目录

Download Text Encoder

attention 默认改为了torch

flash_atten安装

---

GitHub - Tencent/HunyuanVideo: HunyuanVideo: A Systematic Framework For Large Video Generation Model Training

Download Text Encoder

HunyuanVideo uses an MLLM model and a CLIP model as text encoder.

1. MLLM model (text_encoder folder)

HunyuanVideo supports different MLLMs (including HunyuanMLLM and open-source MLLM models). At this stage, we have not yet released HunyuanMLLM. We recommend the user in community to use