Kieran

Prompts with Clarity, Specificity & Contextual Information

"AI Prompt Engineering Tutorial" is an interactive learning activity that guides users in creating and refining prompts for AI models like Groq, Hugging Face or OpenAI's GPT. The tutorial focuses on teaching Clarity and Specificity and Contextual Information in crafting effective prompts for AI. Users will start by providing a vague prompt, then refine it to be more specific, and finally, add contextual information to see how the AI’s responses evolve with each iteration.

Single Image AI captions

In this activity, a local image file is processed through the robust "nlpconnect/vit-gpt2-image-captioning" model from Hugging Face. The model generates a descriptive caption by analyzing visual content in the image.

Inpainting and Restoration Challenge(discontinued)

In this activity, you’ll explore the power of image inpainting to transform or repair images. Instead of generating an image solely from text, you’ll provide an existing image and a corresponding mask (where white areas indicate regions to be modified or restored). By supplying a textual prompt that describes the desired change, the AI model fills in the masked regions to create a seamless, restored, or altered image. This exercise is perfect for learning how to guide the creative process beyond full image synthesis—enabling detailed editing and repair of existing visuals.

Post-Processing Magic Workshop

In this activity, you'll generate an image using a text-to-image model (Stable Diffusion) and then enhance it with post-processing techniques. The session focuses on applying practical image adjustments such as increasing brightness, boosting contrast, and adding a soft-focus effect with Gaussian blur. Using Python libraries like Pillow, you'll learn how to transform raw AI-generated images into polished artworks, highlighting the impact of subtle adjustments on the overall visual quality. Enjoy exploring how post-processing can refine and elevate your creative output!

Sentiment Analysis Application

Sentiment Analysis Application

AI Prompt Refinement: From Vague to Contextual

To reinforce the skill of prompt engineering by crafting, refining, and evaluating prompts for clarity, specificity, and context.

Prompt Lab: Tune Your Creativity & Control

To reinforce how temperature settings and instruction-based prompts influence AI responses—helping students practice generating structured, creative, and tailored content using specific instructions and temperature adjustments.

Image Manipulation Challenge

Learn how to apply basic image manipulation techniques like rotation, cropping, and brightness adjustments, while also gaining experience with image transformations.

Image Resizer

Create a Python script using OpenCV to resize an image into three predefined sizes, display each resized image, and save it.

Adding Random movie recommendation

Create a movie recommendation system that offers AI-based or random suggestions. Users can select recommendations based on genre, mood, or IMDB rating. Display structured movie details like title, genre, IMDB rating, and sentiment analysis of the overview for a clear and engaging experience.

Enhancing the MNIST Digit Classifier

In this assignment, you will build on the concepts you've learned in class to enhance and further explore the MNIST digit classification model. You will modify and improve the neural network to achieve better performance, implement data augmentation to improve model robustness, and experiment with different activation functions and optimizers. This challenge will help reinforce your understanding of neural networks, data preprocessing, and model evaluation.