The Stability AI Stable Image Generate API provides text-to-image generation capabilities powered by models including Stable Diffusion 3.5 and Stable Image Ultra. Developers can generate high-quality images from text prompts with control over style, dimensions, and output format. The API supports multiple model tiers including Stable Image Core for fast and affordable generation and Stable Image Ultra for state-of-the-art quality results.
openapi: 3.1.0
info:
title: Stability AI Stable Image Generate API
description: >-
The Stability AI Stable Image Generate API provides text-to-image generation
capabilities powered by models including Stable Diffusion 3.5 and Stable Image
Ultra. Developers can generate high-quality images from text prompts with
control over style, dimensions, and output format. The API supports multiple
model tiers including Stable Image Core for fast and affordable generation and
Stable Image Ultra for state-of-the-art quality results.
version: 'v2beta'
contact:
name: Stability AI Support
url: https://platform.stability.ai
termsOfService: https://stability.ai/terms-of-service
externalDocs:
description: Stability AI API Documentation
url: https://platform.stability.ai/docs/api-reference
servers:
- url: https://api.stability.ai
description: Production Server
tags:
- name: Generate Core
description: >-
Generate images using Stable Image Core, a fast and affordable model for
high-quality image generation.
- name: Generate SD3
description: >-
Generate images using Stable Diffusion 3 and 3.5 models with advanced
text-to-image and image-to-image capabilities.
- name: Generate Ultra
description: >-
Generate images using Stable Image Ultra, the highest quality model for
state-of-the-art photorealistic and artistic image generation.
security:
- bearerAuth: []
paths:
/v2beta/stable-image/generate/ultra:
post:
operationId: generateImageUltra
summary: Generate an image using Stable Image Ultra
description: >-
Generates a high-quality image from a text prompt using the Stable Image
Ultra model. This endpoint produces state-of-the-art results with
exceptional detail, lighting, and composition. Requests use multipart
form data encoding.
tags:
- Generate Ultra
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/GenerateUltraRequest'
responses:
'200':
description: Successfully generated image
content:
image/jpeg:
schema:
type: string
format: binary
image/png:
schema:
type: string
format: binary
image/webp:
schema:
type: string
format: binary
application/json:
schema:
$ref: '#/components/schemas/GenerateImageResponse'
'400':
description: Bad request due to invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
description: Unauthorized due to missing or invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'403':
description: >-
Forbidden due to content moderation or insufficient permissions
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
/v2beta/stable-image/generate/core:
post:
operationId: generateImageCore
summary: Generate an image using Stable Image Core
description: >-
Generates an image from a text prompt using the Stable Image Core model.
This endpoint provides fast and affordable generation with high-quality
results suitable for most use cases. Requests use multipart form data
encoding.
tags:
- Generate Core
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/GenerateCoreRequest'
responses:
'200':
description: Successfully generated image
content:
image/jpeg:
schema:
type: string
format: binary
image/png:
schema:
type: string
format: binary
image/webp:
schema:
type: string
format: binary
application/json:
schema:
$ref: '#/components/schemas/GenerateImageResponse'
'400':
description: Bad request due to invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
description: Unauthorized due to missing or invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'403':
description: >-
Forbidden due to content moderation or insufficient permissions
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
/v2beta/stable-image/generate/sd3:
post:
operationId: generateImageSD3
summary: Generate an image using Stable Diffusion 3
description: >-
Generates an image using Stable Diffusion 3 or 3.5 models. Supports both
text-to-image and image-to-image generation modes. When an image is
provided along with a prompt, the model uses it as a reference guided by
the strength parameter. Requests use multipart form data encoding.
tags:
- Generate SD3
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/GenerateSD3Request'
responses:
'200':
description: Successfully generated image
content:
image/jpeg:
schema:
type: string
format: binary
image/png:
schema:
type: string
format: binary
image/webp:
schema:
type: string
format: binary
application/json:
schema:
$ref: '#/components/schemas/GenerateImageResponse'
'400':
description: Bad request due to invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
description: Unauthorized due to missing or invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'403':
description: >-
Forbidden due to content moderation or insufficient permissions
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
API key authentication. Pass your Stability AI API key as a Bearer token
in the Authorization header.
