Stability AI models - Amazon Bedrock
Supported models and image services

Stability AI models

This section describes the request parameters and response fields for Stability AI models. Use this information to make inference calls to Stability AI models with the InvokeModel operation. This section also includes Python code examples that shows how to call Stability AI models. To use a model in an inference operation, you need the model ID for the model. To get the model ID, see Supported foundation models in Amazon Bedrock. Some models also work with the Converse API. To check if the Converse API supports a specific Stability AI model, see Supported models and model features. For more code examples, see Code examples for Amazon Bedrock using AWS SDKs.

Foundation models in Amazon Bedrock support input and output modalities, which vary from model to model. To check the modalities that Stability AI models support, see Supported foundation models in Amazon Bedrock. To check which Amazon Bedrock features the Stability AI models support, see Supported foundation models in Amazon Bedrock. To check which AWS Regions that Stability AI models are available in, see Supported foundation models in Amazon Bedrock.

When you make inference calls with Stability AI models, you include a prompt for the model. For general information about creating prompts for the models that Amazon Bedrock supports, see Prompt engineering concepts. For Stability AI specific prompt information, see the Stability AI prompt engineering guide.

Supported models and image services

Amazon Bedrock supports the following Stability AI models and image services.

Note

Support for all other Stability AI models are in the process of being deprecated.

Model Use cases Example

Stable Image Ultra

  • Photorealistic, large-scale output

  • Ultra-realistic imagery for luxury brands and high-end campaigns

A luxury brand uses Stable Image Ultra to create stunning visuals of its latest collection for magazine spreads, ensuring a premium feel that matches its high standards.

Stable Diffusion 3.5 Large

  • High quality, high quantity creative assets

  • High volume outputs such as marketing campaigns and digital assets

A game development team uses SD3.5 Large to create detailed environmental textures and character concepts, accelerating their creative pipeline.

Stable Image Core

  • Fast and affordable

  • Rapid content generation at scale

An online retailer uses Stable Image Core to quickly generate product images for new arrivals, allowing it to list items faster and keep its catalog up-to-date.

Stability AI Image Services

  • Editing: in-painting, search and recolor, search and replace, erase object, and remove background

  • Control: sketch-to-image, control structure, style guide, and style transfer

A media company uses search and recolor, style transfer, and remove background to generate variations of images for an advertising campaign.
Topics