5 Fun Generative AI Projects for Absolute Beginners

Image by Author | Canva

# Introduction

 
This is the second article in my newbie undertaking collection. If you haven’t seen the primary one on Python, it’s value trying out: 5 Fun Python Projects for Absolute Beginners.

So, what’s generative AI or Gen AI? It is all about creating new content material like textual content, photographs, code, audio, and even video utilizing AI. Before the massive language and imaginative and prescient fashions period, issues had been fairly totally different. But now, with the rise of basis fashions like GPT, LLaMA, and LLaVA, every little thing has shifted. You can construct artistic instruments and interactive apps with out having to coach fashions from scratch.

I’ve picked these 5 initiatives to cowl a little bit of every little thing: textual content, picture, voice, imaginative and prescient, and a few backend ideas like fine-tuning and RAG. You’ll get to check out each API-based options and native setups, and by the tip, you’ll have touched all of the constructing blocks utilized in most fashionable Gen AI apps. So, Let’s get began.

 

# 1. Recipe Generator App (Text Generation)

 
Link: Build a Recipe Generator with React and AI: Code Meets Kitchen

We’ll begin with one thing easy and enjoyable that solely makes use of textual content era and an API key, no want for heavy setup. This app allows you to enter just a few fundamental particulars like components, meal kind, delicacies choice, cooking time, and complexity. It then generates a full recipe utilizing GPT. You’ll learn to create the frontend kind, ship the information to GPT, and render the AI-generated recipe again to the person. Here is one other superior model of similar thought: Create an AI Recipe Finder with GPT o1-preview in 1 Hour. This one has extra superior immediate engineering, GPT-4, solutions, ingredient substitutions, and a extra dynamic frontend.

 

# 2. Image Generator App (Stable Diffusion, Local Setup)

 
Link: Build a Python AI Image Generator in 15 Minutes (Free & Local)

Yes, you’ll be able to generate cool photographs utilizing instruments like ChatGPT, DALL·E, or Midjourney by simply typing a immediate. But what if you wish to take it a step additional and run every little thing regionally with no API prices or cloud restrictions? This undertaking does precisely that. In this video, you’ll learn to arrange Stable Diffusion by yourself laptop. The creator retains it tremendous easy: you put in Python, clone a light-weight net UI repo, obtain the mannequin checkpoint, and run a neighborhood server. That’s it. After that, you’ll be able to enter textual content prompts in your browser and generate AI photographs immediately, all with out web or API calls.

 

# 3. Medical Chatbot with Voice + Vision + Text

 
Link: Build an AI Voice Assistant App using Multimodal LLM Llava and Whisper

This undertaking isn’t particularly constructed as a medical chatbot, however the use case suits nicely. You communicate to it, it listens, it might probably have a look at a picture (like an X-ray or doc), and it responds intelligently combining all three modes: voice, imaginative and prescient, and textual content. It’s constructed utilizing LLaVA (a multimodal vision-language mannequin) and Whisper (OpenAI’s speech-to-text mannequin) in a Gradio interface. The video walks via setting it up on Colab, putting in libraries, quantizing LLaVA to run in your GPU, and stitching all of it along with gTTS for audio replies.

 

# 4. Fine-Tuning Modern LLMs

 
Link: Fine tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers

So far, we’ve been utilizing off-the-shelf fashions with immediate engineering. That works, however if you would like extra management, fine-tuning is the subsequent step. This video from Trelis Research is without doubt one of the greatest on the market. Therefore, as a substitute of suggesting a undertaking that merely swaps a fine-tune mannequin, I wished you to focuse on the precise means of fine-tuning a mannequin your self. This video exhibits you the best way to fine-tune fashions like Gemma 3, Qwen3, Llama 4, Phi 4, and Mistral Small utilizing Unsloth (library for sooner, memory-efficient coaching) and Transformers. It’s lengthy (about 1.5 hours), however tremendous value it. You’ll study when fine-tuning is smart, the best way to prep datasets, run fast evals utilizing vLLM, and debug actual coaching points.

 

# 5. Build Local RAG from Scratch

 
Link: Local Retrieval Augmented Generation (RAG) from Scratch (step by step tutorial)

Everyone loves chatbot, however most crumble when requested about stuff outdoors their coaching information. That’s the place RAG is beneficial. You give your LLM a vector database of related paperwork, and it pulls context earlier than answering. The video walks you thru constructing a totally native RAG system utilizing a Colab pocket book or your personal machine. You’ll load paperwork (like a textbook PDF), cut up them into chunks, generate embeddings with a sentence-transformer mannequin, retailer them in SQLite-VSS, and join all of it to a neighborhood LLM (e.g. Llama 2 by way of Ollama). It’s the clearest RAG tutorial I’ve seen for newbies, and when you’ve accomplished this, you’ll perceive how ChatGPT plugins, AI search instruments, and inner firm chatbots actually work.

 

# Wrapping Up

 
Each of those initiatives teaches you one thing important:

Text → Image → Voice → Fine-tuning → Retrieval

If you are simply moving into Gen AI and need to truly construct stuff, not simply play with demos, that is your blueprint. Start from the one which excites you most. And keep in mind, it is okay to interrupt issues. That’s the way you study.
 
 

Kanwal Mehreen Kanwal is a machine studying engineer and a technical author with a profound ardour for information science and the intersection of AI with medication. She co-authored the e-book “Maximizing Productivity with ChatGPT”. As a Google Generation Scholar 2022 for APAC, she champions variety and tutorial excellence. She’s additionally acknowledged as a Teradata Diversity in Tech Scholar, Mitacs Globalink Research Scholar, and Harvard WeCode Scholar. Kanwal is an ardent advocate for change, having based FEMCodes to empower ladies in STEM fields.