Unlocking creativity: How generative AI and Amazon SageMaker assist companies produce advert creatives for advertising and marketing campaigns with AWS

Promoting businesses can use generative AI and text-to-image basis fashions to create modern advert creatives and content material. On this put up, we display how one can generate new photos from current base photos utilizing Amazon SageMaker, a totally managed service to construct, practice, and deploy ML fashions for at scale. With this answer, companies massive and small can develop new advert creatives a lot sooner and at decrease value than ever earlier than. This lets you develop new customized advert artistic content material for your enterprise at low value and at a speedy tempo.

Answer overview

Think about the next state of affairs: a worldwide automotive firm wants new advertising and marketing materials generated for his or her new automobile design being launched and hires a artistic company that’s recognized for offering promoting options for shoppers with sturdy model fairness. The automobile producer is searching for low-cost advert creatives that show the mannequin in various areas, colours, views, and views whereas sustaining the model id of the automobile producer. With the ability of state-of-the-art strategies, the artistic company can help their buyer by utilizing generative AI fashions inside their safe AWS atmosphere.

The answer is developed with Generative AI and Textual content-to-Picture fashions in Amazon SageMaker. SageMaker is a totally managed machine studying (ML) service that that makes it easy to construct, practice, and deploy ML fashions for any use case with totally managed infrastructure, instruments, and workflows. Stable Diffusion is a text-to-image basis mannequin from Stability AI that powers the picture technology course of. Diffusers are pre-trained fashions that use Steady Diffusion to make use of an current picture to generate new photos based mostly on a immediate. Combining Steady Diffusion with Diffusers like ControlNet can take current brand-specific content material and develop beautiful variations of it. Key advantages of growing the answer inside AWS together with Amazon SageMaker are:

  • Privateness – Storing the information in Amazon Simple Storage Service (Amazon S3) and utilizing SageMaker to host fashions means that you can adhere to safety greatest practices inside your AWS account whereas not exposing belongings publicly.
  • Scalability – The Steady Diffusion mannequin, when deployed as a SageMaker endpoint, brings scalability by permitting you to configure occasion sizes and variety of cases. SageMaker endpoints even have auto scaling options and are extremely accessible.
  • Flexibility – When creating and deploying endpoints, SageMaker supplies the flexibleness to decide on GPU occasion sorts. Additionally, cases behind SageMaker endpoints might be modified with minimal effort as enterprise wants change. AWS has additionally developed {hardware} and chips utilizing AWS Inferentia2 for prime efficiency on the lowest value for generative AI inference.
  • Fast innovation – Generative AI is a quickly evolving area with new approaches, and fashions are being always developed and launched. Amazon SageMaker JumpStart frequently onboards new fashions together with basis fashions.
  • Finish-to-end integration – AWS means that you can combine the artistic course of with any AWS service and develop an end-to-end course of utilizing fine-grained entry management via AWS Identity and Access Management (IAM), notification via Amazon Simple Notification Service (Amazon SNS), and postprocessing with the event-driven compute service AWS Lambda.
  • Distribution – When the brand new creatives are generated, AWS permits distributing the content material throughout world channels in a number of Areas utilizing Amazon CloudFront.

For this put up, we use the next GitHub sample, which makes use of Amazon SageMaker Studio with basis fashions (Steady Diffusion), prompts, laptop imaginative and prescient strategies, and a SageMaker endpoint to generate new photos from current photos. The next diagram illustrates the answer structure.

The workflow incorporates the next steps:

  1. We retailer the prevailing content material (photos, model types, and so forth) securely in S3 buckets.
  2. Inside SageMaker Studio notebooks, the unique picture information is reworked to photographs utilizing computer vision techniques, which preserves the form of the product (the automobile mannequin), removes colour and background, and generates monotone intermediate photos.
  3. The intermediate picture acts as a management picture for Steady Diffusion with ControlNet.
  4. We deploy a SageMaker endpoint with the Steady Diffusion text-to-image basis mannequin from SageMaker Jumpstart and ControlNet on a most well-liked GPU-based occasion dimension.
  5. Prompts describing new backgrounds and automobile colours together with the intermediate monotone picture are used to invoke the SageMaker endpoint, yielding new photos.
  6. New photos are saved in S3 buckets as they’re generated.

Deploy ControlNet on SageMaker endpoints

To deploy the mannequin to SageMaker endpoints, we should create a compressed file for every particular person approach mannequin artifact together with the Steady Diffusion weights, inference script, and NVIDIA Triton config file.

