oboro: Text-to-Image Synthesis on Limited Data using Flow-based Diffusion Transformer with MMH Attention

TL;DR

This paper introduces 'oboro,' a novel Japanese-developed image generation model capable of producing high-quality images from limited data, utilizing a flow-based diffusion transformer with MMH attention, and is openly available for commercial use.

Contribution

The paper presents 'oboro,' the first open-source Japanese image generation model trained from scratch on limited data with a unique architecture and publicly released weights.

Findings

High-quality images generated from limited datasets

Open-source model available for commercial use

First Japanese-developed image generation AI

Abstract

This project was conducted as a 2nd-term adopted project of the "Post-5G Information and Communication System Infrastructure Enhancement R&D Project Development of Competitive Generative AI Foundation Models (GENIAC)," a business of the Ministry of Economy, Trade and Industry (METI) and the New Energy and Industrial Technology Development Organization (NEDO). To address challenges such as labor shortages in Japan's anime production industry, this project aims to develop an image generation model from scratch. This report details the technical specifications of the developed image generation model, "oboro:." We have developed "oboro:," a new image generation model built from scratch, using only copyright-cleared images for training. A key characteristic is its architecture, designed to generate high-quality images even from limited datasets. The foundation model weights and inference code are publicly available alongside this report. This project marks the first release of an open-source, commercially-oriented image generation AI fully developed in Japan. AiHUB originated from the OSS community; by maintaining transparency in our development process, we aim to contribute to Japan's AI researcher and engineer community and promote the domestic AI development ecosystem.