Stable Diffusion XL
SDXL 1.0: A Leap Forward in AI Image Generation
Try an example
Breathtaking line art drawing
Magical realism, ghost riders in the sky
A cherry blossom tree in full bloom amidst an arctic tundra showering petals on a polar bear
Detailed photo of a creature with the body of a lion and the wings of an eagle cinematic still
Portrait photo of an anthropomorphic farmer cat holding a shovel in a garden vintage film photo
A taxi driver in a barren marsh background, muted colors, 1900s
Blue furry monster with two large eyes and a big nose on white background, cute, first day of school, photo shooting, pixar animation
Pink llama with a fuzzy hairdo, positive energy, happy, octane, substance, art history museum 8k
Under water photography, whale swimming through a cloud of krill, national geographic, nature photography, nikon dslr, wide angle shot
Bee flying out of a glass jar in a green and red leafy basket, glass and lens flare, diffuse lighting elegant
A layer cake made out of a stratographic cross-section of the Sonoran Desert
A frozen castle made entirely of ice cream in a land of cotton candy clouds and lollipop trees
Lebanon street cinematic
Two hands silhouettes reaching to the sky reaching the clouds
A teal flower in a barren garden, beautiful villa background, octane, redshift, highly detailed
Elegant lavender garnish cocktail idea, cocktail glass, realistic, sharp focus, 8k high definition, insanely detailed, intricate
Sunrise over a mountain range in the alpes
Woman standing in front of a window with her hair blowing, modern anime, highly detailed, digital drawing, perfect composition, light atmosphere, evening light
Glowing jellyfish floating through a foggy forest at twilight
Aesthetic magical realism Through the Yellow Windows of the Last Train grainy film
Photo of a brooding serious bearded old
A lion made entirely of autumn leaves. standing on a hill overlooking a crystal clear lake
A 3d cube shaped hamburger
An astronaut sitting on the moon, friendly town background, stars, beautiful
Man in a leather jacket standing next to a motorcycle light shadow effects intricate highly detailed digital
Robotic hand with gold and white accents
Woman with gold paint on her face sitting on steps, fashion pose bust shot cinematic dynamic composition
Shot of Vaporwave fashion dog in miami
1990s anime low resolution screengrab couple walking away in street at night
Skeleton man going on an adventure in the foggy hills of Ireland wearing a cape
Construction site tilt-shift effect
A laptop computer from the 90's in the style of vaporwave, pastel colors
Black muscle car, with a golden engine in the front, empty street, sunny city background
Miniature house with plants in the potted area, hyper realism, dramatic ambient lighting, high detail
surrealistic painting of a water melon with egg yolk inside
A mechanical sphere floating over a pink desert, 1970's sci fi, by Ridley Scott, Alfonso Cuarón
Stable Diffusion XL
Generate high-resolution realistic images with AI
Uncrop your photos to any image format
Create multiple variants of an image with Stable Diffusion
Transform your doodles into real images in seconds
Remove objects, people, text and defects from your pictures automatically.
Extract the main subject from a picture with incredible accuracy. It's like magic.
Relight your images with beautiful lights.
Upscale your images by 2x or 4x in seconds. It can also remove noise and recover beautiful details.
Teleport anything, anywhere with AI
Remove text from any image
Replace gray sky with blue sky in a snap
Frequently Asked Questions
What is Stable Diffusion XL 1.0?
Stable Diffusion XL 1.0 (SDXL 1.0) is the most advanced development in the Stable Diffusion text-to-image suite of models launched by Stability AI.
SDXL 1.0 is released under the CreativeML OpenRAIL++-M License. Details on this license can be found here.
The weights of SDXL 1.0 and the associated source code have been released on the Stability AI GitHub page.
How to generate images from text?
Stable Diffusion can take an English text as an input, called the "text prompt", and generate images that match the text description. These kinds of algorithms are called "text-to-image".
First, describe what you want, and Clipdrop Stable Diffusion XL will generate four pictures for you. You can also add a style to the prompt.
Then you can retry until you find the perfect picture or customize your text prompts. When you find an image that works, you can download it!
What is the official Stable Diffusion Demo?
How to test Stable Diffusion for free?
To try Stable Diffusion for free:
1) Use the official Stable Diffusion link.
2) Type a prompt or use one pre-written example
3) Stable Diffusion will generate a full resolution image