Stable Diffusion XL 1.0
Stableby Stability AI
Industry standard image generation model. 2.6B UNet with dual text encoder (CLIP ViT-L 0.123B + OpenCLIP ViT-bigG 0.695B). Massive ecosystem of LoRAs, ControlNets, and community resources.
VRAM requirements, GPU fit, and setup notes for Stable Diffusion XL 1.0, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI, Automatic1111, and Diffusers support. Best download size: ~6.9 GB at FP16.
- Largest ecosystem of LoRAs and ControlNets
- Runs on 8GB+ VRAM GPUs
- Dual CLIP text encoder
- Huge community support and resources
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Stable Diffusion XL 1.0 outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
Text-image alignment accuracy (higher is better)
VRAM Requirements by Resolution and Precision
Compare which GPUs can run Stable Diffusion XL 1.0 at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.
FP16 (full precision)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 6.5 GB | S● | S● | A● | S● |
| 768×768 | 7.8 GB | S● | S● | B● | S● |
| 1024×1024 | 8.0 GB | S● | S● | B● | S● |
Optimization Tips
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
ControlNets available
Add guided generation with 5 adapters (+1.2 GB VRAM each)
Rich LoRA ecosystem
Customize style, characters, and quality with community LoRAs
Run with Python
from diffusers import StableDiffusionXLPipeline
import torch
pipe = StableDiffusionXLPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16
)
pipe.to("cuda")
image = pipe(
prompt="your prompt here",
num_inference_steps=30,
guidance_scale=7.5,
height=1024,
width=1024,
).images[0]
image.save("output.png")Get started
Setup instructions for running Stable Diffusion XL 1.0 locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/3. Launch ComfyUI
python main.pyComfyUI Workflow
Basic txt2img workflow for Stable Diffusion XL 1.0
Drag & drop into ComfyUI or use File → Import
Memory Breakdown
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Estimated Generation Time
Time per image at 1024×1024, 28 steps, FP16.
Sample Outputs
Available Formats, Downloads & Setup
Download Stable Diffusion XL 1.0 in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
ControlNet Support
5 ControlNets available for Stable Diffusion XL 1.0. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.
Canny Edge
+1.2 GB VRAMEdge detection for structural guidance. The most popular SDXL ControlNet.
Depth Map
+1.2 GB VRAMDepth-based spatial control for maintaining 3D composition.
OpenPose
+1.2 GB VRAMHuman pose control for character positioning and body language.
IP-Adapter
+1.5 GB VRAMUse reference images to guide style and composition. Works like 'image prompting'.
Union (Multi-Control)
+1.2 GB VRAMSingle model supporting canny, depth, pose, tile, and other conditions.
LoRA Ecosystem
Large EcosystemHundreds of LoRAs available on CivitAI and HuggingFace covering styles, characters, concepts, and quality improvements. SDXL has the second-largest LoRA ecosystem after SD 1.5.
Approximately 5,000 LoRAs available on CivitAI. Each LoRA adds ~0.2 GB VRAM.
Popular LoRAs for Stable Diffusion XL 1.0
Related Workflows
You might also like
Frequently asked questions
FAQ — Stable Diffusion XL 1.0 VRAM, Runtimes & Fit
How much VRAM does Stable Diffusion XL 1.0 need?
Stable Diffusion XL 1.0 (2.6B parameters) requires approximately 8.0 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.
Can I run Stable Diffusion XL 1.0 on an 8GB GPU?
Stable Diffusion XL 1.0 usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.
Does Stable Diffusion XL 1.0 work in ComfyUI and Automatic1111?
Stable Diffusion XL 1.0 is marked for ComfyUI, Automatic1111, and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.
Can I run Stable Diffusion XL 1.0 on RTX 4090?
Yes, the RTX 4090 (24 GB VRAM) can run Stable Diffusion XL 1.0 comfortably at FP16. Expected generation time is around ~4s per image at 1024×1024.
Does Stable Diffusion XL 1.0 support ControlNet?
Yes, Stable Diffusion XL 1.0 has 5 ControlNet adapters available: Canny Edge, Depth Map, OpenPose, IP-Adapter, Union (Multi-Control). Each ControlNet adds roughly 1.2 GB of extra VRAM.
Does Stable Diffusion XL 1.0 have LoRA support?
Hundreds of LoRAs available on CivitAI and HuggingFace covering styles, characters, concepts, and quality improvements. SDXL has the second-largest LoRA ecosystem after SD 1.5. The LoRA ecosystem for Stable Diffusion XL 1.0 is rated as "large". There are approximately 5,000 LoRAs available on Civitai. Each LoRA adds roughly 0.2 GB of extra VRAM.
How fast is Stable Diffusion XL 1.0?
On a reference GPU (RTX 4090 24GB), Stable Diffusion XL 1.0 generates a 1024×1024 image in approximately ~4s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.
About Stable Diffusion XL 1.0
See also