comfyui-mcp/packs/z-image-base-controlnet/pack.yaml

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),

name: z-image-base-controlnet
display_name: Z-Image Base — ControlNet (Pose / Depth / Canny)
family: z-image
kind: controlnet
description: >-
  Z-Image Base (Alibaba Tongyi, 6B S3-DiT base model) with the Z-Image-Fun ControlNet
  Union: condition generation on Pose, Depth, or Canny control images (preprocessed via
  comfyui_controlnet_aux). Chains the BASE and distilled TURBO models, uses a Qwen text
  encoder (not CLIP/T5), GGUF-quantized to run in <8GB VRAM, with an 8-step distill LoRA
  and a Detailer Daemon detail pass. Single-purpose controlnet graph sliced from the
  z-image-base monolith (no group toggles).
vram: "<8GB"
workflow: workflow.json
skill: z-image-txt2img
launch_args: []
sources:
  model: https://huggingface.co/Aitrepreneur/FLX
  mirror: https://huggingface.co/Aitrepreneur/FLX
notes:
  - Run the generated installer from your ComfyUI root (folder with custom_nodes/
    and models/).
  - Sliced + un-bypassed from the monolith's "Z-IMAGE COMBO CONTROLNET" (Pose /
    Depth / Canny groups).
  - The ControlNet patch is loaded via ModelPatchLoader
    (Z-Image-Fun-Controlnet-Union-2.1.safetensors into models/model_patches/).
  - ControlNet preprocessor weights (depth_anything_v2_vitl, dw-ll_ucoco, yolox_l)
    are not bundled; comfyui_controlnet_aux downloads them on first use.
  - The z-image VAE is saved as z-image-ae.safetensors (its weights differ from
    Flux's ae.safetensors despite the same size).
post_install:
  - Restart ComfyUI (or ComfyUI-Manager -> Install missing custom nodes for any
    node Python deps, incl. comfyui_controlnet_aux and the Detailer Daemon).
  - Load workflow.json.