Build AI Image Generator in Python | Text to Image with Stable Diffusion

Welcome to AI & Data Skills Shorts by CodeVisium 🚀 In this project you will build a Text-to-Image AI Generator using Python. The application takes a text prompt and generates an AI image using a model like Stable Diffusion. You will learn: How AI image generation works How to call AI APIs using Python How to save generated images How to create a simple web UI 🔹 Step 1: Install Required Libraries Run: pip install requests pillow streamlit Libraries used: requests Used to send API requests. pillow (PIL) Used for handling images. streamlit Used for building a quick web interface. 🔹 Step 2: Create Text Prompt A prompt describes what image you want. Example: prompt = "astronaut riding a horse in space" Better prompts give better images. Examples: futuristic city skyline cyberpunk robot warrior fantasy castle on floating island 🔹 Step 3: Generate Image using API Example Python script: import requests api_url = "https://api-inference.huggingface.co/models/stabilityai/stable-diffusion-2" headers = { "Authorization": "Bearer YOUR_API_KEY" } data = { "inputs": "A futuristic neon city at night" } response = requests.post(api_url, headers=headers, json=data) with open("generated.png", "wb") as f: f.write(response.content) This code: Sends text prompt to AI model Model generates image Image is saved locally 🔹 Step 4: Open Generated Image Using Python: from PIL import Image img = Image.open("generated.png") img.show() This will display the generated AI artwork. 🔹 Step 5: Build Web Interface with Streamlit Create file app.py import streamlit as st import requests st.title("AI Image Generator") prompt = st.text_input("Enter prompt") if st.button("Generate Image"): response = requests.post( api_url, headers=headers, json={"inputs": prompt} ) st.image(response.content) Run app: streamlit run app.py Now you have a simple AI image generator web app. 📂 Tools Used in This Project Py