
Comfyui Video Pipeline
Orchestrates three different video generation engines in ComfyUI and picks the right one based on what you need. Wan 2.2 for highest quality (film-level at 24GB VRAM or 1.3B variant for 8GB), FramePack when you need 60-second videos on just 6GB VRAM, AnimateDiff for fast iteration with motion control LoRAs. The routing logic is smart: it looks at your quality requirements, VRAM availability, video length, and whether you need camera control or first/last frame specification. Includes full post-processing with RIFE interpolation, face enhancement, and deflickering. Honestly, the decision tree alone saves you from having to understand the tradeoffs between these engines yourself.
- skills.sh installs
- 1.3K
- GitHub stars
- 94
- last updated
- Jul 14, 2026
Install
$ npx -y skills add mckruz/comfyui-expert --skill comfyui-video-pipeline --agent claude-codeInstalls into .claude/skills of the current project.
Files
ComfyUI Video Pipeline
Orchestrates video generation across three engines, selecting the best one based on requirements and available resources.
Engine Selection
VIDEO REQUEST
|
|-- Need film-level quality?
| |-- Yes + 24GB+ VRAM → Wan 2.2 MoE 14B
| |-- Yes + 8GB VRAM → Wan 2.2 1.3B
|
|-- Need long video (>10 seconds)?
| |-- Yes → FramePack (60 seconds on 6GB)
|
|-- Need fast iteration?
| |-- Yes → AnimateDiff Lightning (4-8 steps)
|
|-- Need camera/motion control?
| |-- Yes → AnimateDiff V3 + Motion LoRAs
|
|-- Need first+last frame control?
| |-- Yes → Wan 2.2 MoE (exclusive feature)
|
|-- Default → Wan 2.2 (best general quality)
Pipeline 1: Wan 2.2 MoE (Highest Quality)
Image-to-Video
Prerequisites:
wan2.1_i2v_720p_14b_bf16.safetensorsinmodels/diffusion_models/umt5_xxl_fp8_e4m3fn_scaled.safetensorsinmodels/clip/open_clip_vit_h_14.safetensorsinmodels/clip_vision/wan_2.1_vae.safetensorsinmodels/vae/
Sponsors
Details
- Repository
- github.com/mckruz/comfyui-expert
- Categories
- DevOps & CI/CD, Automation & Workflows, Sales & Marketing, Generative Media
- First seen
- Jun 3, 2026