Sold by: Stability AI
Deployed on AWS
The official foundation model for image generation from Stability. Deploy this optimized instance and serve generative AI within minutes.
Overview
SDXL is the largest open source image model from Stability AI, designed for creative professionals who want to make the highest quality images without sacrificing on performance.
SDXL produces high resolution images with unprecedented control of color and contrast. Calibrated for photorealism and other styles ready for marketing, design, and other commercial use cases, SDXL is perfect for creating and editing works of art.
Highlights
- The foundation model for images: All text to image, image to image, inpainting, and outpainting workflows are handled by the official SDXL model. SDXL introduces a new SOTA architecture for image generation, comprising a 3.5B parameter base model stage and a 6.6B parameter ensemble pipeline.
- Unprecedented quality and ease of use: Native 1024x1024 image generation 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.
- Professional: Compared to previous versions, SDXL 1.0 generates more vibrant and accurate colors, with better contrast, lighting, and shadows. All aspect ratios at high resolution are native.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
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.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Vendor refund policy
n/a
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.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
New in SDXL 1.0 from 0.9
- TBD: 2-stage process can be split so that only a single stage is used
- Less reliance on refiner stage: First stage (generation) is more capable of creating high quality images
- Image quality improvements:
- More accurate color generation
- Higher contrast
- Deeper black levels, more vibrant hues, brighter shades of white
Additional details
Inputs
- Summary
This model accepts JSON input aligned with the Stability REST API as well as protocol buffers aligned with the Stability GRPC API .
- Limitations for input type
- Input images must be base64 encoded in JSON or supplied via protobuf.
- Input MIME type
- application/json, application/x-protobuf
{
"cfg_scale": 7,
"height": 1024,
"width": 1024,
"steps": 50,
"seed": 42,
"sampler": "K_DPMPP_2M",
"text_prompts": [
{
"text": "A photograph of fresh pizza with basil and tomatoes, from a traditional oven",
"weight": 1
}]
}
https://platform.stability.ai
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
height | The height of the image in pixels. Must be a multiple of 64.
On p4d/p4de instances, resolutions values are unlocked and only limited by GPU memory.
On g5 instances, optimized native resolutions are limited to:
1024x1024
1152x896 / 896x1152
1216x832 / 832x1216
1344x768 / 768x1344
1536x640 / 640x1536
Lower resolutions than native will be cropped. Higher resolutions will result in an error. | Default value: 1024
Type: Integer | No |
width | The width of the image in pixels. Must be a multiple of 64.
On p4d/p4de instances, resolutions values are unlocked and only limited by GPU memory.
On g5 instances, optimized native resolutions are limited to:
1024x1024
1152x896 / 896x1152
1216x832 / 832x1216
1344x768 / 768x1344
1536x640 / 640x1536
Lower resolutions than native will be cropped. Higher resolutions will result in an error. | Default value: 1024
Type: Integer | No |
text_prompts | An array of text prompts to use for generation.
Given a text prompt with the text A lighthouse on a cliff and a weight of 0.5, it would be represented as:
"text_prompts": [
{
"text": "A lighthouse on a cliff",
"weight": 0.5
}
] | Type: FreeText
Limitations: Structured JSON array of prompts. | Yes |
cfg_scale | How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt) | Default value: 7.0
Type: Continuous
Minimum: 0
Maximum: 35 | No |
sampler | Which sampler to use for the diffusion process. | Default value: K_DPMPP_2M for text-to-image, K_DPM_2_ANCESTRAL for image to image
Type: Categorical
Allowed values: DDIM,DDPM,K_DPMPP_SDE,K_DPMPP_2M,K_DPMPP_2S_ANCESTRAL,K_DPM_2,K_DPM_2_ANCESTRAL,K_EULER,K_EULER_ANCESTRAL,K_HEUN,K_LMS | No |
seed | Random noise seed (omit this option or use 0 for a random seed) | Default value: 0
Type: Integer | No |
style_preset | Pass in a style preset to guide the image model towards a particular style. This list of style presets is subject to change. | Default value: none
Type: Categorical
Allowed values: enhance,anime,photographic,digital-art,comic-book,fantasy-art,line-art,analog-film,neon-punk,isometric,low-poly,origami,modeling-compound,cinematic,3d-model,pixel-art,tile-texture | No |
steps | Number of diffusion steps to run. | Default value: 30
Type: Integer
Minimum: 10
Maximum: 150 | No |
Resources
Vendor resources
Support
AWS infrastructure support
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.
