Stable Diffusion XL 1.0
Q4 GGUF download: gpustack/stable-diffusion-xl-base-1.0-GGUF - 3.94 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve stabilityai/stable-diffusion-xl-base-1.0New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Stable Diffusion XL 1.0
Stable Diffusion XL 1.0 is Stability AI's foundational text-to-image model. With a 3.5B parameter ensemble (base + refiner), it generates 1024×1024 images and was the model that kicked off the open image generation revolution. Still one of the most downloaded models at 1.74M monthly.
Architecture
SDXL uses a two-stage pipeline:
- Base model (3.5B) - generates latents from text prompt
- Refiner model - enhances detail and quality
Usage
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="a photo of a cat on a park bench",
height=1024, width=1024
).images[0]When to use
- Legacy workflows - huge ecosystem of LoRAs and extensions
- Creative art - flexible and well-understood
- Open research - fully open weights (CreativeML Open RAIL-M)
From the community
What users are saying
“I think I know what this issue is. It is likely due to the model files not fully downloading, so I'd recommend clearing all HF cache and then rerunning the script. Make sure you have enough storage for the model (roughly 6 GB).”
“well. you must create an access token in your profile part, and then use hg-cli to download like this: hf download google/gemma-4-E4B-it --local-dir . --token hftvRrSpRU”
“import torch from diffusers import DiffusionPipeline pipe = DiffusionPipeline.frompretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, devicemap="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]”
Frequently asked
Quick answers to common questions
How much VRAM does Stable Diffusion XL 1.0 need?
Stable Diffusion XL 1.0 with 3B parameters needs significant VRAM depending on quantization. Use our VRAM calculator for an exact estimate.
Is Stable Diffusion XL 1.0 better than other Stable Diffusion models?
Stable Diffusion XL 1.0 has 3B parameters with 8,192 context - a strong choice for text-to-image, image-generation.
What license is Stable Diffusion XL 1.0 under?
Stable Diffusion XL 1.0 is released under the Other license, making it suitable for most commercial and personal projects.
What hardware runs Stable Diffusion XL 1.0 well?
With 3B parameters, Stable Diffusion XL 1.0 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Stable Diffusion XL 1.0?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Step up to Q5_K_M or Q8_0 only if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with Stable Diffusion XL 1.0?
Stable Diffusion XL 1.0 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Compare & pair with
Similar models and recommended hardware
Related models
Nearby options
Similar models and compatible hardware by spec