Visual Muse

ComfyUI 图像生成工坊 — 用自然语言描述需求，自动生成高质量 AI 图片。支持 SDXL/Flux 多模型、风格模板自动匹配、批量生成、质量评分。说「画一张图」即可触发。

This skill is plausible for local ComfyUI-based image generation, but review and take precautions before running its setup scripts: - Inspect scripts (setup.sh, paint-dispatch.sh, quick-generate.sh, switch-painter-model.sh) line-by-line. They will clone repos, pip install torch and other packages, and download multi-gigabyte model files. - Note that some scripts hardcode http://host.docker.internal:8188 instead of using COMFYUI_API_URL; if your ComfyUI runs elsewhere update those invocations first. - The setup and helper scripts copy files into ~/.openclaw/workspace and create ~/ai-studio, and switch-painter-model.sh runs docker exec / docker restart on the openclaw-gateway container—only run these if you trust the environment and have backups (or run in an isolated VM/container). - The skill references external hosts (GitHub, HuggingFace and mirrors, ghfast.top, hf-mirror.com, ofox.ai, a Telegram bot). Expect network traffic to those endpoints when installing or when invoking model-switching features. - If you only want the prompt-generation/runtime behavior, avoid running the full setup; instead run the specific scripts you reviewed or adapt the Python tools to point to your existing ComfyUI instance. - If unsure, run the installer in a disposable VM/container, or manually perform the steps after verifying each remote URL and command. Do not provide unrelated credentials—no extra API keys are required by the skill itself, but gateway/container operations may rely on credentials held by your system.

Type: OpenClaw Skill Name: visual-muse Version: 1.4.0 The visual-muse skill bundle is a legitimate and well-structured toolset for integrating local ComfyUI image generation into the OpenClaw environment. It includes comprehensive setup scripts (scripts/setup.sh) for installing ComfyUI and models, as well as specialized Python and Bash tools (tools/comfyui-client.py, tools/paint-dispatch.sh) for API interaction. The agent instructions (SOUL.md) are notably security-conscious, explicitly forbidding the AI from writing its own scripts, installing unauthorized packages, or modifying the workspace. While it includes scripts that interact with Docker (scripts/switch-painter-model.sh), these are intended for user-initiated configuration and align with the stated purpose of managing a local AI workshop.