schemas:
GenerateUltraRequest:
type: object
required:
- prompt
properties:
prompt:
type: string
maxLength: 10000
description: >-
Text describing what you wish to see in the output image. Strong,
descriptive prompts that clearly define elements, colors, and subjects
lead to better results.
negative_prompt:
type: string
maxLength: 10000
description: >-
Text describing elements to exclude from the output image.
aspect_ratio:
type: string
enum:
- '16:9'
- '1:1'
- '21:9'
- '2:3'
- '3:2'
- '4:5'
- '5:4'
- '9:16'
- '9:21'
default: '1:1'
description: >-
Controls the aspect ratio of the generated image.
seed:
type: integer
minimum: 0
maximum: 4294967294
default: 0
description: >-
A value to control randomness in generation. Set to 0 for a random
seed. Using the same seed with the same parameters produces similar
results.
output_format:
type: string
enum:
- jpeg
- png
- webp
default: png
description: >-
The output format of the generated image.
GenerateCoreRequest:
type: object
required:
- prompt
properties:
prompt:
type: string
maxLength: 10000
description: >-
Text describing what you wish to see in the output image.
negative_prompt:
type: string
maxLength: 10000
description: >-
Text describing elements to exclude from the output image.
aspect_ratio:
type: string
enum:
- '16:9'
- '1:1'
- '21:9'
- '2:3'
- '3:2'
- '4:5'
- '5:4'
- '9:16'
- '9:21'
default: '1:1'
description: >-
Controls the aspect ratio of the generated image.
seed:
type: integer
minimum: 0
maximum: 4294967294
default: 0
description: >-
A value to control randomness in generation.
output_format:
type: string
enum:
- jpeg
- png
- webp
default: png
description: >-
The output format of the generated image.
style_preset:
type: string
description: >-
An optional style preset to guide the image model towards a
particular visual style.
GenerateSD3Request:
type: object
required:
- prompt
properties:
prompt:
type: string
maxLength: 10000
description: >-
Text describing what you wish to see in the output image.
negative_prompt:
type: string
maxLength: 10000
description: >-
Text describing elements to exclude from the output image.
image:
type: string
format: binary
description: >-
An optional input image for image-to-image generation. When provided,
the model uses this image as a reference guided by the strength
parameter.
strength:
type: number
minimum: 0
maximum: 1
default: 0.7
description: >-
Controls how much influence the input image has on the output.
Lower values produce images closer to the input, higher values allow
more creative deviation. Only applicable for image-to-image mode.
aspect_ratio:
type: string
enum:
- '16:9'
- '1:1'
- '21:9'
- '2:3'
- '3:2'
- '4:5'
- '5:4'
- '9:16'
- '9:21'
default: '1:1'
description: >-
Controls the aspect ratio of the generated image. Only applicable
for text-to-image mode.
model:
type: string
enum:
- sd3
- sd3-turbo
- sd3.5-large
- sd3.5-large-turbo
- sd3.5-medium
default: sd3.5-large
description: >-
The Stable Diffusion 3 model variant to use for generation.
seed:
type: integer
minimum: 0
maximum: 4294967294
default: 0
description: >-
A value to control randomness in generation.
output_format:
type: string
enum:
- jpeg
- png
- webp
default: png
description: >-
The output format of the generated image.
mode:
type: string
enum:
- text-to-image
- image-to-image
default: text-to-image
description: >-
The generation mode. Use text-to-image for prompt-only generation
or image-to-image when providing a reference image.
GenerateImageResponse:
type: object
properties:
image:
type: string
description: >-
Base64-encoded image data when Accept header is set to
application/json.
finish_reason:
type: string
enum:
- SUCCESS
- CONTENT_FILTERED
description: >-
The reason the generation finished. SUCCESS indicates a successful
generation, CONTENT_FILTERED indicates the output was blocked by
content moderation.
seed:
type: integer
description: >-
The seed used for generation. Useful for reproducing results.
ErrorResponse:
type: object
properties:
id:
type: string
description: >-
A unique identifier for the error instance.
name:
type: string
description: >-
The error type name.
message:
type: string
description: >-
A human-readable description of the error.