Get started
Image model

Stable Diffusion - a neural network for image generation

Stable Diffusion models in GPTunneL: the open neural network for generating pictures from a description. Pay per image, no subscription and no VPN.

What the Stable Diffusion family is good at

Traits Stability AI keeps from one generation to the next — you can count on them whichever model you pick.

An open model

Stable Diffusion is published and runs on an ordinary graphics card — the entire image-generation market started with it.

A huge ecosystem

More fine-tunes, styles and tools have been built around this family than any other: almost every task already has a recipe.

Low price

One of the most affordable models in the service — the choice when you need a lot of frames on a limited budget.

Any style

From photorealism to anime and pixel art: the family is not tied to a single visual language.

Which model to pick

The service carries two models from the family — they differ in generation and in frame quality.

SDXLThe classic, and draftsSD 3.5The default pick
Best forTrying ideas fast, familiar stylesFinished images, complex scenes
DetailMediumHigh
Text on the imagePoorPassable
PriceLowestLow

Figures come from the platform catalogue. Exact per-model prices are on the Pricing

Every Stable Diffusion model

Release dates follow Stability AI's official announcements.

October 2024

SD 3.5

The current generation: it follows the prompt noticeably better and handles complex scenes with more confidence.

July 2023

SDXL

The generation that made Stable Diffusion mainstream: quality rose far enough that the pictures stopped giving themselves away at a glance.

August 2022

Stable Diffusion 1.5

The first public version and the start of the whole image-generation market: the weights were released openly and anyone could run the model.

How billing works

There is no subscription: you top up one balance and spend it on any model on the platform.

Pay per generation

You are charged for exactly what the generation used. Not using it costs nothing: no limits, no monthly fee.

One balance for every model

Stable Diffusion, ChatGPT, Claude, image and video generation — all out of the same wallet. No separate subscription per service.

Top up the way you prefer

International cards, Apple Pay, Google Pay or crypto. The minimum top-up is $5.

See pricing

Sample generations

Every image was generated in Stable Diffusion from a text description. The model is not tied to one style: the prompt can ask for a photograph, an illustration or flat graphics.

How to get started with Stable Diffusion

Sign in to GPTunneL
One account for every model on the platform.
A silhouette in a hat and coat against a night city, red smoke, black-and-white noir
SD 3.5
A frame generated in Stable Diffusion from a text description

Sign in whichever way suits you.

The model switches right inside the input — you can change it between frames.

The finished frame arrives at full resolution.

Try Stable Diffusion in GPTunneL

Signing up takes a minute, and $5 on the balance is enough to see whether the model fits your task.

Frequently asked questions

No. Requests go through GPTunneL's infrastructure, so the models open like any ordinary website — no VPN and no proxy.

Stable Diffusion is an open neural network that generates images from a text description — and the model the whole market started with. Its weights were published in 2022 and anyone could run it, which is where the huge ecosystem of fine-tunes, styles and tools around it comes from.

The family is not tied to one visual language: a prompt can ask for a photograph, an illustration or flat graphics, and the model will not drag the picture back towards a house style. It trails newer generators like FLUX on photorealism and on text within the image, but it remains one of the cheapest — the choice when you need a lot of frames.

Stable Diffusion models are available in GPTunneL without a graphics card of your own — worldwide, without a VPN, with one balance and billing per generated frame.