---
language: en
license: other
tags:
  - text-to-video
  - hunyuan
  - character-consistency
---

# HunyuanVideo + HunyuanCustom + HunyuanVideo-I2V — partial mirror

**Organization:** [WindstormLabs](https://huggingface.co/WindstormLabs)  
**Used by:** [SceneMachine](https://huggingface.co/SceneMachine)

SceneMachine is a sub-project of Windstorm Labs. This repo hosts shared AI/ML infrastructure used by SceneMachine and reusable by future Windstorm Labs sub-projects.

## What this is

Partial mirror of Tencent's HunyuanVideo family. Reserved for SceneMachine Stack B (alternate character-consistency path via Hunyuan's built-in identity preservation, no LoRA needed). Provider workflow not yet wired in SceneMachine; weights staged here for future use.

## Upstream source

Primary distribution: https://huggingface.co/Tencent-Hunyuan/HunyuanVideo

This repo is a **mirror**. License terms of the upstream apply unchanged.

**Primary license owner(s):** Tencent (HunyuanVideo Community License)

## Files

| Filename | Size |
|---|---|
| `HunyuanVideo/hunyuan-video-t2v-720p/vae/pytorch_model.pt` | 0.99 GB |
| `HunyuanVideo-I2V/hunyuan-video-i2v-720p/vae/pytorch_model.pt` | 0.99 GB |
| `HunyuanVideo-I2V/hunyuan-video-i2v-720p/lora/embrace_kohaya_weights.safetensors` | 0.65 GB |
| `HunyuanVideo-I2V/hunyuan-video-i2v-720p/lora/hair_growth_kohaya_weights.safetensors` | 0.65 GB |

**Total: 3.28 GB**

## Related repos

- The full SceneMachine model stack: search the [SceneMachine HF collection](https://huggingface.co/SceneMachine).
- Shared encoders and Wan VAE: [`WindstormLabs/wan22-encoders`](https://huggingface.co/WindstormLabs/wan22-encoders).
- Speed LoRAs: [`WindstormLabs/wan22-loras`](https://huggingface.co/WindstormLabs/wan22-loras).

## Provenance

Mirror created 2026-05-13 from local working copy on the SceneMachine development rig. Hashes preserved via HF's content-addressed storage.

🤖 Repo and README generated by [Claude Code](https://claude.com/claude-code) during a SceneMachine CTO session.