본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

comfy-ai

tullyhu 제작

Web & Frontend Development
—아직 평가 없음
내 평가

요약

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

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

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

에이전트
  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

출력

Edited image returned as a media attachment in chat

요구 사항

  • 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

설치

clawhub install tullyhu/comfy-ai

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크