Use cases
AI compute for generation

Image Generation GPU Workspaces

Launch GPU workspaces for ComfyUI, Stable Diffusion, Flux, and image pipelines without configuring drivers or runtime dependencies by hand.

Ready template

Recommended workspace

Template

ComfyUI

GPU

L40S

Access

Browser + SSH

Billing

Per-hour

porfal create --use-case image-generationworkspace ready: browser + ssh

Workloads

ComfyUI workflows

Stable Diffusion

Flux experiments

Batch rendering

Recommended stack

ComfyUI

Ubuntu CUDA

PyTorch

JupyterLab

GPU fit

L40S

RTX 6000 Ada

RTX 4090

Why Porfal

Dedicated GPU compute without infrastructure work.

Pick a GPU, launch the template, connect from browser or SSH, and stop the workspace when the run is done.

Start from a generation-ready template.

Keep workflows isolated per project or client.

Scale up to larger VRAM when pipelines grow.

Workflow

A short path from GPU to running workload.

1

Choose L40S or RTX 4090

2

Select ComfyUI

3

Upload workflow

4

Generate in browser