Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance

TL;DR

This paper introduces a tuning-free multi-character text-to-video generation framework that uses pose guidance and text prompts to produce controllable videos with multiple characters, outperforming previous methods.

Contribution

A novel multi-character video generation method that is tuning-free, utilizing pose and text guidance with a multi-branch control module for fine-grained control.

Findings

Achieves precise multi-character control in generated videos.

Demonstrates superior quantitative performance over previous methods.

Proves generality across various personalized T2I models.

Abstract

Text-editable and pose-controllable character video generation is a challenging but prevailing topic with practical applications. However, existing approaches mainly focus on single-object video generation with pose guidance, ignoring the realistic situation that multi-character appear concurrently in a scenario. To tackle this, we propose a novel multi-character video generation framework in a tuning-free manner, which is based on the separated text and pose guidance. Specifically, we first extract character masks from the pose sequence to identify the spatial position for each generating character, and then single prompts for each character are obtained with LLMs for precise text guidance. Moreover, the spatial-aligned cross attention and multi-branch control module are proposed to generate fine grained controllable multi-character video. The visualized results of generating video demonstrate the precise controllability of our method for multi-character generation. We also verify the generality of our method by applying it to various personalized T2I models. Moreover, the quantitative results show that our approach achieves superior performance compared with previous works.