Servers
Cloud Servers Cloud VPS Dedicated VPS Windows VPS Windows Dedicated VPS Managed Cloud Servers Managed Cloud Dedicated Servers GPU Dedicated Servers Forex VPS Forex Dedicated Server
Hosting
cPanel Hosting WordPress Hosting WooCommerce Hosting cPanel Dedicated cPanel Reseller Nextcloud Hosting Sovereign Workspaces
Platform & Containers
Platform as a Service PaaS Marketplace Red Hat OpenShift Docker Hosting Kubernetes n8n Hosting Dokploy Hosting Coolify Hosting Magento in PaaS WordPress in PaaS
Private Cloud
Private Cloud Hosting Virtual Private Cloud Dedicated Private Cloud HA Private Cloud White-Label Cloud Platform Colocation
Solutions
eCommerce Hosting Fintech Hosting Gaming Hosting Disaster Recovery Digital & Data Sovereignty VMware Replacement Sovereign Government Suite National Digital Identity For Developers For Enterprises AI Infrastructure Blockchain Hosting
Cyber Security
Security Overview DDoS Protection SSL Certificates HSM Decanus Terminal Backup Services Domains SOC Services Aramco CCC SABIC CyberTrust SAMA CSF NCA CCC NCA CSCC CITC CRF Saudi PDPL Qatar Cybersecurity UAE Cybersecurity GCC Cybersecurity CMMC NIS2 DORA TISAX HIPAA
Support
Support Plans DevOps Support Nextcloud Support Proxmox Support VMware Replacement NOC Services
Resources
Technology Data Centers Network High Availability Storage Blog Forex VPS Guides Windows VPS Guides Dokploy Guides Coolify Guides About Us Compare Contact
Browse All Industries →
Login Get Started
24 GB or 96 GB vRAM Order online ComfyUI on port 8188

A Dedicated GPU Server for ComfyUI, SDXL and FLUX

Stable Diffusion hosting here means a bare-metal server with its own NVIDIA card, on which you install ComfyUI and the models you choose. The RTX PRO 4000 server (24 GB, $449.99 a month) runs SDXL, Stable Diffusion 3.5 and FLUX.1; the RTX PRO 6000 server (96 GB, $1,656.15 a month) adds the video models that ask for 60 GB to 80 GB. Both are on the GPU dedicated servers page, with unlimited traffic and no per-image fee.

24 GB
RTX PRO 4000
$449.99
per month
96 GB
RTX PRO 6000
1 Gbps
unlimited traffic

What is Stable Diffusion hosting on a dedicated server?

Stable Diffusion hosting: running an open-weight image model on a GPU you rent, instead of paying a service per image or per seat. On a dedicated server the whole card belongs to one customer, so generation speed does not depend on other tenants, the model files stay on your own NVMe drives, and prompts and outputs do not pass through a third-party image service.

The usual front end is ComfyUI, a node-based interface in which a workflow is a graph: load a checkpoint, encode the prompt, sample, decode, save. The same server can run more than one tool, because it is a plain Linux machine with root access. You choose the operating system at order (Ubuntu 24.04 LTS is the default; there is no Windows option), and it arrives clean: drivers, Python, ComfyUI and models are installed by you, with the steps further down.

What the server does not include: it is not a managed image service, there is no preloaded model library, and there is no hourly billing. If you want to pay only for the minutes you render, an hourly GPU cloud or a subscription is the better fit, and this page says when.

Which image and video models fit in 24 GB and in 96 GB?

File sizes and licences are from the model pages on Hugging Face, checked on 16 November 2026. The image model cards publish no vRAM figure, so the image rows compare file size with card memory; the video rows quote the memory the model authors state.

ModelSize or stated memoryLicenceRTX PRO 4000, 24 GB, $449.99RTX PRO 6000, 96 GB, $1,656.15
SDXL base 1.06.94 GB fileCreativeML Open RAIL++-MFits with room to spareFits, several pipelines at once
Stable Diffusion 3.5 Large (8B parameters)16.5 GB file, plus three text encodersStability Community License: free under $1M annual revenue, Enterprise licence aboveFile fits; the encoders, including T5-xxl, come on top, so test your workflowFits
FLUX.1 [schnell] (12B parameters, 1 to 4 steps)23.8 GB file, plus a 335 MB autoencoderApache-2.0The file alone is as large as the card: expect offloading or lower precisionFits at full precision
FLUX.1 [dev] (12B parameters)23.8 GB file, plus a 335 MB autoencoderFLUX.1 [dev] Non-Commercial LicenseAs schnellFits at full precision
Wan 2.2 TI2V-5B (720P video, 24 FPS)"at least 24GB VRAM"Apache 2.0At the stated minimumFits
Wan 2.2 T2V-A14B (480P and 720P video)"at least 80GB VRAM"Apache 2.0Below the stated minimumFits
HunyuanVideo (13B+ parameters)45 GB peak at 544x960, 60 GB at 720x1280, 129 frames; 80 GB recommendedTencent Hunyuan CommunityDoes not fitFits

Licences matter more than memory for a business. FLUX.1 [schnell] and Wan 2.2 are Apache-licensed. FLUX.1 [dev] is released under a non-commercial model licence: its card says outputs may be used commercially, but the model licence itself is non-commercial, so read the licence text and speak to Black Forest Labs before you build a paid product on it. Stable Diffusion 3.5 Large is free for organisations under $1M in annual revenue and needs an Enterprise licence above that.

