跳到正文
TakoAPI
返回技能列表

comfy-ai

由 tullyhu 提供

Web & Frontend Development
—暂无评分
你的评分

简介

Integrates with local ComfyUI instance at http://192.168.31.7:8000.

描述

该技能的功能

Connects to a local ComfyUI instance to generate images from text prompts or edit uploaded images using a reference workflow. All processing runs on the user's machine using the Flux2-Klein-4B model with VAE and CLIP. Returns generated images directly as chat attachments.

All image generation and editing happens locally, so no prompts or images are sent to external services.

何时使用

  • Generating concept art from a text description
  • Editing a product photo with a new visual style
  • Adding effects or branding elements to an uploaded image
  • Drafting visual mockups without leaving the chat interface
  • Prototyping image variations from a reference photo

示例工作流

输入

User asks: Edit this image [uploads handbag_white.png] to add neon glow and a logo

智能体
  1. 1

    Detects uploaded image in the message

  2. 2

    Copies image to ~/clawd/skills/comfy-ai/input/

  3. 3

    Loads the img2img workflow JSON

  4. 4

    Sends request to local ComfyUI at http://192.168.31.7:8000

  5. 5

    Retrieves generated image from the output folder

输出

Edited image returned as a media attachment in chat

前置要求

  • ComfyUI installed and running at http://192.168.31.7:8000
  • Workflow file at ~/clawd/skills/comfy-ai/image_flux2_klein_image_edit_4b_distilled.json

安装

clawhub install tullyhu/comfy-ai

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。

链接