HomeChatAgentImage StudioVideo StudioGallery
    Text to Video

    Wan 2.6 Text to Video Generator

    Wan 2.6 is Alibaba's text-to-video model, running here in the browser - no GPU, no API keys, nothing to install. Strong quality with audio, up to 15s. Unfiltered. This page opens the studio with Wan 2.6 already selected: clips up to 15 seconds, synced audio, vertical 9:16 as well as widescreen, a fixed seed for repeatable results. It is an open-weights deployment with no provider-side prompt moderation, badged Uncensored in the picker.

    Frequently asked questions

    Is Wan 2.6 free to use?

    You get free credits when you sign up - no card needed - and they work on Wan 2.6. After that it is pay-as-you-go: 1,000 credits = $1, packs start at $10, and each clip's price is shown before you generate it.

    How long can a Wan 2.6 clip be?

    Up to 15 seconds per generation, choosing from 5s, 10s, 15s. For longer pieces, render several clips and join them in the Movie Editor.

    Does Wan 2.6 generate audio?

    Yes - it renders sound synced to the picture, which is what makes it usable for dialogue, sound effects and UGC-style ads without a separate audio pass.

    Is Wan 2.6 uncensored?

    Wan 2.6 runs as an open-weights deployment with no provider-side prompt review, so briefs mainstream hosted models decline will run. Unrestricted means no provider-side prompt moderation on the open models - not no rules. Illegal content is banned, explicit capabilities are gated 18+, and sexual content depicting real people without their consent is prohibited.

    Is Wan 2.6 open source?

    Wan 2.6 is an open-weights model - published weights are exactly what lets it run here without a provider's moderation layer in front of it. Open weights is not the same thing as an open-source licence, so check the model's own terms before you build on its output commercially. Either way you do not need a GPU or an API key to use it here.

    Describe the shot you want and get a clip back.

    Set the quality and filters; we’ll choose the model.
    Quality

    Good quality at a fair price

    Filters

    Big-lab models. Sharpest look, strict content filters

    Rewrites your prompt with cinematic structure — subject, action, camera, lighting, and shot framing — before generating.
    0/2000