Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Prompt Engineering for Vision Models

  • up to 1 hour
  • Beginner

This course provides a comprehensive introduction to prompt engineering for vision models. Learn to prompt different vision models, fine-tune diffusion models, and replace parts of images with generated content. Ideal for those looking to expand their skills in generative AI and vision models.

  • Image Generation
  • Image Segmentation
  • Object Detection
  • In-painting
  • Fine-tuning

Overview

In this course, you will learn to prompt various vision models such as Meta’s Segment Anything Model (SAM), OWL-ViT, and Stable Diffusion 2.0. You will explore techniques like image generation, image segmentation, object detection, and in-painting. Additionally, you will learn to fine-tune diffusion models using DreamBooth and track your experiments with Comet. This hands-on course is designed to help you get started with prompting vision models and enhance your image generation capabilities.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Aspiring Machine Learning Engineers

Individuals looking to gain hands-on experience with vision models and prompt engineering.

Data Scientists

Professionals aiming to expand their skill set to include vision model prompting and fine-tuning techniques.

AI Enthusiasts

Anyone interested in learning about the latest advancements in vision models and generative AI.

This course offers a hands-on approach to learning prompt engineering for vision models. You will gain practical skills in image generation, segmentation, and object detection, making it ideal for beginners and professionals looking to advance their careers in AI.

Pre-Requisites

1 / 2

  • Basic Python experience

  • Familiarity with machine learning concepts

What will you learn?

Image Generation
Learn to prompt with text and adjust hyperparameters like strength, guidance scale, and number of inference steps.
Image Segmentation
Prompt with positive or negative coordinates, and with bounding box coordinates.
Object Detection
Prompt with natural language to produce a bounding box to isolate specific objects within images.
In-painting
Combine the above techniques to replace objects within an image with generated content.
Personalization with Fine-tuning
Generate custom images based on pictures of people or places that you provide, using a fine-tuning technique called DreamBooth.
Iterating and Experiment Tracking
Learn to track experiments and optimize visual prompt engineering workflows using Comet.

Meet your instructors

  • Abby Morgan

    Machine Learning Marketing Engineer, Comet

    Abby Morgan is a driven and highly detail-oriented data scientist with over 600 hours of hands-on experience in data science and machine learning. She has a passion for learning and collaborates with cross-functional teams to build top-quality, clean reports that provide clients with mission-critical analysis.

  • Jacques Verré

    Head of Product, Comet

    Jacques Verré is the Head of Product at Comet, a self-hosted and cloud-based meta machine learning platform that helps data scientists and teams track, compare, explain, and optimize their experiments and models. He leads the product team at Comet, which is building tools to help data scientists be more productive and build better models faster.

  • Caleb Kaiser

    Software Engineer - ML/Growth, Comet

    Caleb Kaiser is a Software Engineer - ML/Growth at Comet. He is also an instructor at DeepLearning.AI.

Upcoming cohorts

  • Dates

    start now

Free