Search papers, labs, and topics across Lattice.
The paper introduces "oboro," a text-to-image generation model trained from scratch on a limited, copyright-cleared dataset, aimed at addressing labor shortages in the Japanese anime industry. Oboro employs a Flow-based Diffusion Transformer architecture with Multi-Modal Hybrid (MMH) attention to achieve high-quality image generation despite data constraints. The authors demonstrate the feasibility of training a commercially-viable, open-source image generation model within Japan, releasing both the model weights and inference code.
A new text-to-image model, "oboro," proves that high-quality generative AI can be built from scratch using limited, copyright-cleared data, opening doors for specialized applications and ethical AI development.
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.