UNPKG

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 (54 loc) • 3.46 kB
# Z-Image Turbo XY-Plot (LoRA comparison) install manifest — consumable by apply_manifest (src/services/manifest.ts). # Ground truth: XY-PLOT-LORA-Z-IMAGE-TURBO-MODELS-NODES_INSTALL.bat # (cross-checked: XY-PLOT-LORA-Z-IMAGE-TURBO-ULTRA-COMFYUI-MANAGER_AUTO_INSTALL.bat, XY-PLOT-LORA-Z-IMAGE-TURBO-AUTO_INSTALL-RUNPOD.sh). # Reconciled against XY-PLOT-LORA-Z-IMAGE-WORKFLOW.json (workflow = source of truth). # Mirror base: https://huggingface.co/Aitrepreneur/FLX/resolve/main # Official Z-Image Turbo weights: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo # # GGUF QUANT TIER: the installer prompts Q5_K_S (GPUs <8GB, recommended) / # Q6_K (8-12GB) / Q8_0 (12-16GB+) for the Z-Image Turbo UNet. This manifest ships # the Q5_K_S tier active (matches the pack's <8GB target); the bundled workflow # selects z_image_turbo-Q8_0.gguf, so uncomment the Q8_0 line below to match it # exactly, or just pick your tier's GGUF in the UnetLoaderGGUF node after install. # # This pack compares USER-TRAINED Z-Image LoRAs on an XY grid. The LoRAs the # workflow references (e.g. Margot-Robbie-Z3_*.safetensors) are user-supplied and # are NOT downloaded here — drop your own trained LoRAs into models/loras/. pip: [] custom_nodes: - https://github.com/ltdrdata/ComfyUI-Manager.git - 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/TinyTerra/ComfyUI_tinyterraNodes # --- Shared Z-Image Turbo node bundle (cloned by the installer; not used by # this XY-plot workflow, but kept for parity with the base Turbo pack) --- - https://github.com/ssitu/ComfyUI_UltimateSDUpscale - https://github.com/cubiq/ComfyUI_essentials - https://github.com/wallish77/wlsh_nodes - https://github.com/ClownsharkBatwing/RES4LYF models: # --- Text encoder (CLIPLoaderGGUF, lumina2) --- - 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 (VAELoader) --- - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/ae.safetensors local_path: vae/z-image-ae.safetensors # --- Diffusion UNet (UnetLoaderGGUF) — Q5_K_S tier active (<8GB, recommended) --- - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/z_image_turbo-Q5_K_S.gguf local_path: unet/z_image_turbo-Q5_K_S.gguf # Q6_K tier (8-12GB) — uncomment to use, comment the Q5_K_S line above # - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/z_image_turbo-Q6_K.gguf # local_path: unet/z_image_turbo-Q6_K.gguf # Q8_0 tier (12-16GB+, best quality; matches the bundled workflow selection) # - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/z_image_turbo-Q8_0.gguf # local_path: unet/z_image_turbo-Q8_0.gguf # --- Upscalers (in the installer's shared Turbo bundle; NOT used by this # XY-plot comparison workflow — uncomment if you want them) --- # - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/4x-ClearRealityV1.pth # local_path: upscale_models/4x-ClearRealityV1.pth # - url: https://huggingface.co/Aitrepreneur/FLX/resolve/main/RealESRGAN_x4plus_anime_6B.pth # local_path: upscale_models/RealESRGAN_x4plus_anime_6B.pth # --- LoRAs: NONE bundled. Bring your own trained Z-Image LoRAs into # models/loras/ — this workflow compares them on an XY grid. ---