MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

Autor:	Bellagente, Marco, Brack, Manuel, Teufel, Hannah, Friedrich, Felix, Deiseroth, Björn, Eichenberg, Constantin, Dai, Andrew, Baldock, Robert, Nanda, Souradeep, Oostermeijer, Koen, Cruz-Salinas, Andres Felipe, Schramowski, Patrick, Kersting, Kristian, Weinbach, Samuel
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult. To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages. MutliFusion leverages pre-trained models and aligns them for integration into a cohesive system, thereby avoiding the need for extensive training from scratch. Our experimental results demonstrate the efficient transfer of capabilities from individual modules to the downstream model. Specifically, the fusion of all independent components allows the image generation module to utilize multilingual, interleaved multimodal inputs despite being trained solely on monomodal data in a single language. Comment: Proceedings of Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems (NeurIPS)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.15296 Zobrazit plný text záznamu View this record from Arxiv