Skip to content
Meshive Docs

QuickStart - Deploying ComfyUI 1

  1. Select Workspace

    Section titled “Select Workspace”

    Create a Workspace and select it.

    Workspace selection dropdown in the Meshive console

  2. Deploy Pod — Select Template

    Section titled “Deploy Pod — Select Template”

    Click Pod in the sidebar, then click the Deploy button.

    "Deploy" button on the Pod page in the Meshive console

    Select the Generative box and click ComfyUI in the Image section.

    Template gallery with the Generative category and the ComfyUI card highlighted

    Select the image tag — base-torch2.8.0-cu128.

    Image-tag selector showing base-torch2.8.0-cu128

  3. Deploy Pod — Select Resources

    Section titled “Deploy Pod — Select Resources”

    Enter your Pod name and select VRAM 32 GB, then select RTX 5090.

    Pod-name field and RTX 5090 / VRAM 32 GB resource selection

    (Optional) Select CPU and RAM.

    Optional CPU and RAM resource fields

    Connect storage

    Section titled “Connect storage”
    1. Click the Connect button to the right of Required Volume Mounts.
    2. Select Local Storage.
    3. Enter the Capacity and click Add.
    Required Volume Mounts pane with the Connect button highlighted Local Storage modal — Capacity input Volume mounts list with the green-light status after a successful add

  4. Connect ComfyUI and Use

    Section titled “Connect ComfyUI and Use”

    Click Accept & Deploy.

    "Accept & Deploy" with the post-deploy waiting status

    Once fully running, click the Connect button to access the GUI.

    "Connect" button revealing the ComfyUI GUI URL

Next

Section titled “Next”