Home Artists Prompts GPT


Stable Diffusion XL 1.0 demo




Advertisement

Generate 1024×1024 images with Stable Diffusion XL 1.0 for free, directly in this page and without an account. Type a prompt, optionally a negative prompt, and get a picture in about 15 to 40 seconds. SDXL is the model that reacts best to artist names and detailed style words.

How to use Stable Diffusion XL 1.0

  1. Write your prompt in English: subject first, then style, lighting and a few quality words.
  2. Add a negative prompt such as "blurry, deformed, watermark, text" if the first result has defects.
  3. Click Run and wait for the queue; the image appears in the same frame.
  4. Right-click the image to save it, or refine the prompt and run again.

Limits and questions

Is there a limit on the number of images?

No hard limit, but the demo shares a GPU with other visitors: at busy times you wait in a queue. Members get a dedicated queue on the txt2img XL page.

Which image sizes are supported?

SDXL is trained at 1024×1024 and works well at any 1-megapixel aspect ratio such as 1152×896 or 896×1152. Smaller sizes give worse compositions.

Why does the demo sometimes fail to load?

This demo is hosted by a third party (Hugging Face Space) and embedded here; it can be slow, queued or temporarily unavailable when the host is busy. Nothing to install, no account needed.

Read the guide: SDXL vs Stable Diffusion 3 vs SD 1.5: which model to use?