IRL & Online Program
Creative AI & Diffusion Models
Explore Stable Diffusion, GANs, and neural rendering to generate art, music, and synthetic media.
Hands-on Highlights
- Train a custom GAN for face generation
- Fine-tune Stable Diffusion using DreamBooth
- Build an AI-powered image editing pipeline
- Generate synthetic voice audio using VITS
Detailed Syllabus
Week 1-2
GANs & Generative Foundations
- Introduction to Generative Adversarial Networks
- Building a DCGAN from scratch
- StyleGAN architectures
- Generating synthetic human faces
Week 3-4
Diffusion Models
- The math behind diffusion (Forward & Reverse processes)
- Stable Diffusion architecture
- Prompt engineering for image generation
- Fine-tuning with DreamBooth and LoRA
Week 5-6
Audio & Video Generation
- ControlNet for guided image generation
- Voice cloning and TTS using VITS/Bark
- Introduction to AI video generation
- Deploying a creative AI web app
Target Roles & Career Paths
Creative Technologist
AI Artist / Prompt Engineer
Synthetic Media Researcher
Generative UI/UX Prototyper
These are the primary roles you will be equipped to apply for upon successful completion of the course and portfolio projects.