STRATA Reserve capacity
Strata/Answers/Guides

Cloud GPUs for self-hosting ComfyUI (images and video)

GuidesUpdated 2026-10-23

You can self-host ComfyUI on any rented GPU server with your own container. At Strata GPU a 96 GB RTX PRO 6000 costs $2.03 per GPU-hour on demand, billed per minute, and runs Flux, SDXL and open video models such as Wan and Hunyuan Video; an 80 GB H100 is $3.23 and a 141 GB H200 $4.31 for heavier video work.

Reserve capacityAll GPUs and prices

Which GPU for which ComfyUI workflow

WorkflowMemory neededGPU at StrataOn demand
SDXL, Flux images, LoRAs, upscalersFits comfortably in 96 GB with several models loadedRTX PRO 6000 96GB$2.03/hr
Open video models (Wan, Hunyuan Video) at high resolution≈ 40–80 GBRTX PRO 6000 or H100 80GB$2.03–$3.23/hr
Longer clips, several video models loadedOver 80 GBH200 141GB$4.31/hr
Light image work, small models24–32 GBRTX 4090 / RTX 5090On request

Strata list prices per GPU-hour, billed per minute on demand. Prices as of 2026-11-10.

For most ComfyUI users the RTX PRO 6000 is the best value: enough memory for Flux plus upscalers and LoRAs, hardware video encoders for the final output, and a lower hourly rate than HBM data-center GPUs.

How to set up ComfyUI on a rented server

From hobby sessions to a production pipeline

Occasional sessions are cheapest on demand, billed per minute from a prepaid balance. If you generate images or video every day for clients, run ComfyUI as a queue of jobs across several GPUs: reserve a small cluster for steady volume (3–14% below on demand on 3–36 month terms) and add on-demand GPUs for campaign peaks. Dedicated servers are not shared with other customers, which matters if you work with client assets. More in GPU servers for image and video generation.

How other options compare

Hosted ComfyUI services, including the official one, need no server setup; check which custom nodes and models they allow and how they bill. Marketplaces such as Vast.ai and RunPod Community Cloud usually have cheaper consumer GPUs per hour, but hosts vary in reliability. Strata suits users who want data-center GPUs with 80–141 GB of memory, dedicated servers that are not shared with other customers, fixed list prices and payment by card, bank transfer, USDT or USDC. Check each provider's current prices on its own pricing page.

Sources

FAQ
Can I run ComfyUI on Strata GPU?

Yes. Use your own ComfyUI container or a PyTorch/CUDA image and connect to the web interface through the browser, ideally over an SSH tunnel.

What is the cheapest GPU for Flux in ComfyUI?

Consumer cards such as the RTX 4090 run Flux at normal resolution. For Flux with upscalers, several LoRAs or video models in the same workflow, the 96 GB RTX PRO 6000 at $2.03 per hour avoids running out of memory.

Do I pay while ComfyUI is idle?

Yes. On-demand servers bill per minute while they are allocated, whether or not a workflow is running, so stop the server when you finish a session.

NVIDIA RTX PRO 6000 Blackwell 96GB
Blackwell · 96 GB GDDR7

RTX PRO 6000

from $2.03/GPU-hr

Specs and pricing →
NVIDIA H100 80GB
Hopper · 80 GB HBM3

H100

from $3.23/GPU-hr

Specs and pricing →
NVIDIA H200 141GB
Hopper · 141 GB HBM3e

H200

from $4.31/GPU-hr

Specs and pricing →
Related questions

How much does it cost to rent an H100 per hour in 2026? How much does it cost to rent an H200 GPU? How much does it cost to rent an NVIDIA B200? Where can I rent an RTX 4090 or RTX 5090 GPU?