WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Stability AI Models/stability-ai/sdxl

text-to-image

stability-ai/sdxl

A text-to-image generative AI model that creates beautiful images.

Doc

Hint: You can drag and drop a file or click to upload

width
height
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Your request will cost $0.0026 per run.

For $1 you can run this model approximately 384 times.

One more thing:

ExamplesView all

A candid street style photograph of a young woman with short messy blonde hair, she is laughing heartily, mid-sentence, natural afternoon sunlight hitting her face, background is a bustling city street with blurred yellow taxis, shot on a 35mm film camera, photorealistic, shallow depth of field, golden hour glow.
Expansive, breathtaking landscape of the Scottish Highlands at dawn, mist rolling through the valleys, a lone stag standing on a distant hill, the sky is painted with soft hues of pink and orange, wide-angle lens, photorealistic, epic scale, serene and majestic atmosphere.
A cozy, sun-drenched living room with a bohemian-style interior, a comfortable-looking sofa with colorful pillows, a cat sleeping peacefully on a knitted blanket, sunlight filtering through a large window creating beautiful dust particles in the air, warm and inviting, photorealistic, detailed textures.
An artist's messy but organized workbench, various paint brushes in a jar, squeezed tubes of oil paint, palettes with mixed colors, a half-finished canvas on an easel, soft, diffused light from a nearby window, top-down view (flat lay), realistic clutter, highly detailed.
Close-up food photography of a juicy, gourmet cheeseburger on a rustic wooden board, melted cheddar cheese dripping down the side, sesame seed bun is perfectly toasted, crispy bacon and fresh lettuce are visible, shallow depth of field, professional studio lighting, mouth-watering details.
A rain-slicked neon-lit street in a futuristic Tokyo, reflections of towering holographic advertisements shimmer on the wet pavement, a lone figure with a glowing umbrella walks down the alley, steam rises from manholes, cyberpunk aesthetic, cinematic, volumetric lighting, Blade Runner style.
A giant, antique gramophone growing out of a desolate desert landscape, its horn pointed towards a sky filled with two moons, the scene is bathed in a surreal twilight glow, style of Salvador Dalí, hyperrealistic detail on the cracked desert floor and the weathered brass of the gramophone.

README

SDXL is a text-to-image generative AI model developed by Stability AI that creates beautiful images. It is the successor to Stable Diffusion.

Features:

  • Text-to-image generation
  • In-painting: Generates images by in-painting parts of an existing image
  • Image-to-image generation: Transforms an input image towards a prompt
  • Refinement: You can use a separate refiner model to add finer detail to your output

Image-to-image generation:

  • Enter a prompt that describes what you want the output image to look like
  • Select an input image in the image field
  • The prompt_strength field changes how strongly the prompt is applied to the input image

Refinement:

  • You can use the refiner in two ways:
    • As an ensemble of experts (base_model_refiner option)
    • In ensemble of experts mode, the SDXL base model handles the steps at the beginning (high noise), before handing over to the refining model for the final steps (low noise)
  • You get a more detailed image from fewer steps
  • You can change the point at which that handover happens, we default to 0.8 (80%)
  • In this mode you take your final output from SDXL base model and pass it to the refiner
  • You can define how many steps the refiner takes