What 96 GB changes. Apart from the 60 GB to 80 GB video models, one RTX PRO 6000 can be divided with NVIDIA MIG into four isolated 24 GB instances, so four artists each get their own ComfyUI on one card. The RTX PRO 4000 does not support MIG. The Wan authors report a 5-second 720P clip from the 5B model in under 9 minutes on one consumer GPU; we publish no timing of our own, so run your workflow and time it. The RTX PRO 4000 vs RTX PRO 6000 comparison covers the two cards in detail.

Dedicated server, Midjourney or Runway seats, or hourly cloud: which costs less?

A server is a fixed cost and a subscription scales with people, so the comparison is a seat count. Midjourney's plans, checked on 16 November 2026, are Basic $10, Standard $30 (15 fast hours), Pro $60 (30 fast hours) and Mega $120 (60 fast hours) per month. Runway lists Standard at $15 (625 credits), Pro at $35 (2,250 credits) and Max at $95 (9,500 credits) per user per month billed monthly. Hourly cloud prices are on-demand rates of the same date.

OptionMonthly costEquals the 24 GB server atNotes
RTX PRO 4000 server, 24 GB$449.99-One-time setup $346.48, so the first month is $796.47. No cap on images.
Midjourney Standard$30 per seat15 seats ($450)15 fast hours per seat
Midjourney Pro$60 per seat8 seats ($480)30 fast hours per seat
Midjourney Mega$120 per seat4 seats ($480)60 fast hours per seat
Runway Pro (as listed)$35 per seat13 seats ($455)2,250 credits per seat
Runway Max (as listed)$95 per seat5 seats ($475)9,500 credits per seat
AWS g5.xlarge, one A10G 24 GB, N. Virginia$1.006 per hourAbout 447 hours730 hours: $734.38. Storage and $0.09 per GB egress extra
AWS g6.xlarge, one L4 24 GB, N. Virginia$0.8048 per hourAbout 559 hours730 hours: $587.50. Storage and egress extra
Google Cloud g2-standard-4, one L4 24 GB, Iowa$0.706832 per hourAbout 637 hours730 hours: $515.99. Egress $0.12 per GiB on the Premium Tier

Where a subscription fits. Below the seat counts in the table, paying per seat costs less, with nothing to install or patch and no setup fee. Midjourney's own model is not available as open weights, so if its look is what your clients want, a server does not replace it.

Where hourly cloud fits. If you render a few hours a day, well below the hours in the table, an instance you can stop is the better buy.

Where the server wins. Studios with 15 or more seats, pipelines that render all day (batch product shots, dataset generation, video), custom checkpoints and LoRAs that you train and keep, and work under NDA where prompts and reference images should stay on a machine only you use. Per hour over a 730-hour month the 24 GB server works out at $0.62 and the 96 GB server at $2.27.

Is it safe to expose ComfyUI to the internet?

Not directly. By default ComfyUI listens on 127.0.0.1, port 8188, which means only the server itself can reach it. Starting it with --listen and no argument makes it listen on all IPv4 and IPv6 addresses, and on a server with a public IPv4 address that puts the interface on the open internet.

A ComfyUI workflow can load files and run custom nodes, and custom nodes are Python code that runs with the rights of the ComfyUI process. Treat the port like a shell. Three ways to use it safely, in order of effort:

  • SSH tunnel. Leave the default bind address and forward the port from your workstation: ssh -L 8188:127.0.0.1:8188 user@your-server, then open http://localhost:8188.
  • Firewall allow-list. If a team needs access, bind to the public address but allow port 8188 only from your office or VPN addresses.
  • Reverse proxy with TLS and a login. Put a web server with HTTPS and authentication in front and keep ComfyUI itself on localhost.

Run ComfyUI as an unprivileged user, not root, and install only custom nodes whose source you trust. The server is a single machine: keep copies of your workflows, LoRAs and outputs somewhere else, and consider software RAID 1 on the two NVMe drives.

Two servers for image and video generation

24 GB for image models at $449.99 a month, or 96 GB for video models and several users on one card at $1,656.15 a month.

Enterprise

NVIDIA RTX PRO 6000

Large models, fine-tuning and visualization on one 96 GB GPU
CPU
Core Ultra 7 26520 cores / 20 threads
RAM
128 GB DDR5
Storage
2x 1.92 TB NVMeGen4, DC-grade
GPU
RTX PRO 6000Blackwell Max-Q
vRAM
96 GB GDDR7ECC
Network
1 GbpsUnlimited traffic
  • 3,511 AI TOPS
  • CUDA, FP4 and Multi-Instance GPU (MIG) support
  • 1 dedicated IPv4 included
$1,656.15/mo
Starting price, billed monthly. One-time setup fee $1,656.15.
Order Now

Every RTX PRO server includes: a 1 Gbps port with unlimited traffic, one dedicated IPv4 address, hosting in an ISO 27001 certified data center, and your choice of Ubuntu, Debian, AlmaLinux, Rocky Linux, CentOS Stream, openSUSE or Arch Linux, or a rescue system to install your own OS. Billing runs monthly, quarterly, semi-annually, annually, biennially or triennially, and the setup fee is charged once with the first invoice.

