Stability AI SDXL LoRA API

stability-ai /

Stability AI SDXL LoRA is a text-to-image model that generates high-quality images and supports LoRA for adaptation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

lora-support

Input

Enable Safety Checker

Idle

On the desolate, red-dusted surface of Mars, an astronaut is kneeling, gazing in awe at a single, vibrant green sprout miraculously growing from the alien soil. The astronaut's helmet visor clearly reflects the tiny, resilient plant. The background is the vast Martian horizon and distant, blurred mountains.

$0.001per run·~1000 / $1

ExamplesView all

On a flour-dusted workbench in a rustic bakery, a baker's hands knead a large dough with force. At the exact moment of impact, a cloud of flour explodes into the air, beautifully illuminated by a beam of morning light from a side window. The background is a brick wall with some baking tools. The photograph captures the power of labor and the art of baking.

Dramatic sunrise over the Fitz Roy Massif, Patagonia. A storm is clearing, with heavy, gold-rimmed clouds rolling between the jagged peaks. The first rays of sun break through the clouds, precisely illuminating the main spire in a fiery orange-red alpenglow. Below, a glacial lake reflects the sky's dramatic colors, its surface perfectly calm and mirror-like.

The terraced rice paddies of Northern Vietnam at sunrise. Layers of gracefully curved terraces stretch from the valley floor to the hillsides. The golden sun, just cresting the ridge, illuminates the water-filled paddies, making them shine like thousands of shattered mirrors reflecting the colors of the sky. A thin layer of morning mist winds through the terraces like a ribbon, and in the distance, a few farmers in conical hats are working.

A cold winter night in the Lofoten Islands, Norway. A massive, brilliant green aurora borealis dances across the star-filled sky like a velvet curtain. The light from the aurora illuminates the snow-covered, jagged mountains and the frozen fjord below. A single red fisherman's cabin (rorbu) on the shore, with a warm light glowing in its window, adds a touch of human warmth to the immense, cold landscape.

A post-impressionist oil painting of a wheatfield at night, swaying under a turbulent wind, creating swirling vortexes. The moon and stars in the sky radiate exaggerated, spiraling light. The brushstrokes are thick, distorted, and full of energy, with heavy use of deep blues, yellows, and whites. The scene is filled with intense emotion and movement.

A Baroque-style portrait oil painting of an elderly scholar in his dimly lit study. A single, strong light source from the side illuminates his face and an open ancient book, while the background melts into deep shadow. His wrinkled face holds a contemplative expression. The painting is rich in detail and has a dramatic quality.

An impressionist oil painting of a summer afternoon in the Giverny garden. Sunlight filters through willow trees, casting shimmering dapples of light on a pond filled with water lilies. The brushstrokes are thick and rapid, colors are vibrant, focusing on the changing light reflected on the water's surface. A sense of peace and warmth.

A botanical illustration in watercolor. A hummingbird is hovering next to a blooming red hibiscus flower, drinking nectar. The painting has a clean, white background with ample negative space. The watercolor is bright and translucent, with visible bleeding and blending of colors on the paper (wet-on-wet technique). The linework is delicate and precise. The overall feeling is fresh, elegant, and full of life.

A Japanese ukiyo-e style woodblock print. A massive, monstrous wave with claw-like crests is crashing, threatening to engulf several small boats. In the distance, a snow-capped Mount Fuji stands serene. The image uses a limited color palette (predominantly Prussian blue) and features flat planes of color with strong, black outlines. The composition is highly dramatic and full of tension.

Related Models

stable-diffusion-3.5-medium

text-to-image

stable-diffusion-3

text-to-image

stable-diffusion-3.5-large

text-to-image

sdxl

text-to-image

stable-diffusion-3.5-large-turbo

text-to-image

stable-diffusion

text-to-image

README

SDXL LoRA

SDXL LoRA 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

Accessibility:This website uses AI models provided by third parties.

Sdxl Lora API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/sdxl-lora with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Sdxl Lora below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/stability-ai/sdxl-lora" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "negative_prompt": "blurry, low quality, distorted",
    "size": "1024*1024",
    "guidance_scale": 3.5,
    "num_inference_steps": 28,
    "seed": -1,
    "enable_base64_output": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("stability-ai/sdxl-lora", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "negative_prompt": "blurry, low quality, distorted",
        "size": "1024*1024",
        "guidance_scale": 3.5,
        "num_inference_steps": 28,
        "seed": -1,
        "enable_base64_output": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "stability-ai/sdxl-lora",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "negative_prompt": "blurry, low quality, distorted",
    "size": "1024*1024",
    "guidance_scale": 3.5,
    "num_inference_steps": 28,
    "seed": -1,
    "enable_base64_output": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Sdxl Lora API — Frequently asked questions

What is the Sdxl Lora API?

Sdxl Lora is a Stability AI model for AI inference, exposed as a REST API on WaveSpeedAI. Stability AI SDXL LoRA is a text-to-image model that generates high-quality images and supports LoRA for adaptation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Sdxl Lora API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-sdxl-lora.

How much does Sdxl Lora cost per run?

Sdxl Lora starts at $0.001 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Sdxl Lora accept?

Key inputs: `prompt`, `size`, `seed`, `guidance_scale`, `num_inference_steps`, `negative_prompt`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-sdxl-lora.

How long does Sdxl Lora take to generate?

Average end-to-end generation time on WaveSpeedAI is around 45 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Sdxl Lora outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Stability AI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.