HunyuanVideo 1.5 Technical Report

TL;DR

HunyuanVideo 1.5 is a lightweight, open-source video generation model that achieves state-of-the-art quality and coherence with only 8.3 billion parameters, enabling efficient use on consumer GPUs.

Contribution

The paper introduces a novel, compact video generation framework with advanced architecture and training techniques, setting new open-source benchmarks.

Findings

Achieves state-of-the-art quality in open-source video generation.

Operates efficiently on consumer-grade GPUs.

Supports high-quality text-to-video and image-to-video tasks.

Abstract

We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.