Masterclass

Generative AI with Diffusion Models

Thanks to improvements in computing power and scientific theory, generative AI is more accessible than ever before. Generative AI plays a significant role across industries due to its numerous applications, such as creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. In this course, learnes will take a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines

Masterclasses are available only to attendees who purchased a paid upgrade.

Please note: Access to WeAreDevelopers World Congress is not included with a Masterclass ticket unless you have purchased a separate Congress pass.

Location:

All masterclasses will be held at MOA Hotel Berlin
Address: Stephanstraße 41, 10559 Berlin, Germany

08:00 - 09:00 | Registration
09:00 | Start of Masterclass
10:30 - 11:00 | Break I
12:30 - 13:30 | Lunch Break
15:00 - 15:30 | Break II
17:00 | End of Masterclass

What to bring:
Please bring your own laptop, as the Masterclasses are designed to be hands-on and practical.

WeAreDevelopers World Congress Pass Pickup:
If you upgraded your WeAreDevelopers World Congress pass with a masterclass seat, you can check in at the registration. Your pass will be ready there, so you’ll already have it for the main event the next day.

read description ↓

About this Course

Thanks to improvements in computing power and scientific theory, generative AI is more accessible than ever before. Generative AI plays a significant role across industries due to its numerous applications, such as creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. In this course, learnes will take a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines

Learning Objectives

  • Build a U-Net to generate images from pure noise
  • Improve the quality of generated images with the denoising diffusion process
  • Control the image output with context embeddings
  • Generate images from English text prompts using the Contrastive Language—Image Pretraining (CLIP) neural network

Topics Covered

  • U-Nets
  • Diffusion
  • CLIP
  • Text-to-image Models

Course Outline

From U-Net to Diffusion

  • Build a U-Net architecture.
  • Train a model to remove noise from an image.

Diffusion Models

  • Define the forward diffusion function.
  • Update the U-Net architecture to accommodate a timestep.
  • Define a reverse diffusion function.

Optimizations

  • Implement Group Normalization.
  • Implement GELU.
  • Implement Rearrange Pooling.
  • Implement Sinusoidal Position Embeddings.

Classifier-Free Diffusion Guidance

  • Add categorical embeddings to a U-Net.
  • Train a model with a Bernoulli mask.

CLIP

  • Learn how to use CLIP Encodings.
  • Use CLIP to create a text-to-image neural network.

For aspiring AI practitioners, software developers and data scientists

9 July 2025, Berlin

Full-day masterclass

Partner

In-Person NVIDIA Training
Get ready to supercharge your computing skills – join the AI masterclasses led by NVIDIA Deep Learning Institute. This is a special opportunity to learn hands-on from NVIDIA-certified instructors, master cutting-edge parallel programming techniques, and network with fellow engineers and AI developers—all in one high-intensity, lab-driven experience.

Capacity is strictly limited. This workshop is capped to ensure maximum instructor engagement and hands-on support.
Official partner:

Full-Day Masterclass Pass

9 July 2025
Only 30 spots are available
Only 100 spots are available
Current Price
Single
€800
excl. VAT
Group (4+)
€720
excl. VAT

Check out other masterclasses

Fundamentals of Deep Learning
Powered by NVIDIA
LEARN MORE
Fundamentals of Accelerated Computing with CUDA Python
Powered by NVIDIA
LEARN MORE
Did you actually listen?
Elisabeth Schlachter
LEARN MORE
Revolutionizing Software Processes with AI
Patrick Schnell
LEARN MORE
How to put GPT LLMs & friends into your applications
Sebastian Gingter
LEARN MORE
Building a Real World Architecture
David Tielke
LEARN MORE