comfyui-mcp/packs/z-image-turbo-inpainting/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-turbo-inpainting
display_name: Z-Image-Turbo — Inpainting
family: z-image
kind: inpaint
description: >-
  Z-Image-Turbo (Alibaba Tongyi, distilled S3-DiT) inpainting — repaint a masked
  region of an input image from a text prompt in ~8-14 steps at cfg 1. Uses a Qwen
  text encoder (not CLIP/T5). Single-purpose inpainting graph sliced from the
  z-image-turbo monolith (one pipeline, no group toggles).
vram: "<8GB"
workflow: workflow.json
skill: z-image-txt2img
launch_args: []
sources:
  model: https://huggingface.co/Comfy-Org/z_image_turbo
  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 TURBO INPAINTING".
  - Load an image and paint a mask (LoadImage / mask editor); the masked area is
    regenerated from the prompt.
  - 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).
  - Load workflow.json.