🔶 We generated 1000 different synthetic face images that constitute the SDFD (Stable Diffusion Face-image Dataset). SDFD captures a broad spectrum of facial diversity encompassing not only demographics and biometrics but also non-permanent traits like make-up, hairstyle, and accessories.
🔶 We created various prompts that guide a state-of-the-art text-to-image model (Stable Diffusion 2.1)) in generating a comprehensive dataset of high-quality realistic images and can be used as an evaluation set in face analysis systems.
🔷 File finalPrompts.csv contains all the corresponding prompts that we used to get the SDFD dataset.
🔷 File finalPromptsSeparated.csv contains the same prompts with finalPrompts.csv but the attributes are comma separated.
❗ The first step is to install the Diffusers. We recommend installing them in a virtual environment from Conda. For more information see the official documentation .
➡️ In order to produce images run the SDFD.py file:
python3 SDFD.py
TBA