Перейти к содержимому
TakoAPI
Назад к навыкам

comfy-ui

от dihan

DevOps & Cloud
446Число загрузок по данным clawskills.sh
2Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Generate high-quality images using a local ComfyUI instance.

Описание

Что делает этот навык

Connects OpenClaw to a locally running ComfyUI instance for image generation. Uses an SDXL workflow by default (Juggernaut XL) and supports custom API JSON workflows. Images are saved locally and generation happens entirely on your own hardware.

All generation runs on your own machine, so prompts and images never leave your network and there are no per-image API costs.

Когда его использовать

  • Generating images privately without sending prompts to cloud services
  • Running custom LoRA or fine-tuned model workflows from a home server
  • Batch-generating concept art using saved workflow JSON files
  • Automating image creation as part of a local agent pipeline
  • Producing high-resolution SDXL outputs on dedicated GPU hardware

Пример сценария

ВВОД

User asks: Generate an image of a misty mountain at dawn

АГЕНТ
  1. 1

    Reads COMFYUI_SERVER_ADDRESS from environment

  2. 2

    Calls comfy_gen.py with the prompt and server address

  3. 3

    Script connects to ComfyUI via WebSocket/HTTP and queues the prompt

  4. 4

    Waits for generation to complete and downloads the resulting image

  5. 5

    Saves image to image-gens/ folder and returns the file path

ВЫВОД

Generated image saved locally, file path returned to user

Требования

  • COMFYUI_SERVER_ADDRESS environment variable (e.g. http://192.168.1.119:8189)
  • ComfyUI installed and running locally with Dev mode enabled

Установка

clawhub install dihan/comfy-ui

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки