> Markdown version of [/events/world-congress-2025/sessions/661-ai-ll-be-back](https://www.wearedevelopers.com/events/world-congress-2025/sessions/661-ai-ll-be-back). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI'll Be Back: Generative AI in Image, Video, and Audio Production


- **Date:** Thursday, Jul 10, 2025
- **Time:** 16:10–16:40 (30 min)
- **Room:** Stage 2
- **Event:** World Congress 2025
- **Tags:** ai, python

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/1509-ai-ll-be-back-generative-ai-in-image-video-and-audio-production)

## Description

This talk introduces the world of generative AI, focusing on Text-to-Image, Text-to-Audio, and Text-to-Video technologies for creating images, music, and videos. We explore how neural networks use diffusion models and Transformer architectures to generate outputs from short text prompts. Highlighting tools like Sora and Midjourney, we delve into techniques like Latent Diffusion Models, which combine text understanding with denoising processes to create and edit media.

A detailed look at video generation with Sora illustrates how it compresses and reconstructs visual data into final videos. We also discuss alternatives like RunwayML and SunoAI to showcase a wide range of tools for image, audio, and video generation.

By the end of this talk, you’ll gain a foundational understanding of diffusion models, an overview of generation tools, and insights into their functionality. Practical demos will provide hands-on examples throughout the presentation.

## Speakers

### [Anonymized By Request](https://www.wearedevelopers.com/@anonymized-by-request)

### [Martin Foertsch](https://www.wearedevelopers.com/@martin-foertsch)

TNG Technology Consulting GmbH, Principal Consultant
### [Thomas Endres](https://www.wearedevelopers.com/@thomas-endres)

Managing Partner, TNG Technology Consulting GmbH


## Related talks at this congress

- [GenAI Unpacked: Beyond Basic](https://www.wearedevelopers.com/events/world-congress-2025/sessions/918-genai-unpacked) — Damir
- [Privacy-first in-browser Generative AI web apps: offline-ready, future-proof, standards-based](https://www.wearedevelopers.com/events/world-congress-2025/sessions/551-privacy-first-in) — Maxim Salnikov
- [From Zero to Hero: How to put GPT LLMs & friends into your applications - Generative AI in Action](https://www.wearedevelopers.com/events/world-congress-2025/sessions/456-from-zero-to-hero) — Christian Weyer, Sebastian Gingter
- [Mobile AI on Arm: AI Text and Audio Generation Entirely on Device ](https://www.wearedevelopers.com/events/world-congress-2025/sessions/572-mobile-ai-on-arm-ai) — Michael Hall