Alternatives to Open-Sora

An open-source video generation project releasing models, training code and tools for text-to-video. The listings below can replace it for an important use case. Each note says what changes if you switch.

Replacements

Listings that take over the same core job as Open-Sora.

  • HunyuanVideo

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

    FreeProprietaryLinuxCommand line

    HunyuanVideo publishes Tencent's text-to-video weights and inference code with a Gradio interface, under a custom licence and needing a high-end GPU.

  • 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 model variants for different GPU sizes, and runs on Windows as well as Linux through scripts.

  • CogVideoX

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

    FreeProprietaryLinuxCommand line

    CogVideoX provides text-to-video and image-to-video models with fine-tuning code and online demos, with weights under their own licence terms.

  • Mochi 1 (Genmo)

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

    FreeOpen sourceWindowsLinuxCommand line

    Mochi 1 from Genmo has Apache-2.0 open weights and consumer-GPU support via ComfyUI, though repository activity has not been reflected since late 2025.

  • LTX-2

    Open local video model that generates synchronized audio and video.

    FreeProprietaryWindowsLinuxCommand line

    LTX-2 generates synchronized audio and video with an official LoRA trainer, runs on Windows and Linux, and has non-standard license terms.

  • Wan2GP

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

    FreeProprietaryWindowsLinux

    Wan2GP is a local app that runs several open video models on low-memory GPUs with plugins, rather than a research codebase for training.

  • FramePack

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

    FreeOpen sourceWindowsLinux

    FramePack is an Apache-2.0 image-to-video tool designed for consumer GPUs with a Gradio interface, without published training code.

Similar software

Related functionality, not a direct replacement.