Stability.ai

1. Overview

Stability.ai is a company focused on developing AI models. The company's flagship model is Stable Diffusion, which is an image generation model based on deep learning. It has garnered a lot of attention for its ability to generate high-quality images from text descriptions.

Note

The model in this series does not support Chinese very well. Try to use English for natural language descriptions.

Available model list:

• sd-ultra

• sd3-large

• sd3.5-large

• sd3-large-turbo

• sd3.5-large-turbo

• sd3-medium

• sd3.5-medium

• sd-core

2. Request Description

• Request method: POST

• Request address: https://gateway.theturbo.ai/v1/images/generations

3. Input Parameters

3.1 Header Parameters

Parameter Name	Type	Required	Description	Example Value
Content-Type	string	Yes	Set the request header type, which must be multipart/form-data	multipart/form-data; boundary=------------------------y0QNRDhXQUE3yHQi7DEbLz
Accept	string	Yes	Set the response type, which must be image/*	image/*
Authorization	string	Yes	API_KEY required for authentication. Format: Bearer $YOUR_API_KEY	Bearer $YOUR_API_KEY

3.2 Body Parameters (multipart/form-data)

Parameter Name	Type	Required	Description	Example (Default Value)
model	string	Yes	Model ID to use. See available models listed in the Overview for details, such as sd3-large.	sd3-large
prompt	string	Yes	A text describing the required image. The maximum description length is 10,000 characters.	A cute baby sea otter
mode	string	No	Confirm whether is text-to-image or image-to-image. text-to-image requires only prompt; image-to-image requires prompt, image and strength. sd-core does not support image-to-image.	text-to-image
image	string (binary)	No	An image used as the starting point for generation. Only available for image-to-image. Supported formats: JPEG, PNG, WEBP. Supported dimensions: Each side must be at least 64 pixels.
strength	number [0,1]	No	Sometimes referred to as denoising, this parameter controls the influence of the image parameters on the generated output. A value of 0 produces an output identical to the input image, while a value of 1 generates an image as if no input image was provided.	0.9
negative_prompt	string	No	Keywords for content you want to exclude from the output image. sd3-large-turbo does not support this parameter.	a cat
seed	number [0,4294967294]	No	A specific value used to guide the randomness of generation. ( If this parameter is omitted or set to 0, a random seed will be used.)	0
aspect_ratio	string	No	Controls the aspect ratio of the generated image. Support 16:9, 1:1, 21:9, 2:3, 3:2, 4:5, 5:4, 9:16, and 9:21.	1:1
output_format	string	No	jpegorpng。	png
style_preset	string	No	Guides the image model toward a specific style. Support 3d-model, analog-film, anime, cinematic, comic-book, digital-art, enhance, fantasy-art, isometric, line-art, low-poly, modeling-compound, neon-punk, origami, photographic, pixel-art, and tile-texture. Only sd-core support this parameter.

4. Request Example

text-to-image

curl https://gateway.theturbo.ai/v1/images/generations \
	-H "Accept: image/*" \
	-H "Authorization: Bearer $YOUR_API_KEY" \
	-F model="sd3-large" \
	-F prompt="A cute baby sea otter wearing a beret"

image-to-image

curl https://gateway.theturbo.ai/v1/images/generations \
	-H "Accept: image/*" \
	-H "Authorization: Bearer $YOUR_API_KEY" \
	-F model="sd3-large" \
	-F prompt="A cute baby sea otter wearing a beret" \
	-F mode="image-to-image" \
	-F image="@input.png" \
	-F strength=0.9 \

5. Response Example

HTTP/1.1 200 OK
Content-Type: image/png

Image binary file