GenAI Creator: Hands-On Practical Guide

Course Description:

---

Course Summary: GenAI Creator: Hands-On Practical Guide

Unlock the power of Generative AI and build your own smart content assistant from scratch — no prior AI experience needed! In this 4-week, hands-on course designed for you, you’ll dive deep into the world of text, image, and audio generation using free, open-source models like GPT-Neo and Stable Diffusion.

Learn to craft effective prompts, fine-tune models for niche tasks, and deploy your AI-powered application with an interactive web interface. Alongside practical coding sessions, gain valuable industry insights, ethical perspectives, and career guidance to kickstart your journey in the booming field of Generative AI.

By the end, you’ll have a fully functional project - be ready to showcase or launch.

What you get:

• Expert-led hands-on sessions with real Gen AI tools

• Step-by-step project building and deployment

• Access to all free/open-source resources

• Insights into ethical AI and industry trends

Prerequisites:

• Basic to intermediate knowledge of Python programming

• Curiosity and eagerness to learn AI concepts and experiment with generative models

• Access to a laptop or desktop with internet connectivity

Duration: 4 weeks | 20 hours total | Weekend sessions
Price: ₹6000

Step into the future of AI creativity. Build. Experiment. Innovate. Enroll now!

Course Curriculum:

🔹 WEEK 1: Foundations of GenAI & Text Generation

• Introduction to Generative AI (text, image, audio)

• Real-world GenAI applications and use cases

• Setting up Python, Jupyter/Colab, and Hugging Face Transformers

• Text generation with GPT-Neo/GPT-J

• Prompt engineering techniques (zero-shot, few-shot, temperature, top-p)

• Building simple text-based tools (e.g., blog assistant)

• Ethics in text generation (bias, hallucination, safety)

---

🔹 WEEK 2: Image Generation with Stable Diffusion

• Basics of diffusion models and how they generate images

• Installing and running Stable Diffusion via AUTOMATIC1111 or Hugging Face Diffusers

• Text-to-image generation with prompt crafting

• Use of styles, lighting, and object control in image generation

• Image-to-image translation and inpainting

• Ethics in image gen (deepfakes, copyright, misinformation)

• Project: Create a mascot, logo, or poster using AI

---

🔹 WEEK 3: Audio Generation & API Integration

• Overview of Text-to-Speech (TTS) models like Bark and Tortoise TTS

• Setting up and running TTS models in Google Colab

• Creating AI voiceovers from generated text

• Combining text + image + audio for multimodal projects

• Basics of FastAPI for serving GenAI models as APIs

• Building and testing REST APIs for text and audio models

• Ethics in AI audio (consent, voice cloning concerns)

---

🔹 WEEK 4: Full Project Build & Industry Insights

• Project planning and tool integration

• Building a multimodal application using Gradio (text/image/audio)

• GitHub usage and version control best practices

• Hosting on Hugging Face Spaces (free deployment)

• Final project presentation

• Career paths in Generative AI (LLM Developer, Prompt Engineer, AI Creator)

• Industry trends and ethical responsibilities