Sold by: MphasisÂ
Deployed on AWS
This solution can synthesize varied backgrounds for an image containing a subject, whether a human subject or any specific character/object.
Overview
Personalized Image background synthesis helps in creating high-quality ethical images of a specific subject of interest in the unique, photo-realistic varied background based on the text provided. The solution uses deep generative neural network concepts like image synthesis and latent diffusion models to create completely new images of the subject in diverse contextual settings with reduced memory and computational cost. It can also enhance the resolution or change the design of the image as per the text input. It uses ML-based content moderation techniques to consider the ethical aspects of generated images by sending appropriate warnings. If "Not Safe For Work" score (NSFW) is more than a fixed threshold or a blank image is generated then the model throws an error stating to give an appropriate input prompt or to change the random seed.
Highlights
- The solution can be used for subject-driven image upscaling/editing, in which the resolution of an image is increased, with more designs and styles potentially being added to the image keeping the fidelity of the subject. The model also considers the ethical aspects of image generation and gives NSFW (Not Safe For Work) warnings appropriately. The content input by the user and output generated by the listing needs to be duly verified by the user for quality and ethical concerns before using/integrating with other applications.
- This Personalized Image background synthesis can be applied to use cases like data augmentation, in which the visual features of image data are changed keeping the subject/character in context to create more data of similar kind. This reduces manual effort and improves productivity in cross-functional industries, some of which are metaverse, online content generation, Creative/Digital media, wildlife photography, designing UX/UI, etc. Example: Given the subject mickey mouse in a garden can be recreated inside a house, factory, car, etc. based on a prompt provided.
- Mphasis Synth Studio is an Enterprise Synthetic Data Platform for generating high-quality synthetic data that can help derive and monetize trustworthy business insights while preserving privacy and protecting data subjects. Build reliable and high-accuracy models when you have no or low data. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
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
Pricing is based on actual usage, with charges varying according to how much you consume. 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.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.p3.2xlarge Inference (Batch) Recommended | Model inference on the ml.p3.2xlarge instance type, batch mode | $10.00 |
ml.p3.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.p3.2xlarge instance type, real-time mode | $5.00 |
ml.g4dn.xlarge Training Recommended | Algorithm training on the ml.g4dn.xlarge instance type | $5.00 |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $10.00 |
ml.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $10.00 |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $10.00 |
ml.p2.16xlarge Inference (Batch) | Model inference on the ml.p2.16xlarge instance type, batch mode | $10.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $10.00 |
ml.p3.8xlarge Inference (Real-Time) | Model inference on the ml.p3.8xlarge instance type, real-time mode | $5.00 |
ml.p2.xlarge Inference (Real-Time) | Model inference on the ml.p2.xlarge instance type, real-time mode | $5.00 |
Vendor refund policy
Currently, we do not support refunds, but you can cancel your subscription to the service at any time.
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)Â .
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 algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the 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
version 1.0
Additional details
Inputs
- Summary
Usage Methodology for the algorithm:
- The input must be 'Input.zip' file.
- The zip file should contain Input file which includes a .json file.
- The name of the .json file should be "parameters" which is case sensitive.
- The parameter file should contain id,seed and prompt values.
- check the instructions and sample endpoint in the sample jupyter file provided.
- Input MIME type
- application/zip, application/gzip
https://github.com/Mphasis-ML-Marketplace/Personalized-Image-background-synthesis/tree/main/Input
https://github.com/Mphasis-ML-Marketplace/Personalized-Image-background-synthesis/tree/main/Input
Resources
Vendor resources
Support
Vendor support
For any assistance reach out to us at:
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
Turn pictures into personalized art with AI and neural style transfer
Personalized Recommendations delivers hyper-personalized product suggestions by combining deep learning, customer behavior, and rich product data. Designed for fashion and lifestyle retailers, it boosts engagement and conversions through real-time, context-aware recommendations powered by visual AI.
Model is an inference pipeline for person detection, recognition and reidentification
Automate 40 - 70% of business content creation and accelerate your marketing team's ability to deliver high quality automated Hyper-Personalization Marketing Automation through Iternal's platform.
Automate 40 - 70% of business content creation and accelerate your marketing team's ability to deliver high quality Personalized Product Videos through Iternal's platform.
Customer reviews
No customer reviews yet
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.