comfyui-mcp/packs/wan-animate-character/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: wan-animate-character
display_name: WAN Animate 2.2 — Character Replace (standalone)
family: wan
kind: video
description: >-
  WAN Animate 2.2 video-to-video character / motion replacement built on the
  kijai WanVideoWrapper ecosystem. Drives a reference character with the pose,
  expression and motion of a driving video (ViTPose + YOLOv10 detection, SeC
  precise video segmentation for masking, relight LoRA for compositing). Uses the
  14B fp8-scaled WAN Animate model plus the lightx2v step-distill LoRA for fast
  sampling. Single-pipeline graph sliced from the wan-animate monolith (PARAM
  output groups, un-bypassed into a standalone graph — no group toggles). For the
  maintained/recommended character-animation pipeline, prefer the `artokun-flow` pack.
vram: 24GB+
workflow: workflow.json
skill: wan-t2v-video
launch_args: []
sources:
  mirror: https://huggingface.co/Aitrepreneur/FLX
  wanvideo_wrapper: https://github.com/kijai/ComfyUI-WanVideoWrapper
  wan_animate_preprocess: https://github.com/kijai/ComfyUI-WanAnimatePreprocess
  secnodes: https://github.com/9nate-drake/Comfyui-SecNodes
notes:
  - Run the generated installer from your ComfyUI root (the folder containing
    custom_nodes/ and models/). On the Windows portable build that is
    ...\ComfyUI_windows_portable\ComfyUI\.
  - Sliced + un-bypassed from the monolith's WAN Animate pipeline (PARAM-group
    VHS_VideoCombine outputs seed the slice; masking + pose/detection pulled in
    via the backward closure).
  - Requires SageAttention + Triton for the WanVideoWrapper sampler. Install them
    with install_triton_and_sageattention_auto.bat (run from
    ...\ComfyUI_windows_portable\python_embeded\).
  - 'Dtype error "self and mat2 must have the same dtype": delete and re-clone
    kijai/ComfyUI-WanVideoWrapper, then reinstall its requirements.txt with the
    portable python.'
  - 'RTX 5000-series onnxruntime "QuickGelu" / CUDA provider error on the ViTPose
    detection: pin onnxruntime==1.20.1.'
  - Masking has two paths — SeC precise masking (SeC-4B model, manual/prompted)
    or auto masking. SeC is the default; pick the matching mask / background_image
    getter per the in-graph notes.
post_install:
  - Restart ComfyUI (or use ComfyUI-Manager -> Install missing custom nodes for
    any node Python deps).
  - Run install_triton_and_sageattention_auto.bat before first generate.
  - Load workflow.json.