Generative AI

Generative AI creates new content — text, images, audio, video, code — by learning patterns from training data.

What Is Generative AI?

Unlike traditional AI that classifies or predicts, generative AI creates new content. It uses models like LLMs, Diffusion Models, and GANs.

Large Language Models

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "gpt2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "Once upon a time in a land of AI"
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(
    inputs.input_ids,
    max_length=100,
    temperature=0.8,
    do_sample=True,
    top_p=0.9
)

text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(text)

Prompt Engineering

Good prompts produce better AI outputs. Use clear instructions, context, and examples.

# Bad prompt
prompt1 = "Write code"

# Good prompt
prompt2 = '''Write a Python function that:
1. Takes a list of numbers as input
2. Returns the average of those numbers
3. Includes error handling for empty lists
4. Has type hints and docstring

Provide the complete code with comments.'''

Image Generation

from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

image = pipe(
    "A beautiful sunset over mountains, digital art",
    num_inference_steps=30,
    guidance_scale=7.5
).images[0]

image.save("sunset.png")

Build a Simple AI App

from flask import Flask, request, jsonify
from transformers import pipeline

app = Flask(__name__)
summarizer = pipeline("summarization")

@app.route('/summarize', methods=['POST'])
def summarize():
    data = request.json
    text = data.get('text', '')
    result = summarizer(text, max_length=100, min_length=30)
    return jsonify({'summary': result[0]['summary_text']})

if __name__ == '__main__':
    app.run(debug=True)

Summary

You learned generative AI including LLMs, prompt engineering, image generation, and building AI applications. Next, we'll build complete AI projects.