Stability Ai Sdxl
Playground
Try it on WavespeedAI!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.
Features
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:
-1for random, or set any integer for reproducible results.
How to Use
A) Text-to-Image
- Enter a prompt with subject + context + style + lighting + camera.
- Set width/height for your target aspect ratio (e.g., 1536×1536 for square).
- (Optional) Set seed for repeatability.
- Run and iterate on wording or seed.
B) Image-to-Image
- Upload an image.
- Write a prompt describing the desired change or style.
- (Optional) Set seed for repeatability.
- 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.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/stability-ai/sdxl" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"size": "1024*1024",
"seed": -1,
"enable_base64_output": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | No | - | The image to generate an image from. | |
| size | string | No | 1024*1024 | 256 ~ 1536 per dimension | The size of the generated media in pixels (width*height). |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
| enable_base64_output | boolean | No | false | - | If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |