Timo Zander

In the Dawn of the AI: Understanding and implementing AI-generated images

One neural network forges images from random noise. Another learns to spot the fakes. The result? Astonishingly realistic AI-generated art.

In the Dawn of the AI: Understanding and implementing AI-generated images
#1about 3 minutes

The rise of advanced AI text-to-image synthesis

AI models like OpenAI's DALL-E 2 can now generate photorealistic and culturally specific images directly from natural language prompts.

#2about 4 minutes

How generative adversarial networks (GANs) work

GANs use a two-player system where a generator creates fake images and a discriminator judges them against real ones, forcing both to improve.

#3about 2 minutes

The mathematical foundation of the GAN training process

The training process is a min-max game governed by a value function, where the discriminator maximizes accuracy and the generator minimizes it by creating better fakes.

#4about 3 minutes

Overcoming mode collapse for diverse outputs

Mode collapse, where the generator produces limited variety, can be fixed by introducing a similarity check that penalizes a lack of diversity in outputs.

#5about 3 minutes

Fixing non-convergence and vanishing gradient issues

Address training deadlocks with a two-timescale update rule and solve the vanishing gradient problem by replacing sigmoid activation functions with ReLU.

#6about 4 minutes

Using progressive GANs for high-resolution image generation

Progressive GANs achieve high-resolution results by starting with a low-resolution image and gradually fading in new layers to increase detail during training.

#7about 3 minutes

Creating controllable landscapes with GauGAN

GauGAN allows users to control image generation by providing a segmentation map for layout and a style image to set the overall mood and color palette.

#8about 8 minutes

The future and ethical challenges of AI image generation

The Q&A session explores the societal impact of AI-generated images, including deepfake detection, AI safety, AI-powered editing, and legal ownership.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

Deepfakes in Realtime - How Neural Networks Are Changing Our World46:42

Deepfakes in Realtime - How Neural Networks Are Changing Our World

Thomas Endres, Martin Förtsch & Jonas Mayer

The AI Elections: How Technology Could Shape Public Sentiment30:02

The AI Elections: How Technology Could Shape Public Sentiment

Martin Förtsch, Thomas Endres

Multimodal Generative AI Demystified56:55

Multimodal Generative AI Demystified

Ekaterina Sirazitdinova

Your imaginations is (no longer) the limit: how Generative AI empowers people to be creative29:27

Your imaginations is (no longer) the limit: how Generative AI empowers people to be creative

David Estevez

AI'll Be Back: Generative AI in Image, Video, and Audio Production29:54

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

Fabian Pottbäcker, Thomas Endres, Martin Foertsch

GenAI after the Hype: Transforming Organizations with GenAI-based Agents29:26

GenAI after the Hype: Transforming Organizations with GenAI-based Agents

Alexander Birke, Silke Eggert

ChatGPT: Create a Presentation!30:24

ChatGPT: Create a Presentation!

Markus Walker

AI: Superhero or Supervillain? How and Why with Scott Hanselman25:17

AI: Superhero or Supervillain? How and Why with Scott Hanselman

Scott Hanselman

From learning to earning

Jobs that call for the skills explored in this talk.