Building Owly: An AI Comic Video Generator for My Son • Agustinus Nalwan • YOW! 2023

This presentation was recorded at YOW! Perth 2023. #GOTOcon #YOW Agustinus Nalwan - GM of AI, Data Platform & Data Science @agustinusnalwan2200 RESOURCES ABSTRACT Utilising an Amazon Bedrock Large Language Model (LLM) and a fine-tuned Stable Diffusion 2.1 on Amazon SageMaker JumpStart, I developed an AI tech called Owly that crafts personalised comic videos with music, starring my son’s toys as the lead characters. I will take you through the process (but not limited to) how I utilised LLM to generate the story script via prompt engineering and how I fine-tuned the model to learn to generate an image with a new characters. [...] TIMECODES 00:00 Intro 02:04 Project faAi 02:56 Project Ellee 04:20 Demo: Ellee in action 06:12 Owly – a personalized comic video generator 07:44 What does Owly do? 08:09 Demo: Owly in action 10:49 How does Owly work? 12:58 LLM 13:18 Demo 16:52 Amazon Bedrock 17:10 Building the comic image generator 17:45 How the Stable Diffusion model was built 19:52 Challenges & enhancements 24:28 Problems & solutions 26:44 unplanned cool feature 30:10 Architecture 32:15 Something cool 33:48 Outro Download slides and read the full abstract here: RECOMMENDED BOOKS Sean Moriarity • Genetic Algorithms in Elixir • Sean Moriarity • Machine Learning in Elixir • Ian Goodfellow, Yoshua Bengio & Aaron Courville • Deep Learning • Francois Chollet • Deep Learning with Python • #Owly #AI #ArtificialIntelligence #AIVideoGenerator #LLM #AmazonBedrock #AmazonSageMaker #StableDiffusion #AgustinusNalwan #YOWcon Looking for a unique learning experience? Attend the next GOTO conference near you! Get your ticket at Sign up for updates and specials at SUBSCRIBE TO OUR CHANNEL - new videos posted almost daily.
Back to Top