DiffuGen: Adaptable Approach for Generating Labeled Image Datasets using Stable Diffusion Models

TL;DR

DiffuGen is an adaptable method that uses stable diffusion models with prompt templating and textual inversion to efficiently generate high-quality labeled image datasets for computer vision tasks.

Contribution

We introduce DiffuGen, a novel approach combining diffusion models with prompt templating and textual inversion for versatile dataset label generation.

Findings

Efficient generation of labeled datasets with high quality.

Versatile labeling through unsupervised and supervised techniques.

Enhanced diffusion model capabilities via textual inversion.

Abstract

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To address these challenges associated with dataset generation, we introduce "DiffuGen," a simple and adaptable approach that harnesses the power of stable diffusion models to create labeled image datasets efficiently. By leveraging stable diffusion models, our approach not only ensures the quality of generated datasets but also provides a versatile solution for label generation. In this paper, we present the methodology behind DiffuGen, which combines the capabilities of diffusion models with two distinct labeling techniques: unsupervised and supervised. Distinctively, DiffuGen employs prompt templating for adaptable image generation and textual inversion to enhance diffusion model capabilities.