Artificial Intelligence Intermediate Live Classes

Multimodal Gen AI & Diffusion Models

Build image, audio and multimodal generation systems with diffusion models and vision-language models, hands-on.

4.8 540 enrolled 14 weeks · 110+ live learning hours Certificate
Overview
Curriculum
Instructor
FAQ

Program Overview

An intermediate specialization on generation beyond text. Across 14 weeks and 110+ live hours you learn diffusion models, image and audio generation, vision-language models and multimodal pipelines, building creative and practical generation apps.

What you'll learn

  • Understand diffusion model fundamentals
  • Generate and edit images programmatically
  • Work with vision-language models
  • Build multimodal generation pipelines
  • Deploy a generative media app

Tools you'll use

PythonPyTorchHugging Face DiffusersStable DiffusionOpenAI API

Hands-on Projects

  • Image generation and editing app
  • Multimodal generation pipeline

Career Outcomes

Generative AI EngineerMultimodal AI DeveloperAI Creative Technologist

Complimentary software included

Enroll in this course and get these professional tools free — licenses and access are provided as part of the program, at no extra cost.

GPU Cloud Credits Compute

Run diffusion models.

Hugging Face Pro Model Hub

Diffusers and models.

Stable Diffusion (Tools) Generation

Image generation toolkit.

Weights & Biases MLOps

Track experiments.

Curriculum

Generative Modeling Foundations
  • GANs vs diffusion
  • Latent space
Diffusion Models In Depth
  • Denoising
  • Samplers
Image Generation & Editing
  • Text-to-image
  • Inpainting
Vision-Language Models
  • CLIP
  • Captioning
Audio & Multimodal Generation
  • Audio gen
  • Multimodal fusion
Applied Multimodal Project
  • Pipeline
  • Capstone

Marcus Lee

AI Engineering Lead

Built GenAI products used by millions.

Certificate

Verified specialization certificate with project review.

No FAQs yet. Submit an inquiry for any questions.

Related Programs

PGP in Generative AI Featured
Artificial Intelligence

PGP in Generative AI

Flagship 12-month Gen AI postgraduate program covering transformers, LLMs, RAG, fine-tuning, diffusion and production GenAI systems with 6 capstones, 1:1 mentorship and placement support.

Advanced 12 months · 480+ live learning hours Live Certificate
$29,999$39,999
Enroll Now
$14,999