Within the following code, we obtain the mannequin weights for the completely different ControlNet strategies and Steady Diffusion 1.5 to the native listing as tar.gz recordsdata:

if ids =="runwayml/stable-diffusion-v1-5":
    snapshot_download(ids, local_dir=str(model_tar_dir), local_dir_use_symlinks=False,ignore_patterns=unwanted_files_sd)

elif ids =="lllyasviel/sd-controlnet-canny":
    snapshot_download(ids, local_dir=str(model_tar_dir), local_dir_use_symlinks=False)  

To create the mannequin pipeline, we outline an script that SageMaker real-time endpoints will use to load and host the Steady Diffusion and ControlNet tar.gz recordsdata. The next is a snippet from that reveals how the fashions are loaded and the way the Canny approach known as:

controlnet = ControlNetModel.from_pretrained(
        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)

pipe = StableDiffusionControlNetPipeline.from_pretrained(
        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32)

# Outline approach operate for Canny 
picture = cv2.Canny(picture, low_threshold, high_threshold)

We deploy the SageMaker endpoint with the required occasion dimension (GPU sort) from the mannequin URI:

huggingface_model = HuggingFaceModel(
        model_data=model_s3_uri,  # path to your educated sagemaker mannequin
        function=function, # iam function with permissions to create an Endpoint  
        py_version="py39", # python model of the DLC  

# Deploy mannequin as SageMaker Endpoint
predictor = huggingface_model.deploy(

Generate new photos

Now that the endpoint is deployed on SageMaker endpoints, we are able to go in our prompts and the unique picture we wish to use as our baseline.

To outline the immediate, we create a constructive immediate, p_p, for what we’re searching for within the new picture, and the unfavourable immediate, n_p, for what’s to be averted:

p_p="metallic orange coloured automobile, full automobile, color picture, open air in a nice panorama, lifelike, prime quality"

n_p="cropped, out of body, worst high quality, low high quality, jpeg artifacts, ugly, blurry, unhealthy anatomy, unhealthy proportions"

Lastly, we invoke our endpoint with the immediate and supply picture to generate our new picture:

        "image_uri":'s3://<bucker>/sportscar.jpeg', #current content material
        "scale": 0.5,
        "seed": 123, 

Totally different ControlNet strategies

On this part, we evaluate the completely different ControlNet strategies and their impact on the ensuing picture. We use the next unique picture to generate new content material utilizing Steady Diffusion with Management-net in Amazon SageMaker.

The next desk reveals how the approach output dictates what, from the unique picture, to concentrate on.

Approach Title Approach Kind Approach Output Immediate Steady Diffusion with ControlNet
canny A monochrome picture with white edges on a black background. metallic orange coloured automobile, full automobile, color picture, open air in a nice panorama, lifelike, prime quality
depth A grayscale picture with black representing deep areas and white representing shallow areas. metallic purple coloured automobile, full automobile, color picture, open air in nice panorama on seaside, lifelike, prime quality
hed A monochrome picture with white mushy edges on a black background. metallic white coloured automobile, full automobile, color picture, in a metropolis, at night time, lifelike, prime quality
scribble A hand-drawn monochrome picture with white outlines on a black background. metallic blue coloured automobile, much like unique automobile, full automobile, color picture, open air, breath-taking view, lifelike, prime quality, completely different viewpoint

Clear up

After you generate new advert creatives with generative AI, clear up any sources that gained’t be used. Delete the information in Amazon S3 and cease any SageMaker Studio pocket book cases to not incur any additional fees. If you happen to used SageMaker JumpStart to deploy Steady Diffusion as a SageMaker real-time endpoint, delete the endpoint both via the SageMaker console or SageMaker Studio.


On this put up, we used basis fashions on SageMaker to create new content material photos from current photos saved in Amazon S3. With these strategies, advertising and marketing, commercial, and different artistic businesses can use generative AI instruments to enhance their advert creatives course of. To dive deeper into the answer and code proven on this demo, try the GitHub repo.

Additionally, confer with Amazon Bedrock to be used instances on generative AI, basis fashions, and text-to-image fashions.

Concerning the Authors

Sovik Kumar Nath is an AI/ML answer architect with AWS. He has intensive expertise designing end-to-end machine studying and enterprise analytics options in finance, operations, advertising and marketing, healthcare, provide chain administration, and IoT. Sovik has printed articles and holds a patent in ML mannequin monitoring. He has double masters levels from the College of South Florida, College of Fribourg, Switzerland, and a bachelors diploma from the Indian Institute of Know-how, Kharagpur. Exterior of labor, Sovik enjoys touring, taking ferry rides, and watching motion pictures.

Sandeep Verma is a Sr. Prototyping Architect with AWS. He enjoys diving deep into buyer challenges and constructing prototypes for purchasers to speed up innovation. He has a background in AI/ML, founding father of New Information, and usually obsessed with tech. In his free time, he loves touring and snowboarding together with his household.

Uchenna Egbe is an Affiliate Options Architect at AWS. He spends his free time researching about herbs, teas, superfoods, and the right way to incorporate them into his every day eating regimen.

Mani Khanuja is an Synthetic Intelligence and Machine Studying Specialist SA at Amazon Net Providers (AWS). She helps prospects utilizing machine studying to unravel their enterprise challenges utilizing the AWS. She spends most of her time diving deep and instructing prospects on AI/ML initiatives associated to laptop imaginative and prescient, pure language processing, forecasting, ML on the edge, and extra. She is obsessed with ML at edge, subsequently, she has created her personal lab with self-driving package and prototype manufacturing manufacturing line, the place she spend lot of her free time.

Exploring summarization choices for Healthcare with Amazon SageMaker

4 Essential Components for Evaluating Giant Language Fashions in Business Functions | by Skanda Vivek | Aug, 2023