Search papers, labs, and topics across Lattice.
Boogu-Image-0.1 is an open-source unified multimodal model family that includes variants for text-to-image generation, editing, and bilingual text rendering, achieving competitive performance against both open-source and closed-source systems. The model's enhancements stem from targeted improvements in understanding, data quality, and training pipelines, allowing it to perform effectively even with limited compute resources. Evaluations indicate that Boogu-Image-0.1 not only matches but often surpasses existing models on standard benchmarks, achieving results close to leading closed-source alternatives with a significantly lower training cost.
Achieving state-of-the-art multimodal performance with only 208.62 million unique images and a theoretical training cost of just $400K challenges the notion that larger datasets and budgets are always necessary for success.
We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual (Chinese-English) text rendering. Closed-source multimodal systems like Nano-Banana-Pro and GPT-Image-2 achieve strong performance through system-level integration rather than a single model, yet their internal practices remain largely undisclosed. In this work, we demonstrate that targeted improvements in model understanding, data quality, and training pipelines, coupled with agentic inference-time scaling, can substantially enhance generation and editing performance even under highly constrained compute budgets. Comprehensive evaluations show that Boogu-Image-0.1 consistently matches or surpasses other open-source models across standard benchmarks, and achieves results approaching leading closed-source systems. Notably, this is accomplished with only 208.62 million unique images. The base model's theoretical training cost is only approximately \$400K. We share practical discussions that we believe are valuable to the broader research community, and release weights, code, and recipes under Apache 2.0 to advance the open ecosystem for unified multimodal understanding and generation. Our code is available here: https://github.com/Boogu-Project/Boogu-Image.
