from 16 GBImages
Images · Flux
Images from a text prompt: illustrations, covers, social posts and product shots.
from €0.16/h · RTX 4060 Ti, 16 GB
Ready-made app · Stable Diffusion
Run Stable Diffusion and SDXL on a rented GPU
SDXL runs on a 12 GB card, SD 1.5 needs 6 GB, and SD 3.5 Large is comfortable on 24 GB. The ready-made Images · SDXL app installs ComfyUI and SDXL 1.0 on its own: the server starts in 2–5 minutes, and downloading the model takes a few more.
- App
- Images · SDXL
- GPU
- RTX 3060, 12 GB
- Price
- from €0.12/h
To launch, your balance must cover one hour of the machine. You are billed by the minute for actual use. The server installs Images · SDXL for you.
from 12 GBof video memory
2–5 minutesuntil the server is up
By the minutebilled from your balance
ComfyUIopens in your browser
Examples: what went in and what came out
Prompts and results from the ready-made app, no retouching. You can run the same prompt on your own server.
Watercolor illustration of a fox reading a book in an autumn forest
1024×1024 · 25 steps · 25 s on an RTX 3060
Cyberpunk city street at night, neon signs, rain reflections, cinematic
1024×1024 · 20 s on an RTX 3060 Launch SDXL · from €0.12/h RTX 3060, 12 GB · billed by the minute
What is on the server after launch
Images · SDXL is free: you only pay for GPU time. Everything installs at launch; there is nothing to configure by hand.
- ComfyUI in your browser
- Stable Diffusion XL 1.0 base
- PyTorch on CUDA 12.8, Jupyter and SSH
- A button in the dashboard that opens ComfyUI
- Your folder with models and results can be saved when you stop
How much memory you need and which GPU to pick
Images · SDXL needs a card with at least 12 GB; the cheapest suitable one is the RTX 3060. The table shows memory for other versions and tasks. Prices update from available catalogue machines when you open the page.
| Version | Video memoryMemory | Suitable GPUGPU | Price per hourPer hour |
|---|---|---|---|
| Stable Diffusion 1.5 | from 6 GB | RTX 3060 | €0.12 |
| SDXL 1.0 | from 12 GB | RTX 3060 | €0.12 |
| SDXL + ControlNet + LoRA | from 16 GB | RTX 4060 Ti | €0.16 |
| SD 3.5 Large | from 24 GB | RTX 3090 | €0.30 |
Guide from real launches: complex graphs and high resolutions need more memory. Pick: the cheapest single card with enough memory. All GPUs and prices
How to run Stable Diffusion in 3 steps
- Sign up and top up. Create an account and top up from €10. To launch, your balance must cover at least one hour of the chosen machine; after that you pay by the minute.
- Launch the app. Click Launch SDXL. The dashboard opens with Images · SDXL and a card with at least 12 GB already selected; check the price and confirm.
- Work in your browser. The server starts in 2–5 minutes, and the app downloads the model in a few more. Then press the ComfyUI button in the dashboard and type your prompt.
Finished? Stop the server in the dashboard and billing stops. Save and stop keeps /workspace for €0.03 per GB per month, and it comes back on your next server automatically.
Commands for a manual install on an empty server
ComfyUI
git clone https://github.com/comfyanonymous/ComfyUI && cd ComfyUI
pip install -r requirements.txt
python main.py --listen 0.0.0.0
What people run Stable Diffusion for
01
Art in any style
Anime, photorealism, watercolour, pixel art: the community has published thousands of models and LoRAs for SDXL.
02
An image from a pose or a sketch
ControlNet follows a person’s pose, the outline of a sketch or a depth map.
03
Redraw part of a frame
Inpainting changes the selected area and leaves the rest of the image untouched.
04
Hundreds of variations from a list
Batch generation through the ComfyUI API: prompts come from a file, images land in a folder.
Tips before you launch
- For batches of hundreds of images, one RTX 4090 pays off better than two weaker cards.
- Training an SDXL LoRA is comfortable on 24 GB.
- Keep your models in /workspace: that makes it easy to save them and to collect results.
Other ready-made apps
Each app installs its interface and model on its own. You only pay for GPU time.
from 24 GBImages
Images · Qwen-Image
Posters, signs and banners with the lettering drawn right into the image.
from €0.30/h · RTX 3090, 24 GB
from 24 GBImages
Photo editor · Qwen Edit
Edit a photo with words: swap the background, turn day into evening, remove an object.
from €0.30/h · RTX 3090, 24 GB
Frequently asked questions
Which GPU do I need for SDXL?
At least 12 GB, and 16–24 GB is comfortable, especially with ControlNet and LoRA.
How much does it cost to generate 1,000 images?
An RTX 4090 makes an SDXL image in a few seconds, so a thousand images take about 1–2 hours: roughly €0.59–€1.18.
What is in the ready-made SDXL app?
ComfyUI and the Stable Diffusion XL 1.0 base model. You can download other checkpoints and LoRAs into ComfyUI/models and save the folder when you stop, so you don’t have to download them again.
How long does a launch take?
The server usually starts in 2–5 minutes. Then the app downloads the model on its own, which takes a few more minutes, and a button that opens ComfyUI appears in the dashboard.
What happens to my models and results after I stop?
When you stop, click Save and stop: the /workspace folder with your models, LoRAs and results goes to storage for €0.03 per GB per month and comes back on your next server automatically. If you stop without saving, the disk is deleted.
How is it billed?
By the minute from your balance in euros. Top up from €10; to launch, your balance must cover at least one hour of the chosen machine. Stop the server and billing stops.
A server is usually ready in 2–5 minutes
Sign up in a minute, top up from €10, pay by the minute. Stop the server and billing stops.