Stable Diffusion XL base 1.0
by Stability AI
Stability AI's open text-to-image latent diffusion model; works alone or with the SDXL refiner for final detail.
AI image generators Open source
1. Price: huggingface.co
Open weights, free to download.
huggingface.coNo quote yet: price is read from the official pages.
2. Commercial use: huggingface.co
“Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses.”
Allowed, as long as the app avoids the restricted uses in Attachment A and binds its users to them.
huggingface.co3. Credit the author: huggingface.co
“You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License”huggingface.co
4. Agent access: github.com/Stability-AI/generative-models
There is no package or API. Files are downloaded by hand from the official site.
github.com/Stability-AI/generative-modelsLicense checked Oct 25, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error
SDXL base 1.0: open model that draws pictures from text
Stable Diffusion XL is a free, open image model from Stability AI that turns a written description into a picture. You download it and run it on a computer with a strong graphics card, or inside an app that runs it for you. Its license allows commercial use, but forbids a list of harmful uses that you must pass on to your own users.
Where you can use it
Artwork for design work
Make illustrations, mood boards or background art from a short description while you design a page, a poster or a game.
A picture feature in a learning app
Let students or users of a creative app turn their own words into a picture, with the model running on your server.
Restyle a sketch or photo
Start from an existing picture and a description, and get a new version that keeps the layout, for example a rough sketch turned into a finished scene.
Replace one part of an image
Mark an area with a mask and describe what should be there, for example swapping the person in a stock-style scene for a diver.
Extra detail with the refiner
Run a second, companion model after the base one to add fine detail to the final picture, at the cost of more time and memory.
Placeholder art for a prototype Idea
Fill a game or app prototype with quick concept pictures so testers see a finished look before an artist draws the real ones.
As reported by Stability AI: torch.compile can make generation 20-30% faster with a recent PyTorch.
Stable Diffusion XL base 1.0 popularity
How to start
Tell your AI assistant
“Generate 1024x1024 images with stabilityai/stable-diffusion-xl-base-1.0 through diffusers (pinned version, 0.19 or newer) in float16 with the fp16 variant, use enable_model_cpu_offload if memory is short, and keep the CreativeML Open RAIL++-M license with any copy of the weights.”
Or install it yourself.
pip install invisible_watermark transformers accelerate safetensors
Show codeStep 1 or Step 2
Load the base model in half precision and generate an image from a prompt on an Nvidia card.
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
With little graphics memory, move parts to the main memory instead of putting the whole model on the card.
pipe.enable_model_cpu_offload()
Mistakes to avoid
The model was built for 1024 pixels and small sizes break down.
Offloading moves idle parts to main memory so the model fits.
The model cannot draw readable text.
The license requires the restrictions to be enforceable on everyone you serve.
License
CreativeML Open RAIL++-M license. You may use it, host it for others and share it, also commercially, under CreativeML Open RAIL++-M. A list of harmful uses is forbidden, and you must pass that list on to your users.
“Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses.” huggingface.co
“You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License” huggingface.co
“You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model” huggingface.co
Copies must carry the license, kept notices and marked changes, with the use restrictions passed on.
“You must cause any modified files to carry prominent notices stating that You changed the files” huggingface.co
“Licensor claims no rights in the Output You generate using the Model.” huggingface.co
AllowedWith conditionsNot allowedNot stated or not checked yet
Is Stable Diffusion XL base 1.0 free for commercial use? The full answer Not legal advice. Check the license page before you ship.
For your agent
License rules tell your agent what it may do with Stable Diffusion XL base 1.0. Paste them into your prompt or AGENTS.md.
- Stable Diffusion XL base 1.0 (AI image generators). Stability AI's open text-to-image latent diffusion model; works alone or with the SDXL refiner for final detail. Price: free; commercial use with conditions; no credit needed; ship inside your app with conditions.
Connect: download from https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0 (no API).
Rule: Follow the use-based restrictions in Attachment A of the license.
Rule: Pass those restrictions on to your users if you host or redistribute the model.
Rule: Ship a copy of the license with any redistributed weights or derivatives.
License: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md (checked 2026-10-25; details: https://agentgid.com/assets/sdxl/)
Alternatives
Stable Diffusion XL base 1.0 This page
Pick InvokeAI when you want a ready app with a canvas and workflows that runs SDXL and other models for you.
Pick FLUX.1 [dev] for a newer open-weight model for non-commercial work; commercial use needs a paid license.
Pick OpenAI GPT Image when you have no graphics card and prefer paying per image through an online service.
Efficient open-weights image generation model built on a single-stream diffusion transformer.
Tencent's diffusion-transformer text-to-image model with fine-grained Chinese and English prompt understanding.
Questions
Can I sell images I make with SDXL?
The license claims no rights in your output, but the use restrictions still apply to how you use it.
Can I offer SDXL to my users as an online service?
Yes, hosting for others is allowed if your terms include the use restrictions and you give users notice of them.
Do I need the refiner model?
No. The base model works alone; the refiner is an optional second step for fine detail.
Are my images marked as AI-made?
Diffusers adds an invisible watermark by default when the invisible-watermark package is installed.