comfyui-mcp/packs/wan-longer-videos-v2v/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-longer-videos-v2v
display_name: WAN 2.2 Longer Videos — Video Base to Video
family: wan
kind: video
description: >-
  WAN 2.2 longer-video VIDEO-BASE-TO-VIDEO pipeline — load an existing clip
  (VHS_LoadVideo) and extend it into a longer sequence by stitching successive
  generated segments. Uses GGUF quantized A14B I2V (High/Low Noise) UNets +
  umt5-xxl text encoder and Lightning 4-step LoRAs for fast sampling.
  Single-purpose graph sliced from the wan-longer-videos monolith (one pipeline,
  no group toggles). Q4_K_S quant by default (see notes for higher-quality tiers).
vram: "<12GB (Q4_K_S); 12-24GB with Q5_K_S, 24GB+ with Q8_0"
workflow: workflow.json
skill: wan-t2v-video
# WAN 2.2 A14B GGUF video generation is VRAM-hungry; reserving VRAM avoids OOM
# when the GGUF UNet + VAE decode run back to back.
launch_args:
  - "--reserve-vram"
  - "2"
sources:
  mirror: https://huggingface.co/Aitrepreneur/FLX
  installer: WAN2_2-ULTRA-MODELS-NODES_INSTALL.bat
  wan: https://huggingface.co/Wan-AI
notes:
  - Run the generated installer from your ComfyUI root (the folder containing
    custom_nodes/ and models/).
  - Sliced + un-bypassed from the monolith's "WAN 2.2 LONGER VIDEO BASE TO VIDEO".
  - Load a source video via the VHS_LoadVideo node before queueing.
  - GGUF VRAM tiers — this pack installs the -Q4_K_S variants (8.2GB per UNet,
    the <12GB tier). For more headroom/quality, replace the
    unet/Wan2.2-*-Q4_K_S.gguf models with the -Q5_K_S (12-24GB) or -Q8_0 (24GB+)
    variants from the same Aitrepreneur/FLX repo and re-point the
    UnetLoaderGGUF nodes in workflow.json.
  - "Torch not compiled with CUDA fix: if generation errors with \"Torch not
    compiled with CUDA enabled\", a CPU-only torch was installed. Reinstall the
    CUDA build into the ComfyUI python (portable build):
    python_embeded\\python.exe -m pip install --force-reinstall torch torchvision
    torchaudio --index-url https://download.pytorch.org/whl/cu124"
post_install:
  - Restart ComfyUI (or use ComfyUI-Manager -> Install missing custom nodes for
    any node Python deps).
  - Load workflow.json.