Stable Diffusion 3

POST

/sd/v2beta/stable-image/generate/sd3

Generate

Generate an image using a Stable Diffusion 3 model:

SD3 Medium - the 2 billion parameter model

SD3 Large - the 8 billion parameter model

SD3 Large Turbo - the 8 billion parameter model with a faster inference time

This API is powered by Fireworks AI.
API status can be reviewed here.

Try it out

Grab your API key and head over to one of the following sites:

How to use

Please invoke this endpoint with a POST request.

The headers of the request must include an API key in the authorization field. The body of the request must be
multipart/form-data. The accept header should be set to one of the following:

image/* to receive the image in the format specified by the output_format parameter.

application/json to receive the image encoded as base64 in a JSON response.

Generating with a prompt

Commonly referred to as text-to-image, this mode generates an image from text alone. While the only required
parameter is the prompt, it also supports an aspect_ratio parameter which can be used to control the
aspect ratio of the generated image.

**Generating with a prompt and an image**

Commonly referred to as image-to-image, this mode also generates an image from text but uses an existing image as the
starting point. The required parameters are:

prompt - text to generate the image from

image - the image to use as the starting point for the generation

strength - controls how much influence the image parameter has on the output image

mode - must be set to image-to-image

Note: maximum request size is 10MiB.

Optional Parameters:

Both modes support the following optional parameters:

model - the model to use (SD3 Medium, SD3 Large, or SD3 Large Turbo)

output_format - the the format of the output image

seed - the randomness seed to use for the generation

negative_prompt - keywords of what you do not wish to see in the output image

Note: for more details about these parameters please see the request schema below.

Output

The resolution of the generated image will be 1MP. The default resolution is 1024x1024.

Credits

SD3 Medium: Flat rate of 3.5 credits per successful generation.

SD3 Large: Flat rate of 6.5 credits per successful generation.

SD3 Large Turbo: Flat rate of 4 credits per successful generation.

As always, you will not be charged for failed generations.

请求参数

Header 参数

authorization

string

必需

Your Stability API key, used to authenticate your requests. Although you may have multiple keys in your account, you should use the same key for all requests to this API.

>= 1 字符

content-type

string

必需

The content type of the request body. Do not manually specify this header; your HTTP client library will automatically include the appropriate boundary parameter.

>= 1 字符

示例值:

multipart/form-data

enum<string>

必需

Specify image/* to get the image bytes directly. Otherwise specify application/json to receive the image as base64 encoded JSON.

枚举值:

application/jsonimage/*

默认值:

image/*

Body 参数multipart/form-data

prompt

string

必需

What you wish to see in the output image. A strong, descriptive prompt that clearly defines
elements, colors, and subjects will lead to better results.

>= 1 字符<= 10000 字符

mode

enum<string>

GenerationMode

可选

Controls whether this is a text-to-image or image-to-image generation, which affects which parameters are required:

text-to-image requires only the prompt parameter

image-to-image requires the prompt, image, and strength parameters

枚举值:

image-to-imagetext-to-image

默认值:

text-to-image

示例值:

text-to-image

image

file

可选

The image to use as the starting point for the generation.

Supported formats:

jpeg

png

webp

Supported dimensions:

Every side must be at least 64 pixels

Important: This parameter is only valid for image-to-image requests.

strength

number

可选

Sometimes referred to as denoising, this parameter controls how much influence the
image parameter has on the generated image. A value of 0 would yield an image that
is identical to the input. A value of 1 would be as if you passed in no image at all.

Important: This parameter is only valid for image-to-image requests.

>= 0<= 1

aspect_ratio

enum<string>

可选

Controls the aspect ratio of the generated image. Defaults to 1:1.

Important: This parameter is only valid for text-to-image requests.

枚举值:

16:91:121:92:33:24:55:49:169:21

默认值:

1:1

示例值:

1:1

model

enum<string>

可选

The model to use for generation.

sd3-medium requires 3.5 credits per generation

sd3-large requires 6.5 credits per generation

sd3-large-turbo requires 4 credits per generation

枚举值:

sd3-largesd3-large-turbosd3-medium

默认值:

sd3-large

示例值:

sd3-large

seed

number

可选

A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass 0 to use a random seed.)

>= 0<= 4294967294

默认值:

output_format

enum<string>

可选

Dictates the content-type of the generated image.

枚举值:

jpegpng

默认值:

png

示例值:

png

negative_prompt

string

可选

Keywords of what you do not wish to see in the output image.
This is an advanced feature.

Important: This parameter does not work with sd3-large-turbo.

<= 10000 字符

示例代码

Python

JavaScript

Shell

Java

Swift

PHP

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/sd/v2beta/stable-image/generate/sd3' \
--header 'authorization;' \
--header 'accept;' \
--form 'prompt=""' \
--form 'mode="text-to-image"' \
--form 'image=@""' \
--form 'strength=""' \
--form 'aspect_ratio="1:1"' \
--form 'model="sd3-large"' \
--form 'seed=""' \
--form 'output_format="png"' \
--form 'negative_prompt=""'

返回响应

🟢200Generation was successful.

application/json

Body

object {0}

示例

{}

🟠400Invalid parameter(s), see the `errors` field for details.

🟠403Your request was flagged by our content moderation system.

🟠413Your request was larger than 10MiB.

🟠422You made a request with an unsupported language.

🟠429You have made more than 150 requests in 10 seconds.

🔴500An internal error occurred. If the problem persists [contact support](https://stabilityplatform.freshdesk.com/support/tickets/new).

Stable Image Core

Text-to-image

Stable Diffusion 3

Try it out#

How to use#

Generating with a prompt#

Generating with a prompt and an image#

Optional Parameters:#

Output#

Credits#

请求参数

示例代码

返回响应

Try it out

How to use

Generating with a prompt

**Generating with a prompt and an image**

Optional Parameters:

Output

Credits