comfyui-mcp
Version:
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),
35 lines (31 loc) • 1.76 kB
YAML
# ERNIE-Image txt2img install manifest — consumable by apply_manifest.
# Sliced from the ernie monolith's "ERNIE TEXT TO IMAGE" pipeline (groups
# un-bypassed into a standalone graph). Verified: renders headlessly via /prompt.
# Mirror base: https://huggingface.co/Aitrepreneur/FLX/resolve/main (third-party)
# Official weights: https://huggingface.co/Comfy-Org/ERNIE-Image (same filenames)
# comfyui-vrgamedevgirl's nodes.py (FastFilmGrain / FastLaplacianSharpen) imports
# librosa at module load; pin it so the post-proc nodes register. See ernie pack.
pip:
- librosa
custom_nodes:
- https://github.com/city96/ComfyUI-GGUF
- https://github.com/rgthree/rgthree-comfy
- https://github.com/yolain/ComfyUI-Easy-Use
- https://github.com/kijai/ComfyUI-KJNodes
- https://github.com/cubiq/ComfyUI_essentials
- https://github.com/wallish77/wlsh_nodes
- https://github.com/vrgamegirl19/comfyui-vrgamedevgirl
- https://github.com/ClownsharkBatwing/RES4LYF
models:
# UNet (GGUF) — ERNIE-Image-Turbo DiT
- url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/ernie-image-turbo-Q8_0.gguf
local_path: unet/ernie-image-turbo-Q8_0.gguf
# Text encoder — Ministral-3-3B (CLIP type flux2)
- url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/ministral-3-3b.safetensors
local_path: text_encoders/ministral-3-3b.safetensors
# Prompt enhancer — 3B LLM (optional, toggled by the ENHANCE PROMPT boolean)
- url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/ernie-image-prompt-enhancer.safetensors
local_path: text_encoders/ernie-image-prompt-enhancer.safetensors
# VAE — Flux 2 VAE
- url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/flux2-vae.safetensors
local_path: vae/flux2-vae.safetensors