Can I install Stable Diffusion without a graphics card?

It runs on CPU, but an image takes minutes rather than seconds. Use a cloud GPU or the free tools on this site instead.

How much disk space does it take?

About 10 GB for the web UI and its dependencies, plus 2 to 7 GB per SD 1.5 or SDXL model and a few megabytes to a few hundred per LoRA. Allow 50 GB if you collect models.

Is it legal and free to install?

Yes. The web UI is open source (AGPL) and the models are downloadable under their licences, free for personal and most commercial uses.

Download and install Stable Diffusion: Windows, Linux, Mac

To run Stable Diffusion on your own computer you need a GPU with at least 6 GB of VRAM, Python 3.10, Git, the Automatic1111 web UI and a model file. Allow 15 GB of disk space and several gigabytes of downloads; after that, generation is free, offline and private.

Requirements

Component	Minimum	Comfortable
GPU	NVIDIA 6 GB VRAM (SD 1.5)	NVIDIA 8–12 GB (SDXL), 16 GB (SD 3.5 Large, in ComfyUI)
AMD / Apple	ROCm on Linux, Apple Silicon 16 GB RAM	slower but works; on Windows, AMD cards need ComfyUI or a fork of the web UI
RAM	16 GB	32 GB
Disk	15 GB (app + one model)	50 GB+ for several models
OS	Windows 10/11, Ubuntu 22.04+, macOS 13+

No compatible GPU? The tools on this site need no installation: inpainting and upscaling run on our hardware, SDXL is a hosted demo embedded in the page.

Step by step (Windows, Automatic1111)

Install Python 3.10.6 and tick Add Python to PATH. Newer Python versions break some dependencies.
Install Git with default options.
Open a terminal in the folder of your choice and run git clone -b dev https://github.com/AUTOMATIC1111/stable-diffusion-webui. The dev branch is deliberate: the default one has not changed since July 2024 and its first start now fails.
Download a model: SDXL 1.0 base (6.9 GB) and optionally the refiner, or Stable Diffusion 1.5 (4.3 GB). Take the .safetensors file.
Put the model in stable-diffusion-webui/models/Stable-diffusion/.
Double-click webui-user.bat. The first start downloads several gigabytes of dependencies; how long it takes depends on your connection.
Open http://127.0.0.1:7860 in your browser, pick the model at the top left, type a prompt, click Generate.

On Linux and macOS, first install Python 3.10 or 3.11 and the system packages listed in the project README, then run ./webui.sh instead of the .bat file; the script creates its own Python environment.

Useful launch options

Edit webui-user.bat and set COMMANDLINE_ARGS:

--xformers: faster and lighter on NVIDIA.
--medvram or --lowvram: for 4 to 6 GB cards, at the cost of speed.
--listen: reach the interface from another device on your network.
--api: enables the REST API used by scripts (this site talks to its own Automatic1111 that way).

Common errors

CUDA out of memory: lower the image size, add --medvram, close other GPU programs.
Torch not compiled with CUDA: an unsupported Python version or a CPU-only PyTorch; reinstall with Python 3.10 and delete the venv folder.
No model found: the file is not in models/Stable-diffusion or has the wrong extension.
Black images on AMD or Apple: add --no-half or --upcast-sampling.

Alternatives to Automatic1111

Forge is a faster fork with the same interface; it too has had no updates since June 2025. ComfyUI uses a node graph, ideal for SD 3.5 and Flux and for complex pipelines. Fooocus hides most settings behind one prompt box, as Midjourney does; it runs only SDXL models and now receives nothing but bug fixes. Forge and ComfyUI read the same model and LoRA files as Automatic1111.

How to download and install Stable Diffusion locally?