Skip to main content
Run any Skill in Manus
with one click

comfyui

Stars4
Forks0
UpdatedJuly 7, 2026 at 05:45

Drive a local ComfyUI instance to generate images and videos from natural language — no manual node wiring. Discovers installed models dynamically and auto-builds runnable API-format workflows, then submits/polls/downloads the result. Use when the user wants to generate / produce an image or video locally, "用 ComfyUI 出图/出视频", text-to-image, image-to-video, run a ComfyUI workflow, 文生图, 图生视频, 本地生图, or batch-generate media. Model- agnostic (Z-Image, FLUX, SD/SDXL checkpoints, Wan 2.2 video, …); tuned for macOS / Apple Silicon (MPS). For generic backend-agnostic image gen with no named backend, `media-gen` routes the choice; call comfyui directly when the user wants local/offline control, a specific local model, video, or a custom ComfyUI workflow.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

File Explorer
88 files
SKILL.md
readonly