Build node-based image generation workflows with ComfyUI on an NVIDIA Tesla P40 (24 GB VRAM, Pascal architecture). GPU servers are not orderable yet; contact us to be notified when they are.
$ git clone https://github.com/comfyanonymous/ComfyUI.git && cd ComfyUI && pip install -r requirements.txt && python main.py --listen
# Example install command
ComfyUI is a node-based interface for Stable Diffusion and related models that makes image generation workflows reproducible. A GPU server supplies the VRAM those pipelines need.
Build and save generation pipelines with visual nodes.
Load a base model, LoRAs and ControlNet models at the same time.
Open your ComfyUI instance in a browser, protected by your own authentication or tunnel.
Install community custom nodes for extra capabilities.
ComfyUI can use an NVIDIA GPU to speed up its work. VPS.org GPU servers are not available to order yet; contact us to hear when they are. ComfyUI is a diffusion / image-generation workload. Expect VRAM headroom for larger resolutions, ControlNet add-ons, and concurrent generation pipelines.
GPU servers are not available to order yet. Today you can run ComfyUI on a regular CPU plan, where it works far more slowly than on a GPU: SSH in and run git clone https://github.com/comfyanonymous/ComfyUI.git && cd ComfyUI && pip install -r requirements.txt && python main.py --listen.
Image diffusion VRAM scales with resolution and batch size. SDXL at 1024x1024 wants about 10 GB of VRAM; SD 1.5 at 512x512 fits in about 4 GB.
GPU pricing will be published when GPU servers can be ordered. Contact us if you want to hear when that happens.
Yes. Every VPS.org server comes with full root access, so you can run other tools alongside ComfyUI within the server's RAM and storage.
Every VPS.org server comes with full root SSH access, so you can install drivers, libraries and ComfyUI however you need.
No. No server comes with a CUDA runtime or NVIDIA driver preinstalled, and GPU servers are not available to order yet. You install the versions ComfyUI needs yourself.
Yes. VPS.org servers are persistent virtual machines, not ephemeral instances: ComfyUI models, configs and data stay on the server's SSD storage until you delete them.
Keep working data on the server's SSD for fast access during ComfyUI runs, and copy finished artifacts (weights, generations, embeddings) to storage outside VPS.org; snapshots and backups stay on the same storage cluster.
You can upgrade any VPS.org server to a larger plan from the control panel; the resize restarts it and your ComfyUI install carries over. GPU servers are not available yet.
Yes. Backups are a paid add-on (daily +30% of the plan price, kept 7 days; weekly +20%, kept 28 days) and snapshots are free, which is useful before long ComfyUI runs. Both stay on the same storage cluster as the server.
Contact support within 30 days of your first purchase to request a refund. GPU servers are not sold yet, so no GPU order is involved.
GPU servers are not orderable yet. Tell us about your workload and we will let you know when they are.