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),
62 lines (59 loc) • 2.73 kB
YAML
# comfyui-mcp RunPod image — extra model paths (FAST-RESTART design).
# =============================================================================
# Baked into the image at /opt/ComfyUI/extra_model_paths.yaml and loaded at
# launch via: main.py --extra-model-paths-config /opt/ComfyUI/extra_model_paths.yaml
#
# WHY: ComfyUI software (install + venv + custom_nodes) lives in the IMMUTABLE
# image at /opt/ComfyUI. ONLY user data lives on the /workspace network volume.
# This file points EVERY model category at /workspace/models/<cat> so:
# * your models persist across stop/start (they're on the volume), and
# * Manager's install-model writes downloads to the volume — NOT to the image.
#
# `is_default: true` makes these paths the PRIMARY entries (inserted at the FRONT
# of each category's folder list via folder_paths.add_model_folder_path), so they
# become the DEFAULT download target. Without it, ComfyUI's built-in
# /opt/ComfyUI/models/<cat> (ephemeral, in the image) would stay first and
# Manager downloads would NOT persist.
#
# NOTE: there is deliberately NO `custom_nodes:` key here. custom_nodes must stay
# in the image (immutable software). Mapping custom_nodes to the volume would
# defeat the fast-restart design and the image-baked-nodes contract.
#
# base_path is /workspace, and each value is relative to it (matching ComfyUI's
# own extra_model_paths.yaml.example convention, e.g. `models/checkpoints/`).
# Category KEYS match ComfyUI's folder_names_and_paths keys exactly.
# =============================================================================
comfyui_mcp_volume:
base_path: /workspace
is_default: true
checkpoints: models/checkpoints/
configs: models/configs/
loras: models/loras/
vae: models/vae/
text_encoders: |
models/text_encoders/
models/clip/
diffusion_models: |
models/diffusion_models/
models/unet/
clip_vision: models/clip_vision/
style_models: models/style_models/
embeddings: models/embeddings/
diffusers: models/diffusers/
vae_approx: models/vae_approx/
controlnet: |
models/controlnet/
models/t2i_adapter/
gligen: models/gligen/
upscale_models: models/upscale_models/
latent_upscale_models: models/latent_upscale_models/
hypernetworks: models/hypernetworks/
photomaker: models/photomaker/
classifiers: models/classifiers/
model_patches: models/model_patches/
audio_encoders: models/audio_encoders/
background_removal: models/background_removal/
frame_interpolation: models/frame_interpolation/
geometry_estimation: models/geometry_estimation/
optical_flow: models/optical_flow/
detection: models/detection/