---
library_name: diffusers
pipeline_tag: image-to-video
---

# AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment

This repository contains the AgentHOI model described in the paper [AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment](https://huggingface.co/papers/2607.22241).

Code: https://github.com/bone-11/agenthoi