Cubric Vision - Start

Getting Started

Choose where models live, then let Cubric Vision set up the local generation engine.

If you have not downloaded and extracted the app yet, start with Installation. This page picks up at the first launch, once Cubric Vision opens.

First launch

The first time Cubric Vision opens, it asks where to store AI model files. Pick a drive or folder with enough free space for the models you plan to use.

Cubric Vision first-launch modal asking where to store AI models, with a Models Folder field and Install button
The models folder can be changed later in Settings.

Press Install to start setup. Cubric Vision downloads and prepares the ComfyUI engine, installs required custom nodes, and installs the base files needed for built-in workflows. This can take a while, especially on the first run.

macOS — install Apple's Command Line Tools first

Setting up the local engine needs git, which on macOS only arrives with the Xcode Command Line Tools, and a clean Mac does not have them. The first Install press stops with a message naming exactly that.

  1. Open Terminal.
  2. Run xcode-select --install and let Apple's download finish.
  3. Press Retry in Cubric Vision.

This is a known issue, not a fault in your download. Windows ships a prebuilt engine and never needs git; macOS and Linux build theirs. Removing the requirement is being worked on.

Cubric Vision installation progress modal showing the ComfyUI engine installing with a progress bar and pause button
The progress screen shows download progress, speed, and the current setup step.

No GPU? Skip the engine install

Setting up Cubric used to mean installing the ComfyUI engine first, even on a machine that could never use it. The install screen now offers a way straight past it: Skip this — set up RunPod in Settings, with a link to the setup video beside it.

Take that path and Cubric runs entirely on a cloud GPU through Settings → RunPod. Nothing is downloaded to your machine, and nothing starts billing until you connect a Pod yourself.

It is reversible. Turn the local engine back on from Settings → RunPod whenever you want it after all.

Models and folders

After setup finishes, Cubric Vision opens to the Projects page. Model files live separately from your projects. You can change the ComfyUI models path, add extra LoRA and upscale model folders, and bring your own LoRA later in Settings → External connections.

Settings

Everything else — engine startup, desktop notifications, viewer rendering, what Reuse Prompt copies, and the optional RunPod remote engine — lives on the Settings page.

Cubric Vision Models panel showing one installed model and another model marked partially installed with progress already complete
Partially installed means Cubric Vision found files this model shares with another installed model.

Some models share the same required files. When you install one model, any other model that uses those same files may appear as Partially installed. The progress bar shows how much of that model is already present on disk, so installing it later only needs to download the missing files.

Engine updates

The generation engine updates with the app, and since 1.4 it updates in place: only the parts that moved are replaced, so a typical engine update finishes in seconds and costs almost no bandwidth. It used to delete the whole engine and fetch it again — around eleven gigabytes — even when the change was tiny.

The full reinstall still exists and still runs by itself when an update genuinely needs one, so you never end up on a half-updated engine.

What to expect

The first setup is the slowest run because Cubric Vision is preparing the local engine and downloading required files. Later launches use the installed engine and models from disk.

You no longer need to close your own ComfyUI before opening Cubric Vision — the app's engine runs on its own port and stays out of the way of yours. If something else is using that port, the app tells you which one instead of quietly generating on it.