Saltar al contenido
TakoAPI
Volver a skills

comfy-ai

por tullyhu

Web & Frontend Development
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

Edited image returned as a media attachment in chat

Requisitos

  • 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

Instalación

clawhub install tullyhu/comfy-ai

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces