Workstations for AI image and video generation

Run ComfyUI with Stable Diffusion, FLUX and Wan video models on your own GPU, with no credits or queues.

Runs ComfyUI · Stable Diffusion · FLUX

  • From $3,999
  • GPU memory 16–96 GB
  • Ships in 7–10 business days
Novatech AI workstation in a black SilverStone SETA H2 case with a mesh front

Which models fit

Model 16 GBRTX 5070 Ti · RTX 5080From $3,999 32 GBRTX 5090From $11,499 96 GBRTX PRO 6000From $28,799
Stable Diffusion XLStability AI · 3.5BFullFullFull
FLUX.1 [dev]Black Forest Labs · 12BDoesn't fit in GPU memoryFullFull
Wan 2.2 TI2V-5BAlibaba · 5BDoesn't fit in GPU memoryFitsFits
Wan 2.2 T2V-A14BAlibaba · 27BDoesn't fit in GPU memoryDoesn't fit in GPU memoryFits
  • Full16-bit, full quality
  • FitsRuns as released
  • Doesn't fit in GPU memory

Image models: approximate GPU memory at the precision shown. Video models: the minimum in Wan 2.2's official instructions.

Check any model in the Model Finder

Every build comes with

  • Ready on first bootWindows 11 Pro or Ubuntu. Ollama, Open WebUI or ComfyUI set up on request.
  • 48-hour burn-in report
  • 3-year limited warranty
  • Lifetime technical support
  • Assembled in USA from new parts
  • Built in 7–10 business days, shipped free
What are ComfyUI's system requirements?

ComfyUI itself is light. GPU memory decides what you can run: about 12 GB for SDXL, 28 GB for FLUX.1 [dev] at full precision and 24 GB for Wan 2.2's 5B video model.

Is 16 GB enough for Stable Diffusion?

Yes for SDXL, which needs about 12 GB. FLUX.1 [dev] needs about 17 GB even at 8-bit, and video models need 24 GB or more, so those want the 32 GB build or bigger.

Can it make AI video?

Yes. Wan 2.2's 5B model needs 24 GB, so the 32 GB and 96 GB builds run it. Its 14B models need 80 GB, which only the RTX PRO 6000 build has.

Which software comes installed?

Windows 11 Pro, or Ubuntu if you ask. We can also set up ComfyUI before it ships, so you can load a model and start on first boot.

How long does an image take?

It depends on the model, resolution and number of steps. Ask and we'll run your workflow on the build and send you the timings before you order.

Your AI systems expert

  • POs and purchase cards welcome
  • Net terms
  • University & government procurement
Liquid-cooled processor and memory inside a Novatech AI server
What do you need?
What will you run?Pick all that apply.
How many people will use it?
How are you buying?Pick all that apply.
What's your budget?
Paste your specs
How many systems?
How do we reach you?
No obligation
A real engineer reviews it
Reply within 1 business day

WHAT HAPPENS NEXT

  1. An expert reads it.

    Your models, budget, and preferences, reviewed by the person who would build the system.

  2. You get a real spec.

    Configuration with pricing you can hand to procurement, in one business day.

  3. You decide.

    No obligation. If a smaller build serves your models better, that is what we recommend.