Image to 3D Model.

Local when you can. Mutual when you can’t.

Run the full TripoSplat model on this device when its WebGPU and storage qualify,
or send the same job to a free MutualGPU provider from this page.
Qualified devices can also opt in to help process another person’s TripoSplat job.

Try it out Learn how it works Why this matters
SYSTEM CHECK

Preparing your browser

STEP 1 / IMAGE + SETTINGS

Choose an image and generation settings

YOUR INPUT

Choose a source image, then set the sampling values that control the generated scene. These settings apply whether the job runs locally or through MutualGPU.

No image selected yet.
OPTIONAL / LOCAL PROCESSING

Prepare a photo for TripoSplat

Opaque photos start background removal and the official subject crop automatically in this browser. Your pixels stay on this device; use the button to process again.

Choose an image to enable local processing.

Generation settings

These sampling values apply to both local generation and MutualGPU requests. Keep the defaults for the qualified quality profile.

Continue to browser engine
STEP 3 / RESULT

Your spatial scene

Waiting

A completed scene will appear here without leaving this page.

STEP 2 / EXECUTION

Choose where it runs

CHECKING

Use this device for private, browser-local WebGPU generation when it qualifies, or use MutualGPU without local GPU or storage requirements.

Execution mode

The result returns to this same viewer. Selecting remote mode sends the selected image to the MutualGPU exchange and assigned provider.

Engineering preview. A first local run may download about 6.5 GB and generation can take several minutes. MutualGPU wait time depends on network, service, and provider availability. Browser support and output quality vary.

Checking local model storage and MutualGPU configuration…
Local model server
MutualGPU connection
STATUS

Checking browser compatibility…

COOKIE-SCOPED RECOVERY

Previous MutualGPU tasks

Checking this browser’s MutualGPU requestor session…

    Only tasks associated with this browser’s anonymous MutualGPU requestor cookie are shown. Result links are requested again when opened because signed downloads expire.
    LOCAL / MUTUALGPU PIPELINE

    Image-to-3D pipeline

    Live stages follow this browser for local runs or the assigned provider for MutualGPU runs.

    1. 01
      Source imageInspect, prepare, and securely transfer when remote.
      READY
    2. 02
      Model packageVerify the manifest and load model graphs on the executor.
      WAITING
    3. 03
      ConditioningPreprocess → DINOv3 → Flux VAE.
      WAITING
    4. 04
      Flow sampler20 official steps · 40 CFG DiT calls.
      WAITING
    5. 05
      Spatial decodeOctree occupancy → Gaussian decoder.
      WAITING
    6. 06
      Scene handoffPackage PLY / .splat, verify, and open the result.
      WAITING

    Privacy: local mode keeps image processing and inference on this device. MutualGPU mode uploads the selected image to the exchange and assigned provider. The latest verified MutualGPU result ZIP may be retained in this browser’s private origin storage for crash-safe download recovery; clearing this site’s browser data removes it. Provider mode receives untrusted requestor images and uses the local model cache. TripoSplat model artifacts come from the official Hugging Face package unless you choose another server.

    OPTIONAL / SHARE YOUR GPUBecome a MutualGPU providerChecking

    Qualified Chrome devices can receive one remote requestor’s TripoSplat assignment at a time. Accepted work runs on this browser and can download the same 6.5 GB model cache while sustaining heavy GPU and power use for several minutes. The requestor identity is not disclosed, but every activity line shows the assignment ID, phase, and progress. The provider key stays in this page’s memory and is never saved. Closing the page interrupts the session. Only enable this in an operator-controlled browser.

    PREFLIGHT / KEEP THIS DEVICE ONLINE

    Set up this provider machine

    System sleep, suspend, hibernation, or a sleeping browser tab interrupts the WebGPU provider connection. The display may turn off, but the operating system and this browser tab must remain active for the entire provider session.

    • Connect to external power where possible and use a stable network connection.
    • Prevent system sleep, suspend, and hibernation while providing. Keep this tab open and exclude this page from browser energy-saving or sleeping-tab features when necessary.
    • Do not close a laptop lid unless the device is explicitly configured to stay awake while docked or on external power.
    • A brief sleep can recover if the device resumes before the provider-session timeout. After the timeout, the provider disconnects; restore connectivity and select Start providing again.

    These are manual host settings. This page never changes your operating-system or browser power settings.

    macOS

    Open System Settings → Battery, review power-adapter options, and prevent automatic sleep while the display is off. On supported Macs, consider High Power mode for sustained work. Closing a Mac laptop lid normally sleeps it unless it is in a supported docked configuration.

    Apple: sleep and wake settings

    Windows

    Open Settings → System → Power & battery. While hosting, set plugged-in sleep and hibernate timeouts to Never, choose a high-performance power mode where available, and exclude this page from browser energy-saving or sleeping-tab features.

    Microsoft: Windows 11 power settings

    Linux

    Disable automatic suspend while connected to AC power in your desktop environment’s power settings. Exact controls vary by distribution and desktop environment; in GNOME, review Power → Automatic Suspend for plugged-in behavior.

    GNOME: automatic suspend settings

    Checking local WebGPU, model, and storage requirements…

    REMOTE PROVIDER ACTIVITY · LAST 120 EVENTS
    Select any text, or copy the complete log. New activity never moves your reading position.
    Provider is idle. Accepted assignments run on this browser for a MutualGPU requestor; each activity line identifies the remote task.
    WHY THIS MATTERS

    A monumental attempt to put CUDA-era 3D generation in reach of more people.

    TripoSplat started as a CUDA-based 3D generation pipeline. With Codex GPT 5.6 Sol Ultra and GPT 5.6 Sol Max in Kiro, this project is porting that work to WebGPU—replacing the usual requirements for NVIDIA hardware, CUDA, terminal commands, environment setup, and local dependency installation with a browser-native workflow.

    The goal is not a cosmetic port. It is an attempt to make advanced AI 3D generation radically more accessible: for GPUPoor MacBook users, students, independent developers, and anyone without an expensive GPU. When a browser passes the system check, they can generate a 3D asset locally on hardware they already own—no terminal, no installation, and no cloud GPU bill for inference.

    This is still an engineering preview, with compatibility and quality under active qualification. But the direction is clear: keep powerful spatial-generation tools inspectable, local, and available to more builders.

    Read the source, benchmarks, and open issues on GitHub