DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Susung, Seo, Junyoung, Shin, Heeseong, Hong, Sunghwan, Kim, Seungryong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911771694989312
author Hong, Susung
Seo, Junyoung
Shin, Heeseong
Hong, Sunghwan
Kim, Seungryong
author_facet Hong, Susung
Seo, Junyoung
Shin, Heeseong
Hong, Sunghwan
Kim, Seungryong
contents In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling shifts in scene composition or object placement from a single abstract user prompt. Exploring the ability of large language models (LLMs) to generate time-dependent, frame-by-frame prompts, this paper introduces a new framework, dubbed DirecT2V. DirecT2V leverages instruction-tuned LLMs as directors, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent mapping the value to a different object, we equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos from abstract user prompts, successfully addressing the challenges of zero-shot video generation.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14330
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
Hong, Susung
Seo, Junyoung
Shin, Heeseong
Hong, Sunghwan
Kim, Seungryong
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling shifts in scene composition or object placement from a single abstract user prompt. Exploring the ability of large language models (LLMs) to generate time-dependent, frame-by-frame prompts, this paper introduces a new framework, dubbed DirecT2V. DirecT2V leverages instruction-tuned LLMs as directors, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent mapping the value to a different object, we equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos from abstract user prompts, successfully addressing the challenges of zero-shot video generation.
title DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2305.14330