Skip to content

VideoAlibaba (Tongyi Lab)

Wan

Open-source text- and image-to-video generation from Alibaba.

Category
Video
Pricing
FREEMIUM
Source
Open core
Hosting
Hybrid
Platforms
WebAPI
Models
Self-contained (on-device)
Verified
Jun 20, 2026

Wan is an open-source family of video generation models from Alibaba's Tongyi Lab, covering text-to-video, image-to-video, and image generation and editing. Released under Apache 2.0 with weights, training, and inference code public, it can be self-hosted or used free on the wan.video site. Successive versions, including Wan 2.2's mixture-of-experts architecture, have topped open-video benchmarks.

Pros & cons

  • Fully open weights under Apache 2.0
  • Self-host or use free at wan.video
  • Text-, image-, and edit-to-video
  • Top VBench open-model scores
  • Self-hosting needs strong GPUs
  • Short clips at 480p/720p
  • Hosted site has usage limits
  • Docs and tooling skew technical

Tags

Alternatives to Wan (4)

View all Video →
  • View Kling AI details
    VideoFREEMIUM

    Kling AI

    Kuaishou

    State-of-the-art AI video + image, with strong motion and multishot.

    Kuaishou's creative studio — text- and image-to-video with convincing motion, lip-sync, and multishot sequences up to ~15s, plus image generation. A leading Runway/Sora rival.

    Convincing complex motion and physics
    Credit-based pricing adds up
    • video-gen
    • image-to-video
    • motion
    • multishot
    Open
  • View Sora details
    VideoFREEMIUM

    Sora

    OpenAI

    OpenAI's video generator as a standalone app.

    OpenAI's video model surfaced as a consumer product — generate, remix, and share short videos from prompts or images. Available standalone and bundled into ChatGPT for subscribers.

    Synced dialogue and sound effects
    Still struggles with physics/spatial coherence
    • video-gen
    • consumer
    • social
    Open
  • View Runway details
    VideoFREEMIUM

    Runway

    Runway

    Professional video AI. Gen-series models + a full editor.

    End-to-end video AI platform — text-to-video, image-to-video, in-painting, motion brush, and a timeline editor. Longest-running studio in the space; default choice when the output ships to clients.

    Full editor, not just a generator
    Credits deplete fast on long clips
    • video-gen
    • editing
    • motion
    • film
    Open
  • View Genmo details
    VideoFREEMIUMOpen core

    Genmo

    Genmo

    Open-source text-to-video generation, with a free hosted playground.

    AI video startup behind Mochi 1, an open-source text-to-video model built on an Asymmetric Diffusion Transformer (AsymmDiT) architecture and released under Apache 2.0. The weights and code are on GitHub and Hugging Face for local or self-hosted use, while genmo.ai hosts a free playground to generate clips from prompts in the browser.

    Open weights under Apache 2.0
    Local runs need heavy GPU memory
    • text-to-video
    • open-source
    • video-generation
    • diffusion
    Open
Open Wan