Case Studies | SaaS B2B

Designing rooms from a sentence

AI Image Mock-up Generation

About

A SaaS B2B business working with Cloud Combinator on AWS. The client is anonymised at their request.

Challenge

The proof of concept centred on three focus areas that together defined an usable generation service.

Turning language into accurate imagery

The service had to convert natural language prompts into visually accurate mock-ups, generating realistic room backgrounds in which designers could showcase their products rather than editing each scene by hand.

Control over format and framing

Beyond a single output, the tool needed to automate image sizes and ratios and offer more than one way to generate, so designers could produce variations of a product image or extend a scene to fit a setting.

Reliable operation on managed infrastructure

The model needed to run dependably under expected load without significant downtime or performance degradation, on a serverless, automatable architecture that the client could stand up and reason about.

Solution

An user sends an image and a prompt through an Amazon API Gateway WebSocket API. API Gateway forwards the request to AWS Lambda, which validates it, extracts the image and prompt, and stores the original image in Amazon S3 for reference and logging.

4,096px

Maximum image variation resolution

2

Generation modes: variations and outpainting

512

Characters per natural-language prompt

By the numbers:

  • 4,096px - Maximum image variation resolution
  • 2 - Generation modes: variations and outpainting
  • 512 - Characters per natural-language prompt
Changes

The proof of concept met its agreed scope: a working prompt-to-image pipeline was delivered on AWS, with acceptance based on signing off the delivery scope, the competence of the client's internal technical lead, and confirmation that Amazon Bedrock and SageMaker were a suitable service for the requirement. The efficiency and user-experience gains that motivated the project were the projected benefits of automating the design step.

  • Prompt to mock-up — Natural language prompts turned into realistic room backgrounds and product mock-ups using Amazon Titan Image Generator v2 on SageMaker.
  • Format control — Two generation modes, variations and outpainting, with automated handling of image sizes and ratios.
  • Serverless, deployable pipeline — API Gateway, Lambda, S3 and DynamoDB provisioned via AWS CloudFormation for a repeatable, low-overhead deployment.
  • Data durability — S3 objects moved to Glacier after 180 days and replicated to a second region, with DynamoDB point-in-time and on-demand backups.
  • Handover — A demonstration, user materials and documentation provided so the client's team could operate and extend the service.

With a proven generation pipeline in place, the client is positioned to move the capability from proof of concept toward production and build richer visualisation tools on top of the same AWS foundation.

AWS Stack

Amazon SageMaker

Running Amazon Titan Image Generator v2 for prompt-driven image generation.

Amazon Bedrock

For generative AI capabilities underpinning the service.

Amazon API

Gateway, including a WebSocket API, for handling client requests.

AWS Lambda

For serverless request validation and orchestration.

Amazon S3

For image storage, with Glacier lifecycle archival and cross-region replication.

Amazon DynamoDB

For transaction metadata with point-in-time recovery.

AWS CloudFormation

For repeatable infrastructure deployment, with IAM for access control.

YOU MIGHT LIKE

Related success stories

View all case studies

Case Studies | Insights

Utilising Language Recognition, Speed, and Enhanced Security to Make Social Media a Force for Good

  • Here, we take a detailed look at how the Cloud Combinator team collaborated with another cutting-edge AI service provider that provides intelligent systems to “make social media more social” for brands and users alike.
  • Arwen AI is a UK-based startup specialising in AI solutions to manage and enhance brands’ social media interactions. Founded in 2020 by Matt McGrory, Dr. David Cole, and Joel Bailey, Arwen. AI focuses on using AI to automatically detect and remove spam, toxic comments, and other unwanted content from social media platforms.
  • The team at Arwen have three core products. ‘Moderate’ is focused on identifying and removing toxic content from social media channels. ‘Engage’ helps brands identify and engage with meaningful conversations on social media, and ‘Customize’ allows brands to apply bespoke algorithms to their channels - creating an even more effective moderation and engagement.
Read more
CONTACT US

Ready to turn AI into impact?

We'll help you spot the highest-value opportunities, reduce risk around your first AI initiative, and define a clear path to results from day one.

Why talk to us:

Outcome-driven recommendations

AWS-recognised delivery expertise

Risk-aware AI adoption

Clear next step, not a sales pitch

Start with a focused 20-minute conversation about your goals — no pressure, no commitment.

We use cookies

This website uses cookies to enhance user experience and to analyze performance and traffic on our website.

See our Privacy Policy for details.