AI & Prompt Engineering Meetup Munich


Details
Join us in our Munich office on April 10th, 2025 for the next round of the AI & Prompt Engineering Meetup, an interdisciplinary gathering for AI enthusiasts and experts from all backgrounds. We're excited to continue providing a platform for knowledge sharing and networking among fans and practitioners of AI and prompt engineering.
This time, we will focus on generative AI in the fields of image, audio, and video production. In a special edition of their talk "AI'll Be Back", the TNG Innovation Hacking team will introduce you to a variety of AI tools, explain their inner workings, and provide plenty of practical examples in fun live demonstrations. Our meetup offers valuable insights into crafting effective prompts and getting enhanced responses from generative AI tools. You will also have the unique opportunity to peek behind the curtain and discover the technology that powers these tools.
But that’s not all: The TNG Innovation Hacking team has also prepared various AI showcases for you to explore, including our brand-new Unitree G1 Robot nicknamed “G1PO”.
Whether you are a business professional, developer, or researcher, you can look forward to a great networking opportunity and a chance to reconnect with like-minded individuals over pizza and drinks.
If you cannot attend the event in person, you can also join us remotely as the talk will also be streamed live: https://tngtech.zoom.us/j/96289464844?pwd=Q3iMcg1wXrAxMJEWCHhiOcwH9QnPo3.1
Let's continue to explore the future of AI together!
Agenda:
18:15 - Doors open
18:45 - Talk "AI'll Be Back: Generative AI in Image, Audio, and Video Production - Special Edition" - Part 1
19:30 - Pizza break
20:00 - Talk "AI'll Be Back: Generative AI in Image, Audio, and Video Production - Special Edition" - Part 2
20:45 - FAQs, discussions, and networking
Abstract:
AI'll Be Back: Generative AI in Image, Audio, and Video Production - Special Edition
Martin Förtsch (Principal Consultant, TNG Technology Consulting GmbH) and Thomas Endres (Managing Partner, TNG Technology Consulting GmbH)
This talk introduces you to the world of generative AI with a focus on Text-to-Image, Text-to-Audio and Text-to-Video for creating images, music and short videos. We explain how neural networks can generate various output formats from short text inputs using diffusion models and so-called Transformer architectures.
We focus on advanced technologies such as Sora or Midjourney. The techniques used, such as Latent Diffusion Models, allow us to generate and edit images and videos by combining text understanding through attention mechanisms and transformers with denoising processes. A detailed examination of the video generation process with Sora shows how it compresses visual data, breaks it into patches, and then reconstructs it into the final video. In addition to Sora, we also discuss alternative methods and tools like RunwayML or SunoAI, to present a broad spectrum of tools for image, audio and video generation.
In this special edition of the talk, you will experience numerous hands-on demos showcasing different generative AI models.
By the end, you will have a basic understanding of diffusion models, an overview of tools for image, audio and video generation, and a deeper understanding of the functionality.

AI & Prompt Engineering Meetup Munich