comfyui-mcp/packs/z-image-turbo-txt2img/manifest.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),

# Z-Image-Turbo txt2img install manifest — consumable by apply_manifest.
# Sliced from the z-image-turbo monolith's "Z-IMAGE TURBO TEXT TO IMAGE" pipeline
# (un-bypassed into a standalone graph). Verified: renders headlessly via /prompt.
# Mirror base: https://huggingface.co/Aitrepreneur/FLX/resolve/main  (third-party)

# comfyui-vrgamedevgirl's nodes.py (FastFilmGrain / FastLaplacianSharpen) imports
# librosa at module load; pin it so the post-proc nodes register.
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/vrgamegirl19/comfyui-vrgamedevgirl
  - https://github.com/ClownsharkBatwing/RES4LYF
  - https://github.com/ChangeTheConstants/SeedVarianceEnhancer

models:
  # UNet (GGUF) — Z-Image-Turbo DiT
  - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/z_image_turbo-Q8_0.gguf
    local_path: unet/z_image_turbo-Q8_0.gguf
  # Text encoder — Qwen3-4B (CLIP type qwen_image)
  - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/Qwen3-4B-UD-Q6_K_XL.gguf
    local_path: text_encoders/Qwen3-4B-UD-Q6_K_XL.gguf
  # VAE — z-image VAE (saved as z-image-ae.safetensors to avoid the Flux ae clash)
  - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/ae.safetensors
    local_path: vae/z-image-ae.safetensors