HunyuanVideo + HunyuanCustom + HunyuanVideo-I2V — partial mirror
Organization: WindstormLabs
Used by: 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/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.
- Shared encoders and Wan VAE:
WindstormLabs/wan22-encoders. - Speed LoRAs:
WindstormLabs/wan22-loras.
Licence
Tencent Hunyuan Community License Agreement. The upstream licence and notice files are reproduced unchanged: LICENSE + Notice for tencent/HunyuanVideo (files under HunyuanVideo/), and LICENSE-HunyuanVideo-I2V + Notice-HunyuanVideo-I2V for tencent/HunyuanVideo-I2V (files under HunyuanVideo-I2V/). The licence does not apply in the European Union, the United Kingdom or South Korea; read it before use.
Provenance
Mirror created 2026-05-13 from a local working copy. Hashes preserved via HF's content-addressed storage.