Inpainting and outpainting in Prompt Engineering / GenAI - Model Pipeline Trace

Model Pipeline - Inpainting and outpainting

This pipeline shows how a generative AI model fills missing parts inside an image (inpainting) or extends the image beyond its original borders (outpainting). It learns from existing image data to create realistic new pixels.

Data Flow - 5 Stages

1Input Image

1 image x 256 x 256 x 3 channels→Original image with missing or extended areas marked→1 image x 256 x 256 x 3 channels

A photo of a landscape with a blank square in the center (inpainting) or blank space on the right edge (outpainting)

↓

2Mask Application

1 image x 256 x 256 x 3 channels→Apply mask to indicate missing or new areas to fill→1 image x 256 x 256 x 4 channels (RGB + mask)

The image now includes a mask channel showing which pixels to generate

↓

3Feature Extraction

1 image x 256 x 256 x 4 channels→Use convolutional layers to extract image features→1 tensor x 64 x 64 x 256 features

Features capture edges, colors, and textures from the visible parts

↓

4Generative Model

1 tensor x 64 x 64 x 256 features→Use a U-Net or transformer-based model to generate missing pixels→1 image x 256 x 256 x 3 channels

Model predicts realistic pixels for masked or extended areas

↓

5Output Image

1 image x 256 x 256 x 3 channels→Combine generated pixels with original image→1 image x 256 x 256 x 3 channels

Completed image with missing parts filled or extended beyond original edges

Training Trace - Epoch by Epoch

Loss
1.2 |*****
1.0 |****
0.8 |***
0.6 |**
0.4 |*
0.2 | 
    +----------------
     1 5 10 15 20 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning to fill missing areas roughly
5	0.8	0.65	Generated pixels become more coherent with surroundings
10	0.5	0.80	Model produces realistic textures and colors
15	0.35	0.88	Fine details and edges are well reconstructed
20	0.25	0.92	Model converges with high-quality inpainting and outpainting

Prediction Trace - 4 Layers

Layer 1: Input Image with Mask

Layer 2: Feature Extraction

Layer 3: Generative Model (U-Net or Transformer)

Layer 4: Combine Output

Model Quiz - 3 Questions

What does the mask channel tell the model during inpainting?

A Which pixels to generate or fill

B The color of the missing pixels

C The size of the image

D The brightness of the image

Key Insight

Inpainting and outpainting models learn to fill or extend images by understanding visible patterns and textures. Masks guide where to generate pixels, and training improves the model's ability to create realistic, seamless images.

Practice

1. What is the main difference between inpainting and outpainting in image editing?

easy

A. Both inpainting and outpainting only remove unwanted parts from images.

B. Inpainting adds new areas around an image, outpainting removes parts inside it.

C. Inpainting fills missing parts inside an image, outpainting adds new areas around it.

D. Inpainting and outpainting are the same process with different names.

Solution

1. Step 1: Understand inpainting

   Inpainting is used to fill missing or unwanted parts inside an image, like fixing scratches or holes.

2. Step 2: Understand outpainting

   Outpainting extends the image by adding new content around the edges, making the image bigger.

3. Final Answer:

   Inpainting fills missing parts inside an image, outpainting adds new areas around it. -> Option C

4. Quick Check:

   Inpainting = fill inside, Outpainting = add outside [OK]

Hint: Inpainting fixes inside; outpainting grows outside [OK]

Common Mistakes:

• Confusing inpainting with outpainting
• Thinking both remove parts only
• Believing they are identical

2. Which of the following is the correct way to describe the input for an inpainting model?

easy

A. Only the new areas to add around the image.

B. An image with missing or masked areas to fill.

C. A complete image with no missing parts.

D. A text description of the image content.

Solution

1. Step 1: Identify input for inpainting

   Inpainting models require an image with missing or masked parts that need filling.

2. Step 2: Check other options

   Complete images or text descriptions are not direct inputs for inpainting; new areas relate to outpainting.

3. Final Answer:

   An image with missing or masked areas to fill. -> Option B

4. Quick Check:

   Inpainting input = image with holes [OK]

Hint: Inpainting needs holes in image input [OK]

Common Mistakes:

• Choosing complete images without masks
• Confusing input with outpainting requirements
• Selecting text descriptions as input

3. Given this Python pseudocode for outpainting, what will be the shape of the output image if the input image is 256x256 and the model adds 64 pixels on each side?

input_image = load_image('photo.png')  # shape (256, 256)
output_image = outpaint_model(input_image, border=64)
print(output_image.shape)

medium

A. (256, 256)

B. (192, 192)

C. (320, 320)

D. (384, 384)

Solution

1. Step 1: Calculate added pixels

   The model adds 64 pixels on each side, so total added width = 64 * 2 = 128 pixels.

2. Step 2: Calculate new image size

   Original size 256 + 128 = 384 pixels. This is 256 + 64 + 64 = 384, since 64 pixels on each side means adding 64 left and 64 right.

3. Step 3: Re-check options

   (384, 384) matches calculation. (320, 320) is 256 + 64, adding only one side.

4. Final Answer:

   (384, 384) -> Option D

5. Quick Check:

   256 + 64*2 = 384 [OK]

Hint: Add border pixels twice (both sides) to original size [OK]

Common Mistakes:

• Adding border only once
• Confusing inpainting with outpainting size change
• Ignoring both width and height increase

4. You run an inpainting model but the output image still has visible holes where the mask was applied. What is the most likely cause?

medium

A. The mask was not correctly applied to the input image.

B. The model was trained only for outpainting, not inpainting.

C. The input image was too large for the model to process.

D. The output image format does not support transparency.

Solution

1. Step 1: Check mask application

   If holes remain, the mask likely was not properly set, so the model didn't know where to fill.

2. Step 2: Evaluate other options

   Model type mismatch or image size issues usually cause errors or poor quality, not visible holes. Output format affects display but not hole filling.

3. Final Answer:

   The mask was not correctly applied to the input image. -> Option A

4. Quick Check:

   Mask error = holes remain [OK]

Hint: Check mask covers missing parts fully [OK]

Common Mistakes:

• Ignoring mask correctness
• Blaming model type without checking input
• Assuming output format causes holes

5. You want to create a larger scenic image by extending the edges of a 512x512 photo using outpainting. You also want to remove a small unwanted object inside the photo using inpainting. Which approach correctly combines both tasks?

hard

A. First apply inpainting on the original image to remove the object, then apply outpainting to extend the image edges.

B. Apply outpainting first to extend the image, then apply inpainting on the extended edges to remove the object.

C. Only use outpainting because it can both remove objects and extend images.

D. Only use inpainting because it can extend images and remove objects.

Solution

1. Step 1: Remove unwanted object first

   Inpainting fixes inside the image, so remove the object before changing image size.

2. Step 2: Extend image after cleanup

   Outpainting adds new areas around the cleaned image, so apply it after inpainting.

3. Step 3: Evaluate other options

   Outpainting cannot remove inside objects; inpainting cannot add new edges. Order matters for best results.

4. Final Answer:

   First apply inpainting on the original image to remove the object, then apply outpainting to extend the image edges. -> Option A

5. Quick Check:

   Fix inside first, then grow outside [OK]

Hint: Clean inside first (inpainting), then extend outside (outpainting) [OK]

Common Mistakes:

• Applying outpainting before inpainting
• Thinking one method does both tasks
• Ignoring task order importance