Stability AI · 3.5B parameters · CreativeML Open RAIL++-M
What GPU do you need to run Stable Diffusion XL?Memory and cards.
Stable Diffusion XL needs about 8 GB of GPU memory (VRAM) at its smallest (Minimum, one image at a time), so a 16 GB card such as an RTX 4080 runs it. The cheapest card on our list that fits, an RTX 4060 Ti 16GB, costs about $0.14 an hour. At its largest (Comfortable, with LoRAs and upscaling) it needs about 12 GB.
GPU memory
Stable Diffusion XL, by version.
Resolution, batch size, upscalers and extra LoRAs all add memory. How we work it out
| Version | Memory needed | Card size | Cards that fit | From |
|---|---|---|---|---|
| Minimum, one image at a time | about 8 GB | 16–20 GB | RTX 4090, RTX 5090, RTX 3090, RTX 4080, RTX 3090 Ti, RTX 5080, RTX 5070 Ti, RTX 4070 Ti SUPER, RTX 5060 Ti 16GB, RTX 4060 Ti 16GB | $0.14/hr on an RTX 4060 Ti 16GB |
| Comfortable, with LoRAs and upscaling | about 12 GB | 16–20 GB | RTX 4090, RTX 5090, RTX 3090, RTX 4080, RTX 3090 Ti, RTX 5080, RTX 5070 Ti, RTX 4070 Ti SUPER, RTX 5060 Ti 16GB, RTX 4060 Ti 16GB | $0.14/hr on an RTX 4060 Ti 16GB |
The most fine-tuned image model: thousands of community styles and LoRAs build on it.
Run it
Start Stable Diffusion XL in minutes.
The rented machine downloads it straight from Hugging Face, not through your computer. On KernelMachine, Rent an Image maker with these files, below: they load into ComfyUI's model folders by themselves once it's ready. Already renting one? Pick it under Load from link on the rental's page, or run km load with each link. ComfyUI on a rented GPU
$ km load https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors
Files to load
Stable Diffusion XL in ComfyUI.
The files ComfyUI's own "SDXL1.0: Text to Image (Simple)" template uses, 6.9 GB in all. Each goes in its own folder, and Load from link puts it there. Then open that template from ComfyUI's template menu.
| File | Folder | Size |
|---|---|---|
| sd_xl_base_1.0.safetensors | models/checkpoints | 6.9 GB |
They start loading as soon as the rental is ready, straight from Hugging Face to the machine. Already renting an Image maker? Pick Stable Diffusion XL under Load from link on the rental's page. A card with 16 GB or more runs them.
Common questions
Questions, answered plainly.
How much VRAM does Stable Diffusion XL need?
Minimum, one image at a time: about 8 GB; Comfortable, with LoRAs and upscaling: about 12 GB.
Can an RTX 4090 run Stable Diffusion XL?
Yes. Stable Diffusion XL (Comfortable, with LoRAs and upscaling) needs about 12 GB, which fits in the RTX 4090's 24 GB.
Can I run Stable Diffusion XL on KernelMachine?
Yes. Rent an Image maker with these files, on this page, starts ComfyUI on the cheapest card with 16 GB or more, and the machine downloads each file from Hugging Face into ComfyUI's folders once it's ready. Already renting an Image maker? Pick Stable Diffusion XL under Load from link on the rental's page.
Other models
Compare with other image and video models.
Preparing an invite-only beta
Get an email when access opens.
No launch date is set. We'll email you once when KernelMachine opens. Nothing else.