HunyuanVideo

Tencent's large text-to-video generation model, with weights and inference code you run yourself.

FreeProprietaryLinuxCommand line
Official websitegithub.com

These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.

About HunyuanVideo

HunyuanVideo is Tencent's large video generation model. The repository contains the PyTorch model definitions, the pre-trained weights and the sampling code, so you can generate video from text prompts on your own hardware. A command-line sampling script and a Gradio web interface are included.

It suits researchers and technically confident users with powerful GPUs who want to run a video model locally instead of paying for a hosted service. Setup is done through Python and its requirements file, and the weights are released under Tencent's own community licence rather than a standard open-source licence.

Strengths

  • Model weights and inference code are published
  • Runs locally with no per-video fees
  • Includes a Gradio web interface as well as a sampling script

Limitations

  • Needs a high-end GPU with a lot of memory
  • Custom licence, not OSI open source
  • Python setup aimed at technical users

Details

Pricing
FreeFree to download, under the Tencent Hunyuan Community License.
License
Proprietary (Tencent Hunyuan Community License)
Developer
Tencent Hunyuan
Platforms
Linux, Command line
How it runs
Downloadable app
Account
Not required
Works offline
Yes
Best suited for
Running a text-to-video model on your own GPU
Last verified
Added

Alternatives to HunyuanVideo

Compare all

Software that can replace HunyuanVideo for an important use case, and what changes if you switch.

  • Wan 2.2

    Open, advanced large-scale video generation model for local use.

    FreeOpen sourceWindowsLinuxCommand line

    Wan 2.2 is Apache-2.0 licensed with variants sized to available GPU memory and runs on Windows and Linux, though it has no official end-user GUI.

  • Wan2GP

    A local AI video generator built to run open video and image models on low-memory GPUs.

    FreeProprietaryWindowsLinux

    Wan2GP runs several open video models from one app on low-memory consumer GPUs and adds image models and plugins, though generation is slow on modest hardware.

  • LTX-2

    Open local video model that generates synchronized audio and video.

    FreeProprietaryWindowsLinuxCommand line

    LTX-2 generates synchronized audio and video together, runs on Windows and Linux and includes an official LoRA trainer, but its licence is also non-standard.

  • CogVideoX

    Open text-to-video and image-to-video generation models with inference and fine-tuning code.

    FreeProprietaryLinuxCommand line

    CogVideoX adds image-to-video alongside text-to-video with fine-tuning code and online demos, but it still needs a powerful GPU and has its own weight licence.

  • Mochi 1 (Genmo)

    Open state-of-the-art video generation model from research lab Genmo.

    FreeOpen sourceWindowsLinuxCommand line

    Mochi 1 has Apache-2.0 open weights and runs on consumer GPUs through ComfyUI integration, but its repository shows no activity since late 2025.

  • Open-Sora

    An open-source video generation project releasing models, training code and tools for text-to-video.

    FreeProprietaryLinuxCommand line

    Open-Sora publishes models, training code and a Gradio interface for text-to-video, but it needs powerful GPUs and machine learning experience to set up.

  • FramePack

    Local image-to-video generator that predicts frames progressively so it runs on consumer GPUs.

    FreeOpen sourceWindowsLinux

    FramePack is Apache-2.0 and turns a still image into video on a gaming GPU on Windows or Linux, but it does image-to-video rather than text-to-video.

HunyuanVideo as an alternative

Listings that name HunyuanVideo as an alternative.

  • Kling AI

    An AI studio for generating images and videos from text, images and references.

    FreemiumProprietaryWeb

    HunyuanVideo publishes weights and inference code so you run text-to-video on your own GPU without per-video fees, under a custom non-OSI licence.

  • Vidu

    An AI video generator that makes clips from text prompts, images and reference material.

    FreemiumProprietaryWeb

    HunyuanVideo is Tencent's text-to-video model run locally on a high-end GPU with no per-video fees, under a custom licence and Python setup.

Similar software

Related functionality, not necessarily a direct replacement.

Report a wrong fact or a dead link on this listing