This is the most recent, optimised version of Stable Diffusion. It makes available Stable Diffusion 3.5, Stable Image Core, and Stable Image Ultra.
Stable Diffusion 3.5 (SD3.5) is our most capable text-to-image model yet, with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.
Creating quality, highly realistic images from text prompts, SD3 speeds up the design process and reduces cost by 50% or more.
Enable your organization to go from idea to execution faster! Accelerate your internal workflows for effortless scale by generating a variety of images that can be iterated on the fly. Unleash innovation and empower creativity to boost your business, decreasing time to market.
Our new Multimodal Diffusion Transformer (MMDiT) architecture uses separate sets of weights for image and language representations, which improves text understanding and spelling capabilities compared to previous versions of Stable Diffusion.
Highlights
The latest foundation model for images. SD3.5 introduces a new SOTA architecture for image generation, comprising an 8 billion parameter ensemble pipeline.
Unprecedented quality and ease of use: Native 1024x1024 image generation and higher, with cinematic photorealism and fine detail. The most advanced text generation within images.
Fine-tuned to create complex compositions with basic natural language prompting, thanks to the largest CLIP model in production.
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
You pay per output image generated by Stable Diffusion 3.5 Large. This is usage-based pricing, so charges scale with how many images you produce. There is no upfront commitment or fixed subscription. The listing lists the same output image unit across its dimensions, meaning cost grows directly with your generation volume. You are billed only for what you use. This model produces images at 1 megapixel resolution and supports a range of styles for professional use cases.
Top-of-mind questions for buyers
What counts as one billed output image for Stable Diffusion 3.5 Large?
One unit is a single output image the model generates at 1 megapixel resolution. Each image you produce is metered separately. The count grows directly with the number of images you generate, so producing more images raises your charge one image at a time.
Am I charged if I stop generating images or leave the model idle?
Charges apply only when the model produces an output image. If you generate nothing, no image charges accrue. There is no upfront commitment or fixed subscription, so an idle period adds nothing to your image usage cost. You pay only for images you actually generate.
Do image styles or subject matter change what I pay per image?
No. The model supports many styles, such as 3D, photography, painting, and line art, at 1 megapixel resolution. Style choice does not change the unit. Each output image is billed the same way regardless of the style or content you request.
stability.ai
Helpful?
Vendor refund policy
No refunds will be offered.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA).
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Knowledge Pilot is a conversational agent powered by Generative AI, utilizing AWS services such as Bedrock Generation Model, Titan Embedding Model, Elastic OpenSearch, EC2 and EKS that empowers knowledge workers to create a difference to drive impactful results.
Flatcar Container Linux is a lightweight operating system optimized for running containers. Designed for use in modern distributed infrastructure, Flatcar is automatically updated with the latest system software to reduce operational complexity associated with traditional OS management.
Be the first to review this product. We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.