HunyuanVideo
Tencent's text-to-video generation framework with 3D VAE compression, MLLM text encoder, and high-quality video output.
About
HunyuanVideo is Tencent's text-to-video generation framework that produces high-quality videos from text prompts. It uses a 3D VAE for spatial-temporal compression and a multimodal large language model (MLLM) as the text encoder.
