bannerbannerExperience Now
WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Stability AI Models/stability-ai/sdxl
text-to-image

text-to-image

Stability AI SDXL | Text-To-Image Generator | WaveSpeedAI

stability-ai/sdxl

Stability AI SDXL is a text-to-image generator that creates beautiful, high-quality images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

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

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.

Your request will cost $0.0026 per run.

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

One more thing::

ExamplesView all

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 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.
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 — Text / Image-to-Image

SDXL is Stability AI’s flagship diffusion model for high-quality image generation. It excels at photorealism, stylized illustration, and product renders.

Key Features

  • Text-to-Image (T2I): Generate fully new images from natural-language prompts.
  • Image-to-Image (I2I): Transform an input image toward your prompt while preserving composition.

Modes & When to Use

  • T2I: Best for concepting and fresh compositions.
  • I2I: Use when you already like the framing/pose and want a new style or content consistent with the source.

Inputs & Parameters

  • prompt (required): Describe subject, style, lighting, camera, mood.
  • image: PNG/JPEG/WebP; used as the starting point.
  • width / height: Flexible canvas; common choices 1024×1024, 1536×1536, 1024×1536, 1536×1024.
  • seed: -1 for random, or set any integer for reproducible results.

How to Use

A) Text-to-Image

  1. Enter a prompt with subject + context + style + lighting + camera.
  2. Set width/height for your target aspect ratio (e.g., 1536×1536 for square).
  3. (Optional) Set seed for repeatability.
  4. Run and iterate on wording or seed.

B) Image-to-Image

  1. Upload an image.
  2. Write a prompt describing the desired change or style.
  3. (Optional) Set seed for repeatability.
  4. Run; tweak strength or prompt until the balance feels right.

Price

  • Per image for $0.0026.

Prompting Tips

  • Structure prompts as: [subject] + [context] + [style/artist] + [lighting] + [camera] + [mood].
  • For photorealism: “cinematic lighting, shallow depth of field, 50mm, natural skin texture.”
  • For products: “studio sweep, three-point lighting, soft reflections, high detail.”
  • Keep negative prompts concise: “blurry, extra fingers, watermark, text, low-res.”
  • Lock a seed once you like the look to iterate predictably.

Notes

  • SDXL will honor platform safety rules; if a prompt is blocked, simplify and try again.
  • Commercial use follows Stability AI licensing and WaveSpeedAI terms.