Stable Diffusion WebUI hosting
The AUTOMATIC1111 interface — GPU-bound, listed for completeness.
Stable Diffusion WebUI is in our catalogue but not yet orderable: it needs GPU capacity, and we would rather list it honestly than sell a CPU plan that disappoints. Tell us what you need and we will tell you where it stands.
Stable Diffusion WebUI is the browser interface written by AUTOMATIC1111 on top of Gradio and PyTorch, and for several years the default way to run diffusion models yourself. It covers txt2img and img2img, inpainting, outpainting, upscaling, LoRA and textual inversion, checkpoint merging and an optional HTTP API, and its extension ecosystem adds ControlNet and much more. It runs SD 1.5, SD 2.x, SDXL and, since version 1.10, SD3 Medium checkpoints.
Image generation is dominated by the GPU: each step is a large tensor workload that a CPU completes many times more slowly. That is why the project’s own guidance starts at an NVIDIA card with 4 GB of VRAM, and why we list it without selling a plan. The latest tagged release, 1.10.1, dates from February 2025, so newer model families tend to arrive in forks and in ComfyUI first.
What Stable Diffusion WebUI needs
When GPU plans launch: a single Python container running the WebUI with PyTorch and CUDA, with models, outputs and extensions on persistent volumes.
What we configure for you
- --listen with --gradio-auth so the interface is never open without a password
- --api enabled if you want HTTP access from other tools
- Checkpoint, LoRA and VAE folders on a persistent volume you can fill over SFTP
- Extensions folder persisted across updates
- TLS on your hostname
Which plan fits
There are no tiers yet. A realistic plan would need an NVIDIA GPU with at least 8 GB of VRAM for SDXL, plus 16 GB of system RAM for loading checkpoints and enough disk for several multi-gigabyte models.
The honest limits
Not orderable today: we will not offer it on CPU. Upstream development has slowed since the 1.10.1 release, so support for the newest model families is limited.
What people run Stable Diffusion WebUI for
Inpainting and outpainting
Repair or extend existing images with masked regeneration.
LoRA and style experiments
Stack LoRAs and embeddings on a base checkpoint and compare results side by side.
Image API for other apps
Run with --api so scripts and bots can request images over HTTP.
Licence and version policy
| Item | Position |
|---|---|
| Upstream licence | AGPL-3.0 |
| Sold as managed hosting | No |
| Tenancy | Single tenant — one customer per instance |
| Patching | Critical advisories within 24 hours, high severity within 72 |
Our full position on licences, including the applications we decline to sell, is on the licensing page.
Reading on Stable Diffusion WebUI
Works well with Stable Diffusion WebUI
ComfyUI
Node-based image and video generation — waiting on GPU capacity.
on requestDetails →
InvokeAI
A studio-style diffusion workspace — GPU-bound.
on requestDetails →More Speech, image & video we host
Stable Diffusion WebUI hosting: your questions
Why can I not order Stable Diffusion WebUI now?
What GPU would it need?
Should I choose WebUI, ComfyUI or InvokeAI?
Does it have an API?
Which licence does it use?
Tell us what you need
If this is the app you need, say so — demand is how things move up the list.