metadata

license: apache-2.0
pipeline_tag: feature-extraction
tags:
  - clip
  - zh
  - image-text
  - feature-extraction

Taiyi-Stable-Diffusion-1B-Chinese-v0.1

Github: Fengshenbang-LM
Docs: Fengshenbang-Docs

简介 Brief Introduction

首个开源的中文Stable Diffusion模型，基于0.2亿筛选过的中文图文对训练我们的IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese模型。

The first open source Chinese Stable diffusion, which was trained on 20M filtered Chinese image-text pairs.

模型分类 Model Taxonomy

需求 Demand	任务 Task	系列 Series	模型 Model	参数 Parameter	额外 Extra
特殊 Special	多模态 Multimodal	太乙 Taiyi	Stable Diffusion	1B	Chinese

模型信息 Model Information

我们将Noah-Wukong数据集(100M)和Zero数据集(23M)用作预训练的数据集，先用IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese对这两个数据集的图文对相似性进行打分，取CLIP Score大于0.2的图文对作为我们的训练集。我们使用IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese作为初始化的text encoder，冻住模型的其他部分，只训练text encoder，以便保留原始模型的生成能力且实现中文概念的对齐。该模型目前在0.2亿图文对上finetune了一个epoch。

We use Noah-Wukong(100M) 和 Zero(23M) as our dataset, and take the image and text pairs with CLIP Score (based on IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese) greater than 0.2 as our Training set. We utilize IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese as our init model. To keep the powerful generative capability of stable diffusion and align Chinese concept with the iamges, We only train the text encoder and freeze other part of the model.

下游效果 Performance

使用 Usage

引用 Citation

如果您在您的工作中使用了我们的模型，可以引用我们的论文：

If you are using the resource for your work, please cite the our paper:

@article{fengshenbang,
  author    = {Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen and Ruyi Gan and Jiaxing Zhang},
  title     = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
  journal   = {CoRR},
  volume    = {abs/2209.02970},
  year      = {2022}
}

也可以引用我们的网站:

You can also cite our website:

@misc{Fengshenbang-LM,
  title={Fengshenbang-LM},
  author={IDEA-CCNL},
  year={2021},
  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}