Text-to-image

Generate an image from a text prompt.

Using SDXL 1.0

Use stable-diffusion-xl-1024-v1-0 as the engine_id of your request and pass in height & width as one of the following combinations:

1024x1024

1152x896

896x1152

1216x832

1344x768

768x1344

1536x640

640x1536.

Using SD 1.6

Pass in stable-diffusion-v1-6 as the engine_id of your request and ensure the height & width you pass in adhere to the following restrictions:

No dimension can be less than 320 pixels

No dimension can be greater than 1536 pixels

Using SD Beta

Pass in stable-diffusion-xl-beta-v2-2-2 as the engine_id of your request and ensure the height & width you pass in adhere to the following restrictions:

dimensions must be between 128x128 and 512x896 (or 896x512)

only one dimension can be greater than 512, but not both

NOTE: Only Version 1 engines will work with this endpoint.

请求参数

Path 参数

engine_id

string

必需

示例值:

stable-diffusion-v1-6

Query 参数

string

可选

Header 参数

enum<string>

可选

The format of the response. Leave blank for JSON, or set to 'image/png' for a PNG image.

枚举值:

application/jsonimage/png

默认值:

application/json

Organization

string

可选

Allows for requests to be scoped to an organization other than the user's default. If not provided, the user's default organization will be used.

示例值:

org-123456

Stability-Client-ID

string

可选

Used to identify the source of requests, such as the client application or sub-organization. Optional, but recommended for organizational clarity.

示例值:

my-great-plugin

Stability-Client-Version

string

可选

Used to identify the version of the application or service making the requests. Optional, but recommended for organizational clarity.

示例值:

1.2.1

string

可选

Body 参数application/json

Represents the optional parameters that can be passed to any generation request.

height

integer

DiffuseImageHeight

可选

Height of the image to generate, in pixels, in an increment divisible by 64.

>= 128

默认值:

512

示例值:

512

倍数:

width

integer

DiffuseImageWidth

可选

Width of the image to generate, in pixels, in an increment divisible by 64.

>= 128

默认值:

512

示例值:

512

倍数:

text_prompts

array[object (TextPrompt) {2}]

TextPrompts

必需

An array of text prompts to use for generation.

Given a text prompt with the text A lighthouse on a cliff and a weight of 0.5, it would be represented as:

"text_prompts": [
  {
    "text": "A lighthouse on a cliff",
    "weight": 0.5
  }
]

>= 1 items

text

string

必需

The prompt itself

<= 2000 字符

示例值:

A lighthouse on a cliff

weight

number <float>

可选

Weight of the prompt (use negative numbers for negative prompts)

示例值:

0.8167237

cfg_scale

number

CfgScale

可选

How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)

>= 0<= 35

默认值:

示例值:

clip_guidance_preset

enum<string>

ClipGuidancePreset

可选

枚举值:

FAST_BLUEFAST_GREENNONESIMPLESLOWSLOWERSLOWEST

默认值:

NONE

示例值:

FAST_BLUE

sampler

enum<string>

Sampler

可选

Which sampler to use for the diffusion process. If this value is omitted we'll automatically select an appropriate sampler for you.

枚举值:

DDIMDDPMK_DPMPP_2MK_DPMPP_2S_ANCESTRALK_DPM_2K_DPM_2_ANCESTRALK_EULERK_EULER_ANCESTRALK_HEUNK_LMS

示例值:

K_DPM_2_ANCESTRAL

samples

integer

Samples

可选

Number of images to generate

>= 1<= 10

默认值:

示例值:

seed

integer

Seed

可选

Random noise seed (omit this option or use 0 for a random seed)

>= 0<= 4294967295

默认值:

示例值:

steps

integer

Steps

可选

Number of diffusion steps to run.

>= 10<= 50

默认值:

示例值:

style_preset

enum<string>

StylePreset

可选

Pass in a style preset to guide the image model towards a particular style.
This list of style presets is subject to change.

枚举值:

3d-modelanalog-filmanimecinematiccomic-bookdigital-artenhancefantasy-artisometricline-artlow-polymodeling-compoundneon-punkorigamiphotographicpixel-arttile-texture

extras

object

Extras

可选

Extra parameters passed to the engine.
These parameters are used for in-development or experimental features and may change
without warning, so please use with caution.

示例

{
  "cfg_scale": 7,
  "height": 512,
  "width": 512,
  "sampler": "K_DPM_2_ANCESTRAL",
  "samples": 1,
  "steps": 30,
  "text_prompts": [
    {
      "text": "A lighthouse on a cliff",
      "weight": 1
    }
  ]
}

示例代码

Python

JavaScript

Shell

Java

Swift

PHP

HTTP

Objective-C

Ruby

OCaml

Dart

返回响应

🟢200Generation successful.

application/json

Body

An array of results from the generation request, where each image is a base64 encoded PNG.

artifacts

array[object (Image) {3}]

可选

base64

string

可选

Image encoded in base64

finishReason

enum<string>

可选

枚举值:

CONTENT_FILTEREDERRORSUCCESS

示例值:

CONTENT_FILTERED

seed

number

可选

The seed associated with this image

示例值:

1229191277

示例

{
  "artifacts": [
    [
      {
        "base64": "...very long string...",
        "finishReason": "SUCCESS",
        "seed": 1050625087
      },
      {
        "base64": "...very long string...",
        "finishReason": "CONTENT_FILTERED",
        "seed": 1229191277
      }
    ]
  ]
}

🟠400bad_request: one or more parameters were invalid.

🟠401unauthorized: API key missing or invalid

🟠403permission_denied: You lack the necessary permissions to perform this action

🟠404not_found: The requested resource/engine was not found

🔴500server_error: Some unexpected server error occurred

Using SDXL 1.0#

Using SD 1.6#

Using SD Beta#

请求参数

示例代码

返回响应

Using SDXL 1.0

Using SD 1.6

Using SD Beta