You’ll need a PC with a modern AMD or Intel processor, 16 gigabytes of RAM, an NVIDIA RTX GPU with 8 gigabytes of memory, and at least 10 gigabytes of available storage. GPUs with more memory will be able to generate larger images without requiring an upgrade.
Steady Diffuse is a popular AI-powered image generator that you can run on your own PC. But what are the minimum specs to run a Stable Diffuse and which components matter the most?
What PC hardware stable diffusion is required?
The most important component for Diffusion Stabilization is your graphics card (GPU). Diffusion stable — at least the major version — runs almost exclusively on your GPU. That means other system components, like your CPU, RAM, and storage drive, aren’t nearly as important.
Note: Community forks sometimes change the way Stable Diffusion works and may result in more CPU and RAM demands on you than the official Stable Diffusion release.
All in all, these are the minimum specs we recommend if you’re building a new PC with Diffuse Stabilization in mind:
- CPU: Any modern AMD or Intel CPU.
- smack: At least 16 gigabytes of DDR4 or DDR5 RAM.
- Warehouse: Any SATA or NVMe solid-state drive from a reputable company with a capacity of 256 gigabytes or more. You need at least 10 gigabytes of free space. Typically, a terabyte drive offers the best price per gigabyte of storage.
- GPUs: Any GeForce RTX GPU with at least 8 gigabytes of GDDR6 memory.
RELATED: How to run stable diffusion on your PC to create AI images
What kind of graphics card (GPU) do you need to run stable diffusion?
The Stable Diffuse community has worked hard to expand the number of devices that Diffuse Stable can run on. We’ve seen Diffuse Stable run on M1 and M2 Macs, old AMD and NVIDIA cards, but they tend to be harder to run and more prone to crashes. NVIDIA RTX GPUs are the only GPUs natively supported by Stable Diffusion at the time of writing in December 2022.
RELATED: How to check which Graphics Card (GPU) is in your PC
Any of the following NVIDIA RTX cards should work fine:
- RTX 2060 (12GB), RTX 2070, RTX 2070 Super, RTX 2080, RTX 2080 Super, RTX 2080 Ti or RTX Titan
- RTX 3060, RTX 3060 Ti, RTX 3070, RTX 3070 Ti, RTX 3080, RTX 3080 (12GB), RTX 3080 Ti, RTX 3090 or RTX 3090 Ti
- RTX 4090, RTX 4080, and Future 40 Series GPUs
Note: The RTX 3050 will also work, but it’s difficult to recommend its price compared to the 12-gigabyte RTX 3060 variant.
Try to buy the latest GPU you can. Any 20, 30, or 40-series GPU with NVIDIA’s 8 gigabytes of memory will work, but older GPUs — even with the same amount of video RAM (VRAM) — will take longer to process. generate images of the same size. If you’re building or upgrading a PC specifically with Steady Diffusion, avoid the older RTX 20 series GPUs unless you find a great deal on one as they are significantly slower.
How much video memory (GPU memory) do you need?
The larger you make your image, the more VRAM Stable Diffusion will use. The minimum The amount of VRAM you should consider is 8 gigabytes.
The unmodified Diffuse release will produce a 256×256 image using 8 GB of VRAM, but you will likely experience problems when trying to create a 512×512 image. If you want to go to a 512×512 image without messing around with settings, buy a GPU with 12 gigabytes of VRAM or more.
The RTX 3060 is a potential option at a fairly low price point. The RTX 3060 is slower than the 3060 Ti, however, the RTX 3060 has 12 gigs of VRAM, while the 3080 Ti has only 8 gigs. The extra VRAM will really shine in the Diffuse Stable, but that comes at the expense of speed and gaming performance.
When it comes to Additional VRAM and Stable Diffuse, there are no limits — Steady Diffusion will gladly use every gigabyte of VRAM available on the RTX 4090. It all depends on the size of the image you’re creating.
Of course, there are all sorts of optimized branches that allow you to use much less VRAM at the expense of speed, but if you want to be sure that it will work, go for an NVIDIA RTX card with less at least 8 gigabytes of memories.
Should you use an optimized stable diffuse fork?
In a word: Yes.
The Stable Diffuse community has done a great job expanding the number of supported GPUs to make Stable Diffusion more accessible.
Community branches often include user interfaces, additional models to refine your work, and optimizations that allow you to create larger images with less VRAM. Some users were able to create 512×512 images with just 4 gigabytes of VRAM using community forks. The same optimizations allow users with 8 and 12 gigabyte GPUs to produce significantly larger images.
The user interface is also a great feature as it makes it easier to use Stable Diffusion.
Just be careful. Most of the modifications you find are written by well-intentioned enthusiasts, but there’s always the possibility that someone is acting maliciously. If your anti-virus software marks a Diffuse Stable fork as malicious, don’t ignore it. Stable diffusion is not known for generating false positives from anti-virus software, so any warnings you receive should be taken seriously.
Once you have the right hardware in place, you can spend your time optimizing the Diffuse Stable prompt instead of your PC.
RELATED: How to write a great steady popular reminder