AI & Machine Learning
Generative AI with Diffusion Models
Learn how diffusion models generate images.
1 dayIntermediate1 modules
About this course
Learn how diffusion models generate images. You will build a U-Net, implement the denoising diffusion process, compare DDPMs with DDIMs, control output with context embeddings and use CLIP to generate images from text prompts.
What you'll learn
- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the Denoising Diffusion process
- Compare Denoising Diffusion Probabilistic Models (DDPMs) with Denoising Diffusion Implicit Models (DDIMs)
- Control the image output with context embeddings
- Generate images from English text-prompts using CLIP
Curriculum
1 modules
- Course Introduction
- From U-Nets to Diffusion
- Control with Context
- Text-to-Image with CLIP
- State-of-the-art Models
- Final Review
Who it's for
Developers and data scientists with deep learning experience who want to build generative image systems.
Before you start
- Good understanding of PyTorch
- Good understanding of deep learning
Related courses
More in AI & Machine Learning →Intermediate
Accelerated Delivery Using AI
AI & Machine Learning
View course →Intermediate
Accelerating Data Engineering Pipelines
AI & Machine Learning
View course →Foundation
Agentic Fundamentals for Business Professionals
AI & Machine Learning
View course →Intermediate
AI Agents with Google's ADK Bootcamp: Build with Gemini, Protocols, & AgentOps
AI & Machine Learning
View course →Intermediate
AI Driven Road Management
AI & Machine Learning
View course →Foundation
AI Ethical Use and Responsibility - Beginner
AI & Machine Learning
View course →Let's plan your next step together.
Tell us the course or certification you have in mind and we'll send the outline, upcoming dates, fees and private-team options.