUI Image Generation Notes:

  1. Server Address:

    • The ComfyUI server address needs to be passed as a direct argument to the comfy_gen.py script after the prompt, not just as an environment variable.
    • Example: python3 ... "Your prompt" http://192.168.1.119:8189 ...
  2. Workflow Paths:

    • When specifying a workflow file path that contains spaces or special characters, it must be enclosed in single quotes to be parsed correctly by the script.
    • Example: --workflow '/path/to/your/workflow file name.json'
  3. Lora Weight Control:

    • The current comfy_gen.py script does not appear to have a direct parameter for controlling Lora weights (e.g., setting 'l1lly' Lora to 0.90). This might need to be configured within the workflow JSON itself, or require modifications to the script or workflow.
  4. Output Filenames:

    • Generated images might be saved with temporary names (e.g., ComfyUI_temp_...png) rather than more descriptive ones by default.
  5. ComfyUI Setup:

    • Ensure "Enable Dev mode" is turned on in ComfyUI settings for API interactions.
安全使用建议
This skill appears to do what it says: it posts a workflow JSON to a ComfyUI server and downloads the resulting image to image-gens/. Before installing, ensure the COMFYUI_SERVER_ADDRESS points to a trusted, local ComfyUI instance (do not point it at an untrusted remote host). The script trusts the ComfyUI server's response for filenames and will write image files under image-gens/ without sanitizing filename strings — a malicious or remote server could cause unexpected file writes (path traversal or overwriting) or serve unwanted content. If you will use non-local servers, review or harden the script (sanitize filenames, validate server host, restrict target directory). Also review included workflow JSONs for prompts or model names you may not want; the workflows contain explicit prompts/negative prompts and model file references. Finally, confirm 'Enable Dev mode' in ComfyUI only when you trust the host and network.
功能分析
Type: OpenClaw Skill Name: comfy-ui Version: 1.0.0 The skill is classified as suspicious due to several vulnerabilities in `scripts/comfy_gen.py`. The script allows for arbitrary file reading via the `--workflow` argument, enabling an attacker to instruct the agent to load and potentially exfiltrate the content of any JSON file on the system. Additionally, the script permits connecting to an arbitrary `server` address, which could be abused for internal network scanning or connecting to malicious external hosts. There is also a potential shell injection vulnerability if the OpenClaw agent does not properly sanitize or quote user-provided arguments when executing the `python3` command as instructed in `SKILL.md`.
能力评估
Purpose & Capability
The skill's name/description (local ComfyUI image generation) matches the included Python script and example workflows. The only required environment variable (COMFYUI_SERVER_ADDRESS) and the workflow files are appropriate for the stated purpose.
Instruction Scope
The SKILL.md stays within the stated purpose (connect to a ComfyUI server, post workflows, download images). Small inconsistencies: SKILL.md emphasizes setting COMFYUI_SERVER_ADDRESS as an env var, but the script requires the server address as a positional argument (the SKILL.md examples use the env var as an argument, so this is workable). The documentation mentions an 'Auto-Backup' sync feature but no code implements syncing beyond saving to image-gens/.
Install Mechanism
Instruction-only with bundled scripts and workflows; there is no install spec or external downloads. Nothing is written to disk by an installer step prior to use beyond the script saving generated images at runtime.
Credentials
Only COMFYUI_SERVER_ADDRESS is required, which is proportional to a local-server integration. No unrelated credentials, secrets, or config paths are requested.
Persistence & Privilege
The skill does not request permanent/always-on inclusion and does not modify other skills or system configurations. It only writes generated images to an image-gens/ folder in its working directory.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install comfy-ui
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /comfy-ui 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the ComfyUI skill
元数据
Slug comfy-ui
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

ComfyUI Skill 是什么?

Generate high-quality images using a local ComfyUI instance. Use when the user wants private, powerful image generation via their own hardware and custom wor... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 912 次。

如何安装 ComfyUI Skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install comfy-ui」即可一键安装,无需额外配置。

ComfyUI Skill 是免费的吗?

是的,ComfyUI Skill 完全免费(开源免费),可自由下载、安装和使用。

ComfyUI Skill 支持哪些平台?

ComfyUI Skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 ComfyUI Skill?

由 Dihan(@dihan)开发并维护,当前版本 v1.0.0。

💬 留言讨论