Appearance

Stable Diffusion XL

POST/v1/run

Fast Sdxl Inpainting by Stability AI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to stability-ai/fast-sdxl/inpainting.

Default: stability-ai/fast-sdxl/inpainting

stringpromptrequired

The prompt to use for generating the image. Be as descriptive as possible for best results.

stringimagerequired

The URL of the image to use as a starting point for the generation.

Optional<string>mask

The URL of the mask to use for inpainting.

Optional<number>guidance_scale

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

Range: 0 to 20

Default: 7.5

Optional<integer>num_inference_steps

The number of inference steps to perform.

Range: 1 to 65

Default: 25

Optional<number>strength

determines how much the generated image resembles the initial image

Range: 0.01 to 1

Default: 0.95

Optional<boolean>expand_prompt

If set to true, the prompt will be expanded with additional prompts.

Default: false

Optional<array<object>>loras

The list of LoRA weights to use.

Default:

Optional<string>request_id

An id bound to a request, can be used with response to identify the request itself.

Default:

Optional<string>format

The format of the generated image.

Allowed values: jpeg, png

Default: jpeg

Optional<array<object>>embeddings

The list of embeddings to use.

Default:

Optional<string>safety_checker_version

The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.

Allowed values: v1, v2

Default: v1

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16

Optional<integer>seed

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

Default: null

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async