Stability AI in Amazon Bedrock

Build with the most advanced text-to-image models from Stability AI

Introducing Stability AI’s latest text-to-image models

Stable Diffusion 3.5 Large, Stability AI’s most advanced text-to-image model is now available in Amazon Bedrock, providing high-speed, scalable, AI-powered visual content creation capabilities.

This new model generates high-quality images from text descriptions in a wide range of styles to accelerate the creation of concept art, visual effects, and detailed product imagery for customers in media, gaming, advertising, and retail.

Stable Image Ultra, powered by Stability AI’s most advanced models, including Stable Diffusion 3.5, sets a new standard in image generation. It excels in typography, intricate compositions, dynamic lighting, vibrant colors, and artistic cohesion.

Using an enhanced version of SDXL, Stable Image Core delivers exceptional speed and efficiency while maintaining the high-quality output synonymous with Stable Diffusion models—all at half the price of SDXL.

Meet Stability AI

Stability AI is a world-leading open source generative AI company delivering breakthrough AI models with minimal resource requirements in imaging, language, code, and audio.

Model features

Style variety

Stable Diffusion 3.5 Large is able to render images across a wide range of style varieties like 3D, photography, painting, and line art, making it adaptable to your specific creative needs.  

These four images were made with SD3.5 Large using prompts that include style variety descriptors like hand-drawn illustration, vibrant colors, halftone, collage art, detailed photorealism, and more.

Style variety

Photorealism

Stable Image Ultra delivers images with exceptional detail, color, and lighting, enabling photorealistic outputs as well as high-quality outputs in flexible styles.

This image was generated using Stable Image Ultra with the prompt: An ornate, Victorian-era key lying on a weathered, wooden surface, with intricate, steampunk-inspired gears and mechanisms visible within its transparent, glass shaft.

Photorealism

Prompt understanding

Stability AI models are able to comprehend long and complex prompts involving spatial reasoning, compositional elements, actions, and styles.

This image was generated using Stable Diffusion 3.5 Large with the prompt: photo of three potions: the first potion is blue with the label "MANA", the second potion is red with the label "HEALTH", the third potion is green with the label "POISON". Old apothecary.

Prompt understanding

Typography

Stable Diffusion 3.5 Large achieves unprecedented text quality with fewer errors in spelling, kerning, letter forming, and spacing. Here, SD3.5 Large is able to accurately generate specific text, objects, and lighting conditions.

This image was generated using SD3.5 Large with the prompt: Aesthetic cute cartoon 3D render, a delicious cup of coffee in a mug that reads, "Good Morning, Sunshine.”

Typography

Product rendering

Stability AI’s models can be used to generate high-quality concept art and product renderings or create visually stunning images for billboards and print ads.

This image was generated using SD3 Large with the prompt: professional 3d render of a white and teal sneaker, floating in center, hovering, floating, high quality, photorealistic.
 

Product rendering

Benefits

SOTA open architecture for image generation with 3.5B parameter base model stage and 6.6B parameter ensemble pipeline.
Native 1024 x 1024 image generation with cinematic photorealism and fine detail.
Fine-tuned to create complex compositions with basic natural language prompting.