How to install ComfyUI on the server

These steps assume Ubuntu 24.04 LTS, the default at order. The driver commands are NVIDIA's documented apt route and the ComfyUI commands are from its README, both read on 16 November 2026.

  1. Install the NVIDIA driver and reboot.
    apt install linux-headers-$(uname -r)
    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb
    dpkg -i cuda-keyring_1.1-1_all.deb
    apt update
    apt install nvidia-open
    reboot
    After the reboot, nvidia-smi must show the card and its 24 GB or 96 GB of memory.
  2. Install ComfyUI as a normal user, in a virtual environment. The README requires a cu130 or newer PyTorch build on NVIDIA 20-series cards and later.
    git clone https://github.com/comfyanonymous/ComfyUI
    cd ComfyUI
    python3 -m venv venv && source venv/bin/activate
    pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu130
    pip install -r requirements.txt
  3. Add a model. Download a checkpoint such as sd_xl_base_1.0.safetensors (6.94 GB) into models/checkpoints. A 23.8 GB FLUX file is about 190 gigabits, so it takes at least three minutes at the full 1 Gbps line rate.
  4. Start it and connect. python main.py starts ComfyUI on 127.0.0.1:8188. Open an SSH tunnel from your computer and load http://localhost:8188.
  5. Verify. Queue the default workflow and watch nvidia-smi in a second terminal: memory use should rise on the card while the image samples.

The full walkthrough, including FLUX and a systemd unit, is in ComfyUI and FLUX on a GPU server; the older Stable Diffusion on a GPU server post covers the general setup.

What else can the same server do?

The card is not tied to one tool. The RTX PRO 4000 has two NVENC encoders and the RTX PRO 6000 four, with AV1 and 4:2:2 H.264 and HEVC encoding and no limit on concurrent sessions (NVIDIA support matrix, checked on 16 November 2026), so a render node can also transcode video with NVENC. Blender renders headless from the command line with Cycles on OptiX, as the Blender rendering guide shows. And a prompt-writing or captioning model can run beside the image model: a 24 GB card has room for SDXL and a small language model at once, and a 96 GB card for FLUX and a 70B model at 4-bit (43 GB). For language models as the main workload, see Ollama hosting.

Frequently Asked Questions

The RTX PRO 4000 server with 24 GB of vRAM is $449.99 a month plus a one-time setup fee of $346.48. The RTX PRO 6000 server with 96 GB is $1,656.15 a month with a setup fee of the same amount. Traffic is unlimited on a 1 Gbps port and there is no per-image charge.
The FLUX.1 file is 23.8 GB, about the size of the whole card, so at full precision ComfyUI has to offload parts of the pipeline to system RAM or load the weights at lower precision. Black Forest Labs publishes no vRAM figure on the model card. For FLUX at full precision with headroom, choose the 96 GB server; the ComfyUI and FLUX guide walks through both.
No. The server arrives with a clean operating system and root access. Installing the NVIDIA driver, ComfyUI and a first model takes a handful of commands and one reboot, shown on this page.
Port 8188, bound to 127.0.0.1 by default. Reach it through an SSH tunnel, or put a TLS reverse proxy with a login in front. --listen without an argument opens it on every address, which you should not do on a public IP without a firewall rule.
FLUX.1 [dev] is under a non-commercial model licence, while FLUX.1 [schnell] is Apache-2.0. The dev model card says outputs may be used commercially, but running the model in a paid service is a licensing question for Black Forest Labs: read the licence text first. This is information, not legal advice.
Wan 2.2 TI2V-5B states a minimum of 24 GB, which the RTX PRO 4000 meets exactly. Wan 2.2 T2V-A14B states at least 80 GB, and HunyuanVideo peaks at 45 GB to 60 GB with 80 GB recommended, so both need the 96 GB RTX PRO 6000 server.
Yes. On the 24 GB server, users share one ComfyUI queue. On the 96 GB server you can split the card with NVIDIA MIG into four isolated 24 GB instances and run one ComfyUI per person; see the MIG guide.
At 15 Standard seats ($30 each), 8 Pro seats ($60 each) or 4 Mega seats ($120 each) the monthly cost passes the $449.99 server. Below those seat counts, paying per seat costs less and needs no administration. A server also cannot run Midjourney's own model, only open-weight models such as SDXL, Stable Diffusion 3.5 and FLUX.

Run ComfyUI on your own GPU

24 GB from $449.99 a month or 96 GB from $1,656.15 a month, bare metal with root access and unlimited traffic.

24 GB or 96 GB vRAM
1 Gbps, unlimited traffic
Root access
24/7 support
See the servers