Similar products
Avahi’s offering for image applications will demonstrate how to generate new images from text, and transform existing images with text instructions - using Stable Diffusion XL on Amazon Bedrock and AWS Sagemaker. Stable Diffusion XL generates images of high quality in virtually any art style and is the best open model for photorealism.
This product has charges associated with it for seller support.
Incredibly high quality text-to-image generation services, leveraging the latest Stable Diffusion models from Stability AI.
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.
Flatcar Container Linux Pro is an AWS-optimized edition of Flatcar Container Linux, a minimal, secure Linux distribution for Docker and Kubernetes apps. It is ideal for production container environments wanting the backing of a global open source community.
ComfyUI is a highly flexible, powerful, and user-friendly node-based interface for Stable Diffusion that enables advanced AI image generation workflows with ease.
Customer reviews
0 ratings
0 AWS reviews
|
10 external reviews
Star ratings include only reviews from verified AWS customers. External reviews can also include a star rating, but star ratings from external reviews are not averaged in with the AWS customer star ratings.
Consulting
Stable diffusion review
Reviewed on Jun 12, 2024
Review provided by G2
What do you like best about the product?
We can create photos for our projects, goods, or services without being concerned about any legal fallout.
What do you dislike about the product?
Pricing can have segmentation for user groups
What problems is the product solving and how is that benefiting you?
It provides better accuracy in terms of generating images and it saves time since we don't have to worry about verifying its legality
Anant K.
The Best advanced image model out there
Reviewed on May 20, 2024
Review provided by G2
What do you like best about the product?
I recently used Stable Diffusion 3. I found the text to image capabilities to be absolutely top class. The level of spelling abilities and image quality is just remarkable
What do you dislike about the product?
When it comes to Stable Music, I think the platform has some distance to go. The functionality is a bit weak and offers a lot of room for improvement
What problems is the product solving and how is that benefiting you?
I think it reduces workload for organizations looking to streamline human intensive tasts. It can be very cost efficient if this technology is deployed at scale
Sumit P.
Better way to transform personal ideas into reality
Reviewed on Apr 27, 2024
Review provided by G2
What do you like best about the product?
I'm studying it to use at my wife's company (swags, t-shirts, DTF, sublimations, all sorts of personalized products) to create some unique images. After two weeks of putting so many hours into it, I finally managed to consistently get the results I was looking for. The next steps is to develop a workflow to generate a few collections. I might have something in two or three weeks.
One thing I would love to do is create a simpler front-end to SD where my customer could type prompts and select the images to order products :)
One thing I would love to do is create a simpler front-end to SD where my customer could type prompts and select the images to order products :)
What do you dislike about the product?
Developing a workflow to generate collections could be time-consuming and complex, requiring careful planning and coordination between different stages of the design process.
What problems is the product solving and how is that benefiting you?
Graphic design and logo designing
Rahul S.
Great AI model for generating high quality images from prompts and images.
Reviewed on Apr 16, 2024
Review provided by G2
What do you like best about the product?
Stable Diffusion is the best AI model which helps us generate very high quality images for our websites. It generates images from both our prompts as well as our images. They offers the cheapest price for their image generating credits. It also offers alots of images styles and sizes for generating our required images for our websites and social medias.
What do you dislike about the product?
It is not yet the most capable Image generating AI model as it lacks in generating complex images.
What problems is the product solving and how is that benefiting you?
Stable Diffusion has multiple AI models which provides us with high demanding image generating features like Negative prompting, style selection, aspect ratio and seeding, which helped us generate our images with precise styling and aspect ratio for our blog page and social media posts. It supports generating images from both prompts as well as images, which helped us replace our old images on our blogs with latest and high quality images.
Oscar P.
I must say I'm thoroughly impressed
Reviewed on Feb 29, 2024
Review provided by G2
What do you like best about the product?
The accuracy and quality of the generated images far exceeded my expectations. The process was seamless, and I was amazed at how quickly I could turn my textual descriptions into visually stunning images. Not only did the service save me valuable time, but it also allowed me to unleash my creativity in ways I never thought possible.
What do you dislike about the product?
Time and credit management should improve.
What problems is the product solving and how is that benefiting you?
Creation of contextual images for social meda posts and news websites.