Our current turnaround time is 7-10 working days
What are you building for?
Tailored recommendationsPC builds across the site will be filtered to match your chosen use-case.

Generative Image Workstations

Stable Diffusion, FLUX & ComfyUI workstations — built for sustained GPU load.

Generative image workflows hammer the GPU for hours at a time. Our SD-tuned builds use the cooler, PSU and case airflow needed to hold full power across batch and video diffusion runs.

  • Pre-tested with A1111, ComfyUI, Forge
  • Optimised cooling for batch generation
  • Up to 96GB VRAM (RTX 6000 Pro)
  • 5-year warranty

Recommended configurations

Three calibrated starting points. Every component is configurable in our builder.

Most popular

SDXL Creator

SDXL & FLUX up to 1080p batch

£3,199

Starting price

CPU
AMD Ryzen 9 9950X
GPU
NVIDIA RTX 5090 (32GB)
RAM
64GB DDR5-6000
Storage
2TB Gen5 NVMe
Best for
SDXL · FLUX · Forge · ComfyUI
Configure SDXL Creator

SD Studio

High-res, Stable Video, training

£7,999

Starting price

CPU
AMD Threadripper PRO 7965WX
GPU
NVIDIA RTX 6000 Pro Blackwell (96GB)
RAM
128GB DDR5 ECC
Storage
4TB Gen5 NVMe + 8TB NVMe
Best for
4K img, video, LoRA training
Configure SD Studio

SD Production

Dual GPU, parallel pipelines

£15,499

Starting price

CPU
AMD Threadripper PRO 7995WX
GPU
2× NVIDIA RTX 6000 Pro Blackwell
RAM
256GB DDR5 ECC
Storage
4TB Gen5 + 16TB NVMe
Best for
Studio-scale image / video pipelines
Configure SD Production

Which Stable Diffusion model fits which GPU?

Image-diffusion VRAM use scales with resolution, batch size and base model. The figures below assume default fp16 weights with xFormers / sage-attention enabled.

Which Stable Diffusion model fits which GPU?
 WorkflowVRAM at 1024×1024VRAM at 2048×2048 (Hi-Res)Recommended GPU
SD 1.5
~5GB~10GBRTX 5060 Ti 16GB+
SDXL
~9GB~16GBRTX 5070 Ti / 5080
FLUX.1 [dev]
~17GB~28GBRTX 5090 (32GB)
Stable Video Diffusion
~16GB~30GBRTX 5090 / 6000 Pro
SDXL LoRA training
~24GB~40GBRTX 6000 Pro Blackwell

Numbers from public ComfyUI / A1111 benchmarks at default precision. Lower-precision (fp8 / Q4) and offload modes can cut VRAM by 30–50% at some quality cost.

Why CREATE PCs

Thermals built for batch jobs

Most generative workloads pin the GPU at 100% for an hour or more. We spec coolers and chassis that hold full clocks without throttle.

Storage tiered for model libraries

Gen5 NVMe for the OS and active workflow, secondary NVMe for your weights / LoRA / VAE library — checkpoints can easily exceed 1TB.

Quiet under load

Workstation acoustics matter when you sit next to the box for eight hours. Whisper-quiet builds are an option on every tier.

Stable Diffusion Workstations FAQs

Is the RTX 5090 enough for FLUX.1?

Yes. FLUX.1 [dev] runs comfortably on a 32GB RTX 5090 at 1024×1024 with reasonable batch sizes, and at 2048×2048 with hi-res fix. For long-form Stable Video or LoRA training on FLUX, you may want the RTX 6000 Pro Blackwell.

Will more system RAM speed up Stable Diffusion?

Only indirectly — VRAM is the binding constraint for inference. System RAM matters when you swap models often, run hi-res fix on big base models, or use offload modes (where weights spill from VRAM to system RAM). 64GB is the sweet spot; 128GB+ for ComfyUI workflows juggling several models at once.

Can I run multiple diffusion models in parallel?

Yes — our SD Production tier with two RTX 6000 Pro cards is set up for parallel pipelines, useful for studio-scale image or video work where one card handles base generation and another handles upscaling or refinement.

Do you preinstall ComfyUI / A1111 / Forge?

On request. We install Windows 11 Pro with NVIDIA Studio drivers as standard and can preinstall ComfyUI, Automatic1111 or Forge with your chosen model weights ready to launch on first boot.

What about local video generation?

Stable Video Diffusion, AnimateDiff and CogVideoX are workable on a 32GB RTX 5090 at modest resolutions and clip lengths. For sustained or higher-resolution video pipelines, the RTX 6000 Pro tier is the safer choice.