Ddpm Fake Icons

🚀 Unconditional icon generation using DDPM Diffusion

This project focuses on unconditional icon generation using DDPM Diffusion, offering a new approach to icon creation.

🚀 Quick Start

📦 Installation

To use this project in Google Colab, you need to install the necessary packages first. Run the following command:

!python3 -m pip install diffusers==0.21.* accelerate

💻 Usage Examples

Basic Usage

You can generate images using the DDPM Pipeline with the following code:

from matplotlib import pyplot as plt
from diffusers import DDPMPipeline

ddpm = DDPMPipeline.from_pretrained("mayur7garg/ddpm-fake-icons")
ddpm.to("cuda")

inference_image = ddpm(
    batch_size = 36,
    num_inference_steps = 1000
).images

plt.figure(figsize = (18, 18), dpi = 120)

for i, image in enumerate(inference_image):
    plt.subplot(6, 6, i + 1)
    plt.imshow(image)
    plt.axis(False)
plt.tight_layout()
plt.show()

📚 Documentation

Data set used for training

The data set used for training is Kaggle - Icons-50.

Reference code for training

The reference code for training is Kaggle - Generating Fake Icons using DDPM Diffusion.

Image samples

📄 License

This project is under the MIT license.