---
title: CogView2
canonical_url: "https://www.modelscope.cn/models/ZhipuAI/CogView2"
md_url: "https://www.modelscope.cn/models/ZhipuAI/CogView2.md"
repository: ZhipuAI/CogView2
last_updated: 2024-01-09
license: apache-2.0
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 217
stars: 1
---

# CogView2

> CogView2 - ZhipuAI 在 ModelScope 开源的模型。CogView2 Model description

ZhipuAI/CogView2 是 ModelScope 魔搭社区上的text-to-video-synthesis模型，采用 apache-2.0 许可。

- **Repository**: ZhipuAI/CogView2
- **License**: apache-2.0
- **Tasks**: text-to-video-synthesis
- **Downloads**: 217
- **Stars**: 1
- **Last updated**: 2024-01-09

Source: https://www.modelscope.cn/models/ZhipuAI/CogView2

---

# CogView2
## Model description

**CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers**

- [Paper](https://arxiv.org/abs/2204.14217)
- [GitHub Repo](https://github.com/THUDM/CogView2)

### Abstract

The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel auto-regressive generation. We pretrain a 6B-parameter transformer with a simple and flexible self-supervised task, Cross-modal general language model (CogLM), and finetune it for fast super-resolution. The new text-to-image system, CogView2, shows very competitive generation compared to concurrent state-of-the-art DALL-E-2, and naturally supports interactive text-guided editing on images.

## BibTeX entry and citation info
```bibtex
@article{ding2022cogview2,
  title={CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers},
  author={Ding, Ming and Zheng, Wendi and Hong, Wenyi and Tang, Jie},
  journal={arXiv preprint arXiv:2204.14217},
  year={2022}
}
```