Quick Deploy - ComfyUI

Quick Deploy is the fastest way to get a ComfyUI workspace running on Meshive. You pick a pre-built bundle, Meshive auto-recommends the cheapest GPU that fits it, you size storage to taste, and click Deploy — then just type a prompt into the workflow to generate an image or video.

Normally, running a model in ComfyUI means SSH-ing into the pod, downloading the right .safetensors files, dropping each into the correct models/ subfolder, and only then loading it in a workflow. Quick Deploy removes that entire step: every bundle is a ComfyUI image with the model files pre-installed, so the workflow is ready to run the moment the pod starts — no downloads, no folder wrangling.

Quick Deploy vs. the Pod wizard

Use Quick Deploy when you want a ready-to-run model bundle with sensible defaults. Use the full Pod → Deploy wizard (see Deploying ComfyUI) when you need to customize the image tag, command, environment variables, endpoints, or attach multiple volumes.

Available bundles

Each card on the Quick Deploy page is an official ComfyUI bundle. Weights ship FP8-quantized (roughly half the VRAM of FP16), and the recommended VRAM drives which GPUs are offered.

Bundle	Type	Recommended VRAM	Notes
FLUX	Image	16 GB+	FLUX.1 12B, weights pre-baked
Qwen-Image	Image	16 GB+	Qwen-Image (~20B)
Qwen-Image Edit	Image	16 GB+	Instruction-based image editing
Z-Image Turbo	Image	8 GB+	Lightweight, fast image model
WAN 2.1	Video	24 GB+	Text-to-video / image-to-video
ComfyUI	Image	12 GB+	Stock image, no bundled weights — pull models yourself after deploy

Note

The exact set of cards depends on which bundles are currently published, so your console may show a subset of the list above. The ComfyUI card is the plain image — pick it only if you intend to download your own models (see Load a workflow & download models).

Deploy

1. Open Quick Deploy

   In your Workspace sidebar, click Quick Deploy under Resources. Each card shows the model name, a short description, and its category · recommended VRAM.

2. Pick a bundle

   Click the bundle you want (for example FLUX or ComfyUI). This opens the Review & Deploy page for that bundle.

3. Review & Deploy

   Everything on this page is pre-filled with a recommended configuration — you only change what you want.

   • Pod Name — pre-filled with a suggested name; edit if you like.
   • Rental Type — Demand (uninterrupted) or Spot (cheaper, may be reallocated).
   • Storage (optional) — None by default. Choose Local Storage (new persistent volume, 100 / 150 / 200 GB, mounted at /workspace/models) or Network Storage (link an existing NFS volume in this workspace).
   • GPU — auto-selected as the cheapest GPU that meets the bundle’s VRAM requirement, with 1 GPU. Use the dropdown to switch cards; the list shows model · VRAM · $/hr.
   • Specs — VRAM, vCPU, RAM, and System Storage are derived automatically from the chosen GPU.
   • Total — the hourly price updates live as you change options.

   Click Deploy.

   Caution

   Spot pods can’t use Local Storage — a reallocated pod would lose the volume. With Spot, use Network Storage, or leave storage on None.

   Note

   Since the model weights are baked into the bundle image, extra storage is optional. Add a volume only if you want to persist custom models, LoRAs, or generated outputs across restarts.

4. Wait for the pod to start

   After you click Deploy, Meshive schedules the pod and pulls the bundle image — the status moves through Creating → Pulling container image → Running. The first pull is several GB, so allow a few minutes.

5. Connect to ComfyUI

   Once the pod shows Running, open the Pod page and click the Connect (plug) icon to launch the ComfyUI GUI. Because the weights are pre-installed, the bundled workflow is ready to run immediately.

Tip

ComfyUI also exposes a Jupyter endpoint (port 8888) and the ComfyUI API server (port 8080) alongside the GUI (port 3000), so you can drop into a terminal or drive it programmatically.

Next

• Load a workflow and generate your first output — for the stock ComfyUI bundle, this also covers downloading model weights via SSH.