Broadcast Date: June 16, 2023
Level: 200
Learn how one of our AWS ML Heroes built Owly, a generative AI application that uses a fine-tuned Stable Diffusion 2.1 model on Amazon SageMaker JumpStart and an LLM to generate personalized comic videos featuring his son’s toys as the main characters. With the help of Amazon SageMaker Batch Transform, the fine-tuned model creates the comic strips, while Amazon Polly Neural TTS adds audio narration. The final story is turned into a video complete with music, courtesy of MoviePy. All this orchestration is made possible thanks to the power of AWS Batch. Tune in for an in-depth presentation with our AWS ML Hero followed by a short Q&A session.
Learning Objectives
- How to use Amazon SageMaker JumpStart, Training Job and Batch Transform to fine-tune the Stable Diffusion model and to generate many images efficiently.
- How to use Amazon SageMaker Studio to easily experiment on your model.
- How to construct prompts for an LLM to generate a captivating story script.
Who Should Attend?
Developers, Data Scientists, ML practitioners
Speaker(s)
Agustinus Nalwan, GM of AI, Data Science and Data Platform at Carsales and AWS Machine Learning Hero
Learn More
To learn more about the services featured in this talk, please visit:
https://agustinus-nalwan.medium.com/building-owly-an-ai-comic-story-generator-for-my-son-c99fb695d83b
Intro body copy here about 2018 re:Invent launches.
Download the slide deck
Compute
Service How To
December 19th, 2018 | 1:00 PM PT
Developing Deep Learning Models for Computer Vision with
Amazon EC2 P3 Instances.
Data Lakes & Analytics
Webinar 1:
What's New / Cloud Innovation
December 10th, 2018 | 11:00 AM PT
EMBARGOED
Register Now>