Exhibit · AI art generation

Generate AI art with real GPU power

24 GB and 48 GB VRAM available. ComfyUI, Automatic1111, LM Studio — full GPU acceleration, no queues, no limits on your creativity.

Full Windows admin access means you can install anything. Here are the most popular tools our creators use.

Node-based Stable Diffusion workflows with full GPU acceleration.

The most popular Stable Diffusion interface, pre-configured for NVIDIA.

Run large language models locally — Llama, Mistral, Mixtral, and more.

Simplified Stable Diffusion — great for beginners exploring AI art.

Professional Stable Diffusion toolkit with a polished creative interface.

Fine-tune Stable Diffusion models with your own artistic data.

CLI-based LLM runner. Pull and run models in seconds for creative writing.

Run GGUF models with GPU offloading for text and story generation.

Choose the right creative tier based on what you want to generate.

ModelVRAM neededSketch (12 GB)Canvas (24 GB)Studio (24 GB)Masterwork (48 GB)
Stable Diffusion XL8-12 GBYesYesYesYes
Flux.1 (dev/schnell)12-24 GBTightYesYesYes
Llama 3 8B (Q4)~6 GBYesYesYesYes
Llama 3 70B (Q4)~40 GBNoNoNoYes
Mixtral 8x7B (Q4)~26 GBNoTightTightYes
SDXL LoRA training16-24 GBNoYesYesYes

ComfyUI, LM Studio, and Fooocus all run with a simple double-click — no terminal, no conda, no Docker. Start creating immediately.

PixelForge workstations come with NVIDIA drivers pre-installed. CUDA and cuDNN work out of the box. No driver conflicts.

If you already run AI tools on Windows, PixelForge is identical — just faster. No need to learn Linux or cloud notebooks.

From the collection

RTX 4090 / 24 GB

Great for Stable Diffusion and smaller LLMs

L40S / 48 GB

Faster inference, more VRAM than Canvas

A100 80GB / 80 GB

Run 70B+ models and large batch jobs