Saved in:
Bibliographic Details
Main Authors: Wang, Zhanyu, Wang, Longyue, Zhao, Zhen, Wu, Minghao, Lyu, Chenyang, Li, Huayang, Cai, Deng, Zhou, Luping, Shi, Shuming, Tu, Zhaopeng
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.16511
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913565071376384
author Wang, Zhanyu
Wang, Longyue
Zhao, Zhen
Wu, Minghao
Lyu, Chenyang
Li, Huayang
Cai, Deng
Zhou, Luping
Shi, Shuming
Tu, Zhaopeng
author_facet Wang, Zhanyu
Wang, Longyue
Zhao, Zhen
Wu, Minghao
Lyu, Chenyang
Li, Huayang
Cai, Deng
Zhou, Luping
Shi, Shuming
Tu, Zhaopeng
contents While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation. To fill this gap, we present GPT4Video, a unified multi-model framework that empowers Large Language Models (LLMs) with the capability of both video understanding and generation. Specifically, we develop an instruction-following-based approach integrated with the stable diffusion generative model, which has demonstrated to effectively and securely handle video generation scenarios. GPT4Video offers the following benefits: 1) It exhibits impressive capabilities in both video understanding and generation scenarios. For example, GPT4Video outperforms Valley by 11.8\% on the Video Question Answering task, and surpasses NExt-GPT by 2.3\% on the Text to Video generation task. 2) it endows the LLM/MLLM with video generation capabilities without requiring additional training parameters and can flexibly interface with a wide range of models to perform video generation. 3) it maintains a safe and healthy conversation not only in output-side but also the input side in an end-to-end manner. Qualitative and qualitative experiments demonstrate that GPT4Video holds the potential to function as a effective, safe and Humanoid-like video assistant that can handle both video understanding and generation scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16511
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
Wang, Zhanyu
Wang, Longyue
Zhao, Zhen
Wu, Minghao
Lyu, Chenyang
Li, Huayang
Cai, Deng
Zhou, Luping
Shi, Shuming
Tu, Zhaopeng
Computer Vision and Pattern Recognition
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation. To fill this gap, we present GPT4Video, a unified multi-model framework that empowers Large Language Models (LLMs) with the capability of both video understanding and generation. Specifically, we develop an instruction-following-based approach integrated with the stable diffusion generative model, which has demonstrated to effectively and securely handle video generation scenarios. GPT4Video offers the following benefits: 1) It exhibits impressive capabilities in both video understanding and generation scenarios. For example, GPT4Video outperforms Valley by 11.8\% on the Video Question Answering task, and surpasses NExt-GPT by 2.3\% on the Text to Video generation task. 2) it endows the LLM/MLLM with video generation capabilities without requiring additional training parameters and can flexibly interface with a wide range of models to perform video generation. 3) it maintains a safe and healthy conversation not only in output-side but also the input side in an end-to-end manner. Qualitative and qualitative experiments demonstrate that GPT4Video holds the potential to function as a effective, safe and Humanoid-like video assistant that can handle both video understanding and generation scenarios.
title GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.16511