Tencent-Hunyuan/HunyuanVideo-1.5

Tencent-Hunyuan/HunyuanVideo-1.5

Description: HunyuanVideo-1.5: A leading lightweight video generation model

Language: Python

License: NOASSERTION

Stars: 4474

Forks: 229

Open issues: 33

Created: 2025-11-20T06:15:42Z

Pushed: 2026-04-10T06:14:59Z

Default branch: main

Fork: no

Archived: no

README: [中文文档](./README_CN.md)

HunyuanVideo-1.5

HunyuanVideo-1.5 is a video generation model that delivers top-tier quality with only 8.3B parameters, significantly lowering the barrier to usage. It runs smoothly on consumer-grade GPUs, making it accessible for every developer and creator. This repository provides the implementation and tools needed to generate creative videos.

👏 Join our WeChat and Discord | 💻 Official website Try our model!&nbsp&nbsp

🔥🔥🔥 News

• 🚀 Dec 23, 2025: Fp8 gemm inference is supported! 🔥🔥🔥🆕
• 🚀 Dec 05, 2025: New Release: We now release the 480p I2V step-distilled model, which generates videos in 8 or 12 steps (recommended)! On RTX 4090, end-to-end generation time is reduced by 75%, and a single RTX 4090 can generate videos within 75 seconds. The step-distilled model maintains comparable quality to the original model while achieving significant speedup. See [Step Distillation Comparison](./assets/step_distillation_comparison.md) for detailed quality comparisons. For even faster generation, you can also try 4 steps (faster speed with slightly reduced quality). To enable the step-distilled model, run `generate.py` with the `--enable_step_distill` parameter. See [Usage](#-usage) for detailed usage instructions. 🔥🔥🔥🆕
• 📚 Dec 05, 2025: Training Code & LoRA Tuning Script Released: We now open-source the training code for HunyuanVideo-1.5! The training script (train.py) provides a full training pipeline with support for distributed training, FSDP, context parallel, gradient checkpointing, and more. HunyuanVideo-1.5 is trained using the Muon optimizer, which we have open-sourced in the [Training](#-training) section. If you would like to continue training our model or fine-tune it with LoRA, please use the Muon optimizer. See [Training](#-training) section for detailed usage instructions. 🔥🔥🔥🆕
• 🎉 Diffusers Support: HunyuanVideo-1.5 is now available on Hugging Face Diffusers! Check out Diffusers collection for easy integration. 🔥🔥🔥🆕
• 🚀 Nov 27, 2025: We now support cache inference (deepcache, teacache, taylorcache), achieving significant speedup! Pull the latest code to try it.
• 🚀 Nov 24, 2025: We now support deepcache inference.
• 👋 Nov 20, 2025: We release the inference code and model weights of HunyuanVideo-1.5.

🎥 Demo

🧩 Community Contributions

If you develop/use HunyuanVideo-1.5 in your projects, welcome to let us know.

• Diffusers - HunyuanVideo-1.5 Diffusers: Official Hugging Face Diffusers integration for HunyuanVideo-1.5. Easily use HunyuanVideo-1.5 with the Diffusers library for seamless integration into your projects. See [Usage with Diffusers](#usage-with-diffusers) section for details.

• ComfyUI - ComfyUI: A powerful and modular diffusion model GUI with a graph/nodes interface. ComfyUI supports HunyuanVideo-1.5 with various engineering optimizations for fast inference. We provide a [ComfyUI Usage Guide](./ComfyUI/README.md) for HunyuanVideo-1.5.

• Community-implemented ComfyUI Plugin - comfyui_hunyuanvideo_1.5_plugin: A community-implemented ComfyUI plugin for HunyuanVideo-1.5, offering both simplified and complete node sets for quick usage or deep workflow customization, with built-in automatic model download support.

• LightX2V - LightX2V: A lightweight and efficient video generation framework that integrates HunyuanVideo-1.5, supporting multiple engineering acceleration techniques for fast inference.

• Wan2GP v9.62 - Wan2GP: WanGP is a very low VRAM app (as low 6 GB of VRAM for Hunyuan Video 1.5) supports Lora Accelerator for a 8 steps generation and offers tools to facilitate Video Generation.

• ComfyUI-MagCache - ComfyUI-MagCache: MagCache is a training-free caching approach that accelerates video generation by estimating fluctuating differences among model outputs across timesteps. It achieves 1.7x speedup for HunyuanVideo-1.5 with 20 inference steps.

• OmniWeaving - OmniWeaving: An omni-level unified video generation model built upon HunyuanVideo-1.5, excelling in free-form multimodal composition and reasoning-augmented generation. Specifically, it seamlessly handles a diverse array of tasks, such as Text-to-Video, First-Frame-to-Video, Key-Frames-to-Video, Video-to-Video Editing, Reference-to-Video, Compositional Multi-Image-to-Video, and Text-Image-Video-to-Video.

📑 Open-source Plan

• HunyuanVideo-1.5 (T2V/I2V)
• [x] Inference Code and checkpoints
• [x] ComfyUI Support
• [x] LightX2V Support
• [x] Diffusers Support
• [ ] Release all model weights (Sparse attention, distill model, and SR models)

📋 Table of Contents

• [🔥🔥🔥 News](#-news)
• [🎥 Demo](#-demo)
• [🧩 Community Contributions](#-community-contributions)
• [📑 Open-source Plan](#-open-source-plan)
• [📖 Introduction](#-introduction)
• [✨ Key Features](#-key-features)
• [📜 System Requirements](#-system-requirements)
• [🛠️ Dependencies and Installation](#️-dependencies-and-installation)
• [🧱 Download Pretrained Models](#-download-pretrained-models)
• [📝 Prompt Guide](#-prompt-guide)
• [🔑 Inference](#-inference)
• [Inference with Source Code](#inference-with-source-code)
• [Usage with Diffusers](#usage-with-diffusers)
• [Prompt Enhancement](#prompt-enhancement)
• [Text to Video](#text-to-video)
• [Image to Video](#image-to-video)
• [Command Line Arguments](#command-line-arguments)
• [Optimal Inference Configurations](#optimal-inference-configurations)
• [🎓 Training](#-training)
• [🎬 More Examples](#-more-examples)
• [📊 Evaluation](#-evaluation)
• [📚 Citation](#-citation)
• [🙏 Acknowledgements](#-acknowledgements)
• [🌟…