# kijai/ComfyUI-WanVideoWrapper

Repository: https://github.com/kijai/ComfyUI-WanVideoWrapper
Canonical: https://ross.abutalabs.com/products/comfyui-wanvideowrapper
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-05-24T13:07:20+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 84, release rhythm 35, longevity 39
- inputs: {"age_days": 554, "days_push": 101, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6678, forks 688 (observed 2026-08-28T04:09:47.583738+00:00)

## What it is
ComfyUI custom nodes wrapping WanVideo (Wan2.1) and related video generation models. It provides a standalone sandbox for quickly implementing new models and VRAM-efficiency features like block swapping and LoRA offloading.

## Use cases
- generate videos with WanVideo models in ComfyUI
- run Wan2.1 video diffusion models with lower VRAM usage
- apply LoRAs to WanVideo models efficiently
- try new video model features before native ComfyUI support
- use block swapping and async offloading for large video models

## When to choose
- you need a WanVideo model or feature not yet available natively in ComfyUI
- you want faster access to experimental video model features
- you need fine-grained VRAM offloading controls for video generation

## When to avoid
- you only use models and features already supported natively in ComfyUI
- you want a polished, stable video generation service rather than a work-in-progress wrapper
- you cannot run models locally on a GPU

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, machine-learning, llm-inference
- domain: artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: comfyui, custom-nodes, wanvideo, video-generation, diffusion-models, vram-optimization, lora, video, gpu

## Member repositories
- kijai/ComfyUI-WanVideoWrapper (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:47.583738+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:00.749929+00:00, confidence not recorded.
  - readme: https://github.com/kijai/ComfyUI-WanVideoWrapper (fetched 2026-08-28T04:09:47.583738+00:00, sha dc4c3d230dcc)
- Data as of 2026-08-30T08:39:29.467469+00:00.