Skip to content

Stability AI

Reference


Activating humanity’s potential through generative AI. Open models in every modality, for everyone, everywhere.

Categories: [artificial-intelligence]

Version: 1


Connections

Version: 1

Bearer Token

Properties

NameTypeControl TypeDescription
API KeySTRINGTEXT

Actions

Create image

Create an image using text-to-image models

Properties

NameTypeControl TypeDescription
ModelSTRINGTEXTThe model to use for image generation.
Messages[{STRING(content), NUMBER(weight)}]ARRAY_BUILDERA list of messages comprising the conversation so far.
HeightINTEGERINTEGERHeight of the image to generate, in pixels, in an increment divisible by 64. Engine-specific dimension validation applies.
WidthINTEGERINTEGERWidth of the image to generate, in pixels, in an increment divisible by 64. Engine-specific dimension validation applies.
Number of responsesINTEGERINTEGERThe number of images to be generated. Must be between 1 and 10.
Response formatSTRINGSELECTThe format in which the generated images are returned.
StyleSTRINGSELECTPass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change.
StepsINTEGERINTEGERNumber of diffusion steps to run. Valid range: 10 to 50.
CFG scaleNUMBERNUMBERThe strictness level of the diffusion process adherence to the prompt text. Range: 0 to 35.
Clip guidance presetSTRINGTEXTPass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change.
SamplerSTRINGTEXTWhich sampler to use for the diffusion process. If this value is omitted, an appropriate sampler will be automatically selected.
SeedNUMBERNUMBERRandom noise seed (omit this option or use 0 for a random seed). Valid range: 0 to 4294967295.

Output

Type: OBJECT

Properties

TypeControl Type
INTEGERINTEGER
[{STRING(url), STRING(b64Json), STRING(revisedPrompt)}]ARRAY_BUILDER