---
title: MoLA
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/MoLA"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/MoLA.md"
repository: AI-ModelScope/MoLA
last_updated: 2025-03-14
license: cc-by-4.0
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 591
stars: 0
tags:
  - Text-to-Motion
---

# MoLA

> MoLA - AI-ModelScope 在 ModelScope 开源的模型。This repository is for the checkpoint of "MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training"

AI-ModelScope/MoLA 是 ModelScope 魔搭社区上的机器学习模型，采用 cc-by-4.0 许可。

- **Repository**: AI-ModelScope/MoLA
- **License**: cc-by-4.0
- **Tags**: Text-to-Motion
- **Downloads**: 591
- **Stars**: 0
- **Last updated**: 2025-03-14

Source: https://www.modelscope.cn/models/AI-ModelScope/MoLA

---

This repository is for the checkpoint of ["MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training"](https://kengouchida-sony.github.io/MoLA-demo/)

Abstract: In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and editing the generated motions according to control signals, such as the start-end positions and the pelvis trajectory. In this paper, we propose MoLA, which provides fast, high-quality, variable-length motion generation and can also deal with multiple editing tasks in a single framework. Our approach revisits the motion representation used as inputs and outputs in the model, incorporating an activation variable to enable variable-length motion generation. Additionally, we integrate a variational autoencoder and a latent diffusion model, further enhanced through adversarial training, to achieve high-quality and fast generation. Moreover, we apply a training-free guided generation framework to achieve various editing tasks with motion control inputs. We quantitatively show the effectiveness of adversarial learning in text-to-motion generation, and demonstrate the applicability of our editing framework to multiple editing tasks in the motion domain.

PDF: [arXiv](https://arxiv.org/abs/2406.01867)

Codebase: Training and inference codes are available at the [GitHub](https://github.com/sony/MoLA)
 
Citation:
```bibtex
@article{uchida2024mola,
        title={MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training},
        author={Uchida, Kengo and Shibuya, Takashi and Takida, Yuhta and Murata, Naoki and Tanke, Julian and Takahashi, Shusuke and Mitsufuji, Yuki},
        journal={arXiv preprint arXiv:2406.01867},
        year={2024}
      }
```

License: Code is released under MIT, this checkpoints are released under CC-BY 4.0.