# kijai/ComfyUI-HunyuanVideoWrapper

Repository: https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
Canonical: https://ross.abutalabs.com/products/comfyui-hunyuanvideowrapper
Language: Python
License Family: other
Last push: 2025-08-20T08:38:14+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 37, release rhythm 35, longevity 45
- inputs: {"age_days": 638, "days_push": 378, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2597, forks 205 (observed 2026-08-28T04:07:03.221409+00:00)

## What it is
A set of custom ComfyUI nodes that wrap Tencent's HunyuanVideo text-to-video and image-to-video diffusion model for use inside ComfyUI workflows. It provides model loading with fp8 scaled quantization, LoRA support, keyframe control, and early-access experimental features ahead of the native ComfyUI implementation.

## Use cases
- generate videos from text prompts in ComfyUI
- run HunyuanVideo locally on my own GPU
- create image-to-video animations with AI
- use LoRAs with HunyuanVideo in ComfyUI
- try new HunyuanVideo features before they land in native ComfyUI
- run the video model with fp8 quantization to fit limited VRAM
- control keyframes in AI video generation

## When to choose
- You want early access to new HunyuanVideo capabilities such as official I2V, keyframe control LoRAs, or manual memory management that are not yet available natively
- You already work in ComfyUI and want HunyuanVideo integrated into your node workflows
- You need the fp8 scaled weights option or the alternative native text-encoding path

## When to avoid
- You only need standard text-to-video or image-to-video generation, since the native ComfyUI implementation now supports most core features
- You want a standalone video generator with its own UI rather than a ComfyUI node pack
- You need long-term guaranteed support, as the maintainer prioritizes native implementation and treats these nodes mainly as a testing ground

## Facets
- artifact type: plugin
- maturity: active
- function: machine-learning, video-processing, stable-diffusion
- domain: artificial-intelligence, machine-learning, deep-learning, media
- platform: python, cross-platform
- tags: comfyui, custom-nodes, video-generation, text-to-video, image-to-video, diffusion-models, hunyuanvideo, lora, fp8-quantization, generative-ai, video, gpu, desktop

## Member repositories
- kijai/ComfyUI-HunyuanVideoWrapper (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:03.221409+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 2026-08-30T02:22:13.126608+00:00, confidence not recorded.
  - readme: https://github.com/kijai/ComfyUI-HunyuanVideoWrapper (fetched 2026-08-28T04:07:03.221409+00:00, sha c2d158d46f81)
- Data as of 2026-08-30T08:39:29.467469+00:00.