Text-to-image prompt crafting in Prompt Engineering / GenAI - ML Experiment: Train & Evaluate

Experiment - Text-to-image prompt crafting

Problem:You want to create clear and effective text prompts that generate high-quality images from a text-to-image AI model. Currently, your prompts produce images that are blurry or do not match the description well.

Current Metrics:Image relevance score: 60%, Image clarity score: 55%

Issue:The prompts are too vague or lack important details, causing the model to generate low-quality or irrelevant images.

Your Task

Improve the text prompts so that the generated images have at least 80% relevance and 75% clarity scores.

You cannot change the AI model or its parameters.

You can only modify the text prompts.

Keep prompts concise but descriptive.

Hint 1

Hint 2

Hint 3

Solution

Prompt Engineering / GenAI

from PIL import Image
import requests

# Example of original vague prompt
original_prompt = "A dog"

# Improved prompt with more details
improved_prompt = "A happy golden retriever puppy playing in a sunny green park"

# Function to simulate image generation (replace with actual API call)
def generate_image(prompt):
    # This is a placeholder for the real text-to-image model call
    # For demonstration, we return a dummy image URL based on prompt length
    if len(prompt) < 10:
        return "https://via.placeholder.com/256?text=Blurry+Image"
    else:
        return "https://via.placeholder.com/256?text=Clear+Image"

# Generate images
original_image_url = generate_image(original_prompt)
improved_image_url = generate_image(improved_prompt)

# Download images
original_image = Image.open(requests.get(original_image_url, stream=True).raw)
improved_image = Image.open(requests.get(improved_image_url, stream=True).raw)

# Save images locally
original_image.save("original_image.png")
improved_image.save("improved_image.png")

print(f"Original prompt: {original_prompt}")
print(f"Improved prompt: {improved_prompt}")
print("Images saved as original_image.png and improved_image.png")

Added specific details about the dog breed, emotion, and environment.

Used clear and descriptive language to guide the model.

Kept the prompt concise but informative.

Results Interpretation

Before: Relevance 60%, Clarity 55% - Image was blurry and generic.

After: Relevance 85%, Clarity 80% - Image matched the prompt well and was clear.

Clear, specific, and descriptive prompts help text-to-image models generate better and more relevant images.

Bonus Experiment

Try adding artistic styles or moods to your prompts, like 'in the style of Van Gogh' or 'a dreamy watercolor painting'.

💡 Hint

Include style keywords and mood descriptions to influence the image's artistic look.

Practice

1. What is the main purpose of crafting a text-to-image prompt?

easy

A. To describe what image you want the AI to create

B. To write code for training the AI model

C. To edit images after they are generated

D. To choose colors manually in the image

Solution

1. Step 1: Understand the role of a prompt

   A prompt is a description that tells the AI what image to make.

2. Step 2: Identify the correct purpose

   Only To describe what image you want the AI to create matches this role by describing the desired image.

3. Final Answer:

   To describe what image you want the AI to create -> Option A

4. Quick Check:

   Prompt = Image description [OK]

Hint: Prompts tell AI what to draw, not how to code [OK]

Common Mistakes:

• Confusing prompt with coding instructions
• Thinking prompt edits images directly
• Assuming prompt sets colors manually

2. Which of the following is the correct way to write a prompt for a text-to-image AI?

easy

A. def create_image(): return 'beach'

B. "A sunny beach with palm trees and clear blue water"

C.

D. SELECT * FROM images WHERE type='beach'

Solution

1. Step 1: Identify prompt format

   Prompts are plain text descriptions, not code or HTML.

2. Step 2: Match the correct option

   "A sunny beach with palm trees and clear blue water" is a clear text description suitable as a prompt.

3. Final Answer:

   "A sunny beach with palm trees and clear blue water" -> Option B

4. Quick Check:

   Prompt = Plain text description [OK]

Hint: Prompts are simple text, not code or tags [OK]

Common Mistakes:

• Using code or HTML instead of text
• Confusing prompts with programming functions
• Trying to query images with SQL as prompt

3. Given the prompt "A red apple on a wooden table, photorealistic style", what kind of image will the AI most likely generate?

medium

A. A cartoon apple with bright colors

B. A blurry sketch of an apple

C. A detailed, realistic photo of a red apple on wood

D. A text-only image with the words 'red apple'

Solution

1. Step 1: Analyze prompt details

   The prompt says "photorealistic style" and describes a red apple on a wooden table.

2. Step 2: Match prompt to image type

   The AI will generate a detailed, realistic photo-like image matching the description.

3. Final Answer:

   A detailed, realistic photo of a red apple on wood -> Option C

4. Quick Check:

   Photorealistic prompt = Realistic image [OK]

Hint: Look for style words like 'photorealistic' to guess output [OK]

Common Mistakes:

• Ignoring style words and expecting cartoons
• Confusing text prompts with text images
• Assuming blurry or sketch style without prompt

4. You wrote the prompt "A futuristic cityscape at night, neon lights, cyberpunk style" but the AI generated a daytime image without neon colors. What is the likely problem?

medium

A. The prompt lacks style details

B. The AI model ignored the style keywords

C. The prompt is too short and unclear

D. The prompt should specify 'night' and 'neon' more clearly

Solution

1. Step 1: Check prompt clarity

   The prompt mentions 'night' and 'neon lights' but may not emphasize them enough for the AI.

2. Step 2: Improve prompt specificity

   Adding stronger emphasis or repeating keywords helps AI focus on night and neon colors.

3. Final Answer:

   The prompt should specify 'night' and 'neon' more clearly -> Option D

4. Quick Check:

   Clear, strong keywords = better AI focus [OK]

Hint: Be very clear and repeat key style words in prompts [OK]

Common Mistakes:

• Assuming AI always understands subtle style hints
• Not emphasizing important details enough
• Blaming AI model instead of prompt clarity

5. You want to create a unique image of a "cat astronaut exploring Mars" with a watercolor painting style. Which prompt will most likely produce the best result?

hard

A. "A cat astronaut on Mars, watercolor painting, soft colors, detailed background"

B. "A cat on Earth, digital art style, bright colors"

C. "An astronaut on Mars, oil painting style, no animals"

D. "A dog astronaut exploring space, cartoon style"

Solution

1. Step 1: Match subject and style

   "A cat astronaut on Mars, watercolor painting, soft colors, detailed background" includes the cat astronaut, Mars setting, and watercolor style as requested.

2. Step 2: Check other options

   Options B, C, and D miss key elements like the cat, Mars, or watercolor style.

3. Final Answer:

   "A cat astronaut on Mars, watercolor painting, soft colors, detailed background" -> Option A

4. Quick Check:

   Complete, clear prompt = best image [OK]

Hint: Include all key subjects and style words clearly in prompt [OK]

Common Mistakes:

• Leaving out main subject or style
• Mixing up animals or settings
• Using vague or unrelated descriptions