MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

arXiv:2404.05674v1 Announce Type: new
Abstract: In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly evolve, the demand for robust image-to-image translation grows. Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text prompt information to …

abstract adapter arxiv capabilities cs.cv demand foundational free image image generation image-to-image image-to-image translation language large language llm multimodal paper personalized robust text text-to-image training translation type zero-shot