Show-o: One Single Transformer To Unify Multimodal Understanding And Generation

Xie Jinheng, Mao Weijia, Bai Zechen, Zhang David Junhao, Wang Weihao, Lin Kevin Qinghong, Gu Yuchao, Chen Zhijie, Yang Zhenheng, Shou Mike Zheng. Arxiv 2024

[Paper] [Code]    
GPT Has Code Language Modeling Merging Model Architecture Multimodal Models Pretraining Methods Reinforcement Learning Transformer

We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model. Code and models are released at https://github.com/showlab/Show-o.

Similar Work