Diffusion model concept in Prompt Engineering / GenAI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a diffusion model in simple terms?

A diffusion model is a type of AI that learns to create data by slowly adding noise to it and then learning how to remove that noise step-by-step to get back the original data.

beginner

Why do diffusion models add noise to data during training?

They add noise to teach the model how to reverse the process, so it can start from random noise and create new, realistic data by removing noise gradually.

beginner

What is the main goal of the reverse diffusion process?

The goal is to start with pure noise and step-by-step remove noise to generate new data that looks like the original training examples.

beginner

How is a diffusion model similar to making a blurry photo clear again?

Just like making a blurry photo clear by removing blur step-by-step, a diffusion model removes noise step-by-step to create clear, realistic data.

beginner

Name one popular use of diffusion models in AI today.

Diffusion models are popular for generating images, like creating art or photos from text descriptions.

What does a diffusion model learn to do?

A Remove noise from data step-by-step

B Add noise to data only

C Classify images into categories

D Translate text from one language to another

Diffusion models learn to remove noise gradually to generate new data.

Why is noise added during training in diffusion models?

A To make data harder to understand

B To speed up training

C To reduce the size of the data

D To teach the model how to reverse noise addition

Noise is added so the model learns how to remove it step-by-step.

What is the starting point for generating new data in a diffusion model?

A Clean original data

B Random noise

C A labeled dataset

D A trained classifier

Generation starts from random noise that the model cleans up.

Which of these is a common application of diffusion models?

A Predicting stock prices

B Sorting numbers

C Image generation from text

D Detecting spam emails

Diffusion models are widely used to generate images from text prompts.

How does the reverse diffusion process work?

A By removing noise step-by-step

B By adding more noise each step

C By copying data exactly

D By randomly guessing data

Reverse diffusion removes noise gradually to create new data.

Explain in your own words how a diffusion model generates new data.

Think about how the model learns by reversing noise addition.

Describe a real-life analogy that helps you understand the diffusion model concept.

Imagine cleaning a dirty window or fixing a blurry picture.

Practice

1. What is the main idea behind a diffusion model in AI?

easy

A. It sorts data into categories using labels.

B. It directly copies existing data without changes.

C. It creates data by gradually removing noise from random input.

D. It compresses data to save space.

Solution

1. Step 1: Understand diffusion model purpose

   Diffusion models generate new data by starting with noise and removing it step-by-step.

2. Step 2: Compare options to this idea

   Only It creates data by gradually removing noise from random input. describes this gradual noise removal process correctly.

3. Final Answer:

   It creates data by gradually removing noise from random input. -> Option C

4. Quick Check:

   Diffusion model = gradual noise removal [OK]

Hint: Diffusion means removing noise slowly to create data [OK]

Common Mistakes:

• Thinking diffusion copies data exactly
• Confusing diffusion with classification
• Believing diffusion compresses data

2. Which of the following best describes the training step of a diffusion model?

easy

A. Adding noise to data and training the model to remove it.

B. Removing noise from data and training the model to add it.

C. Training the model to classify noisy images.

D. Training the model to compress data efficiently.

Solution

1. Step 1: Recall diffusion model training

   Diffusion models learn by adding noise to clean data and training to reverse this process.

2. Step 2: Match options to training process

   Adding noise to data and training the model to remove it. correctly states adding noise then learning to remove it.

3. Final Answer:

   Adding noise to data and training the model to remove it. -> Option A

4. Quick Check:

   Training = add noise, learn to clean [OK]

Hint: Training adds noise, model learns to clean it [OK]

Common Mistakes:

• Confusing noise addition and removal steps
• Thinking model trains to add noise
• Mixing training with classification tasks

3. Consider this simplified pseudocode for a diffusion model step:

noise_level = 0.5
noisy_data = original_data + noise_level * random_noise
cleaned_data = model.predict(noisy_data)

What does cleaned_data represent here?

medium

A. The model's guess of the data with noise removed.

B. The noisy data after adding random noise.

C. The original data before noise was added.

D. Random noise generated by the model.

Solution

1. Step 1: Analyze code variables

   noisy_data is original data plus noise; cleaned_data is model output from noisy input.

2. Step 2: Understand model role

   The model tries to remove noise, so cleaned_data is the model's cleaned guess.

3. Final Answer:

   The model's guess of the data with noise removed. -> Option A

4. Quick Check:

   cleaned_data = model's denoised output [OK]

Hint: Model output after noise removal is cleaned data [OK]

Common Mistakes:

• Confusing noisy_data with cleaned_data
• Thinking cleaned_data is original data
• Assuming cleaned_data is noise

4. A diffusion model training code snippet has this error:

for step in range(1, 11):
    noisy = add_noise(data, step)
    loss = model.train(noisy, data)
    print('Loss:', loss)

The loss does not decrease as expected. What is the likely mistake?

medium

A. The loop range should start at 0, not 1.

B. Loss printing should be outside the loop.

C. The model should train on noisy data only, not original data.

D. Noise is added with increasing step, but the model expects decreasing noise.

Solution

1. Step 1: Understand noise schedule in diffusion

   Diffusion models add noise in training but expect noise level to decrease during denoising steps.

2. Step 2: Identify mismatch in noise and training

   Increasing noise each step conflicts with model learning to remove noise progressively.

3. Final Answer:

   Noise is added with increasing step, but the model expects decreasing noise. -> Option D

4. Quick Check:

   Noise schedule must match model expectation [OK]

Hint: Noise should decrease during denoising, not increase [OK]

Common Mistakes:

• Ignoring noise schedule direction
• Changing loop range without reason
• Misplacing loss print statement

5. You want to generate a clear image from random noise using a diffusion model. Which sequence of steps correctly describes this process?

hard

A. Start with noise, add more noise, then output noisy image.

B. Start with noise, apply model repeatedly to remove noise, get clear image.

C. Start with clear image, add noise repeatedly, then output noisy image.

D. Start with clear image, apply model to add noise, get noisy image.

Solution

1. Step 1: Recall diffusion model generation

   Generation starts from random noise and removes noise step-by-step to create clear data.

2. Step 2: Match options to generation steps

   Only Start with noise, apply model repeatedly to remove noise, get clear image. describes starting with noise and removing it repeatedly to get a clear image.

3. Final Answer:

   Start with noise, apply model repeatedly to remove noise, get clear image. -> Option B

4. Quick Check:

   Generation = noise to clear image [OK]

Hint: Generate by removing noise stepwise from random input [OK]

Common Mistakes:

• Thinking generation adds noise instead of removing
• Confusing training noise addition with generation
• Starting generation from clear image