Join us for a FREE hands-on Meetup webinar on Text Analysis with Azure AI Language Service (AI102) | Friday, December 20th, 2024 · 5:00 PM IST/ 7:30 AM EST Join us for a FREE hands-on Meetup webinar on Text Analysis with Azure AI Language Service (AI102) | Friday, December 20th, 2024 · 5:00 PM IST/ 7:30 AM EST
Search
Close this search box.
Search
Close this search box.

Generative AI Computer Vision Specialization | Level2

Enhance your Computer Vision Skills to solve real world problems using Generative AI

Duration

7.5 Hours

Level

Intermediate Level

Design and Tailor this course

As per your team needs

Edit Content

Welcome to a course tailored for seasoned professionals eager to integrate cutting-edge GenerativeAI concepts into real world image generation scenarios within the industry. In this course, we will thoroughly explore advanced GenerativeAI concepts and their exceptional relevance to modern image synthesis. Prepare to immerse yourself in the forefront of technology, as we dive into the latest state-of-the-art Generative Models like autoencoders, the innovative MidJourney, the revolutionary OPENAi DALLE-2 model, and the Diffusers. By revisiting and fortifying our grasp of GenerativeAI’s pivotal role, we will effectively equip ourselves to mold and define the landscape of image synthesis in real-world contexts.

Edit Content
  • Developers and software engineers interested in learning GenerativeAI
  • Computer Vision engineers looking to implement GenerativeAI models in various industry use cases.
  • AI enthusiasts and professionals aiming to build intelligent and innovative solutions
  • Even Data scientists and machine learning practitioners seeking to enhance their skills in working with GenAI models
Edit Content
  • Recap of GenerativeAI & its applications in Image generation
  • Review the basics of Generative Models – autoregressive models, variational autoencoders, and generative adversarial networks (GANs)
  • Deepdive into Generative AI 
    • Multimodal Models
    • Generative Models
    • Generative Video
    • Generative Audio
  • Conditional Image Generation based on class labels or text description
  • Understanding OpenAI’s DALL-E Image Generation Process
  • Overview of the Vision Transformer (ViT) 
    • How ViT outperform current SOTA CNNs
    • Scaling Up
    • High-Performing Large-Scale Image Recognition
    • Visualizations
  • Building Diffusion Models from Scratch
    • Starting with Noise and Progressing to Final Images
    • Developing Intuition at Each Step
  • MidJourney: Demonstration App
  • Lab(s): DALL-E 2 
  • Concluding Thoughts on Generative Models
  • DreamBooth motivation – Presentation
  • DreamBooth: Demonstration App

Fine-tune text-to-image Stable Diffusion model

Edit Content

Participants should have attended Generative AI Specialisation Computer Vision | Level 1 course or have an equivalent knowledge.

Connect

we'd love to have your feedback on your experience so far