SA
Image gen6.6B
Image gen

Stable Diffusion XL 1.0

Stable Diffusion · Stability AI Community License

The standard for local image generation. 1024x1024 base resolution. Massive LoRA/checkpoint ecosystem. Runs well on 8GB+ VRAM. VRAM usage varies by resolution and batch size; 6.5GB is for single 1024x1024 generation.

Parameters
6.6B
Architecture
Dense
Context
77 tokens
Released
2023-07-26
Engines
ComfyUI, Automatic1111, Fooocus, InvokeAI

Parameters

6.6B

VRAM

6.5 GB

Context

0K

Formats

1

GPUs

22

Stable Diffusion XL 1.0 (6.6B) requires 6.5 GB VRAM at recommended quality (FP16). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 18 tok/s at FP16. For the best experience, Starter AI Desktop ($582) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

6.5 GB

Quantization

FP16

File Size

6.5 GB

Max Context

0K tokens

Primary Use

Image gen

Compatible GPUs

22 devices

Showing 22 of 22 entries

Hardware

Recommended Builds

Complete PC builds that can run Stable Diffusion XL 1.0.

FAQ

Frequently Asked Questions

How much VRAM does Stable Diffusion XL 1.0 need?
Stable Diffusion XL 1.0 requires 6.5 GB VRAM at recommended quality (FP16).
What is the best GPU for Stable Diffusion XL 1.0?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Stable Diffusion XL 1.0, achieving 18 tok/s at FP16 with an excellent rating.

Related Guides

All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Stable Diffusion is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.