Being-Creative-with-AI/C2/Prompting-for-Images/English

From Script | Spoken-Tutorial
Revision as of 13:29, 18 May 2026 by Misbah (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
Visual Cue Narration
Title Slide: “Prompting for Images – Basics” Welcome to this Spoken Tutorial on Prompting for Images.
Learning Objectives Slide In this tutorial, we will learn
  • How to write a good prompt to generate an image.
  • To focus on the four key elements of a good prompt.
  • Simple patterns to build prompts faster
Disclaimer Content Slide As Al tools constantly evolve, if you are unable to locate any icon or encounter difficulty at any step, you may use any conversational Al Chatbot for guidance.
System Requirement slide * To begin, all you need is a laptop or desktop and an internet connection.
  • You can use any image generation tool of your choice.
  • No special setup is required.
Pre-requisite

For the Pre-requisites of this tutorial, visit the website shown on your screen

http://EduPyramids.org

To follow this tutorial, you should know what a prompt is.

For the Pre-requisites of this tutorial, visit the website shown on your screen

Code Files

The following code file is required to practice this tutorial:

Prompting-for-Images.txt

This file is provided in the Code Files link on this tutorial page.

Please download and extract the file.

The following code file is required to practice this tutorial.

This file is provided in the Code Files link of this tutorial page

Please download and extract the file

Two people having different idea Now, think why do two people get different images for the same idea?
AI prompts This happens because prompts shape how the AI imagines a scene.
AI prompts images When the prompt changes, the image also changes.
Prompts So, to guide the AI clearly, we need strong prompts.
“4 Elements of a Good Prompt” Let’s look at the four key elements of a strong prompt for a good image.

They are Subject, Style, Details and Extras

Element 1 - Subject We will start with the first element, subject.
Subject Subject tells the AI who or what should be created as an image?
Text slide: “Popular Tools” You can use tools like, DALL·E, Midjourney, Gemini and Stable Diffusion
Continue showing the previous slide “Popular Tools” For this tutorial, I will use Gemini
Pause and type Open a web browser and type this
Screenshot: prompt box All these tools have a prompt box where you type the prompt.

Show Create Image option

Let's begin.

Go to the bottom of the screen.

Click on the option Create Image.

Typing in prompt box: “A dog” Now in the prompt bar, I will first type a very simple prompt.

A dog and then click on Generate

Result Look at the result.
Example: “A dog” → image of a dog The result may look very general. A dog is the subject.
Prompt improvement Now, let us improve this prompt step by step.
Prompt edited to: “A golden retriever puppy” I will change the prompt to a golden retriever puppy and click on Generate.
More specific image appears Observe how the image becomes clearer.
Guidance to AI Next, let us guide AI how the image should look.
Second element - Style So now I will add the second element, style.
Style examples:Cartoon, painting, or realistic With Style you can decide the look you want.

Cartoon, painting, or realistic.

Type the prompt: “Golden retriever puppy, cartoon style” I will type: “Golden retriever puppy, cartoon style” and click on Generate.
Style changes the visual character of image Adding style gives a distinct visual character to your image.
Compare previous image and this image Notice how the visual style has changed.
Third element - Details Now, let us build the scene further by adding the third element, details.
Details examples: location, lighting, mood In Details you will add setting, lighting, or mood for richer results.
Type the prompt and click on generate Let me now type ‘A golden retriever puppy in a park on a sunny day.’
Compare previous image and this image See how the image feels more complete now.
Fourth element - Extras Let us now add the fourth element, Extras.
Extras slide: composition, camera angle Extras are information about the shot or camera angles.
Type the prompt and click on generate I will now type: close-up shot, dramatic lighting
Compare previous image and this image Observe how the mood of the image changes.
Function of Extras Extras control composition and emotion.
Prompt evolution graphic: Dog → Golden retriever → Style → Details → Extras See how a simple prompt evolved into something powerful.
Text slide: “Useful Prompt Patterns” We can also use simple patterns to build prompts faster.
Patterns of prompts For example, let us try this first pattern that is subject, setting, and style.
Example prompt: “A robot, in a library, in watercolor style” Example: “A robot, in a library, in watercolor style.
click generated image Run the prompt.
Output shown This pattern quickly gives a clear image.
Second pattern Now let us try the second pattern.

Subject, doing action, and style or details

Example: “A chef, juggling vegetables, comic book style” For example: “A chef, juggling vegetables, comic book style
click generated image Run the prompt.
Dynamic image shown With this pattern, the image looks vibrant. .
Image collage: AI-generated art styles Image generation tools can create amazing visuals from text prompts.
Simple prompt vs. detailed prompt side-by-side The effectiveness of your prompt decides how good your image will be.
Mistakes to avoid while writing a prompt Let us look at some common mistakes to avoid while writing a prompt.
Vague prompt example: “A nice picture” + poor output For example when I type “A nice picture” and click on Generate.
Random images appear It gives unclear and random results.
Reasons The reason for this is that the prompt is too vague.
prompt “A girl playing" and generate image Next let me type a promptA girl playing".

It may not generate the image I want.

Missing words in prompts This happens because the key details like style or setting are missing.

AI does not know her location, the time of the day, or the style to use

A figure or person or whatever, with things, maybe sitting maybe not, lights or objects around, some mood, colorful artistic digital feel or something like that. A long unorganised prompt, may give unclear images.
Summary Slide Let us summarize what we learnt.
  • Strong prompts guide the AI clearly.
  • Good prompts have subject, style, details, and extras.
  • Prompt patterns make writing easier.
  • Avoid vague and unstructured prompts.
Assignment Slide
  • Write one image prompt using Pattern 1
  • The structure is: “A [subject], in [setting], in [style]”
  • Next, write one image prompt using Pattern 2
  • The structure is: “A [subject], doing [action], [style or details]”
  • Try out your prompts in any image generation tool and observe the outputs
Here is an assignment for you.
Acknowledgement slide Thank you for joining.
Closing slide

This Spoken Tutorial is brought to you by EduPyramids Educational Services Private Limited, SINE, IIT Bombay.

Contributors and Content Editors

Bellatony911, Misbah