README.md

---
language: zh
license: creativeml-openrail-m

tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- zh
- Chinese
- Anime

inference: true
widget:
- text: "1个女孩,绿色头发,毛衣,看向阅图者,上半身,帽子,户外,下雪,高领毛衣"
  example_title: 1个女孩
- text: "单人,看向阅图者,短发,刘海,黑发,1个男孩,眼间刘海"
  example_title: 1个男孩

  
extra_gated_prompt: |-
  One more step before getting this model.
  This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
  The CreativeML OpenRAIL License specifies: 

  1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 
  2. IDEA-CCNL claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
  Please read the full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license
  
  By clicking on "Access repository" below, you accept that your *contact information* (email address and username) can be shared with the model authors as well.
extra_gated_fields:
 I have read the License and agree with its terms: checkbox
---

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

- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
- Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
- API：[Fengshen-OpenAPI](https://fengshenbang-lm.com/open-api)

## 简介 Brief Introduction

首个开源的中文Stable Diffusion动漫模型，基于100万筛选过的动漫中文图文对训练。

The first open source Chinese Stable diffusion Anime model, which was trained on 100w filtered Anime 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

我们将两份动漫数据集(100万低质量数据和1万高质量数据)，基于[IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1](https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1) 模型进行了两阶段的微调训练，计算开销是4 x A100 训练了大约100小时。该版本只是一个初步的版本，我们将持续优化并开源后续模型，欢迎交流。

We use two anime dataset(1 million low-quality data and 10k high-qualty data) for two-staged training the chinese anime model based our pretrained model [IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1](https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1). It takes 100 hours to train this model based on 4 x A100. This model is a preliminary version and we ~~will~~ update this model continuously and open sourse. Welcome to exchange！

### Result
以下例子是模型在webui运行获得。

These example are got from an model running on webui.
|  prompt1   |  prompt2 |
|  ------  |  ------  |
|  <img width=250/>  | <img width=250/>  |
|  1个女孩,绿色头发,毛衣,看向阅图者,上半身,帽子,户外,下雪,高领毛衣   |  1个男生,帅气,微笑,看着阅图者,简单背景,白皙皮肤,上半身,衬衫,短发,单人 |
| ![](result_examples/girl.png)  | ![](result_examples/boy.png) |
|  户外,天空,云,蓝天,无人,多云的天空,风景,日出,草原  |  室内,杯子,书,无人,窗,床,椅子,桌子,瓶子,窗帘,阳光,风景,盘子,木地板,书架,蜡烛,架子,书堆,绿植,梯子,地毯,小地毯 |
| ![](result_examples/outdoor.png)  | ![](result_examples/indoor.png)  |
|  建筑,科幻,城市,城市风景,摩天大楼,赛博朋克,人群  |  户外,天空,水,树,无人,夜晚,建筑,风景,反射,灯笼,船舶,建筑学,灯笼,船,反射水,东亚建筑 |
| ![](result_examples/city.png)  | ![](result_examples/villege.png)  |
|  无人,动物,(猫:1.5),高清,棕眼  |  无人,动物,(兔子:1.5),高清,棕眼 |
| ![](result_examples/cat.png)  | ![](result_examples/rabbit.png)  |


## 使用 Usage

### webui配置 Configure webui
非常推荐使用webui的方式使用本模型，webui提供了可视化的界面加上一些高级修图功能。

It is highly recommended to use this model in a webui way. webui provides a visual interface plus some advanced retouching features.

https://github.com/IDEA-CCNL/stable-diffusion-webui/blob/master/README.md

### 全精度 Full precision

```py
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1").to("cuda")

prompt = '1个女孩,绿色头发,毛衣,看向阅图者,上半身,帽子,户外,下雪,高领毛衣'
image = pipe(prompt, guidance_scale=7.5).images[0]  
image.save("1个女孩.png")
```

### 半精度 Half precision FP16 (CUDA)

添加 `torch_dtype=torch.float16` 和 `device_map="auto"` 可以快速加载 FP16 的权重，以加快推理速度。
更多信息见 [the optimization docs](https://huggingface.co/docs/diffusers/main/en/optimization/fp16#half-precision-weights)。

```py
# !pip install git+https://github.com/huggingface/accelerate
import torch
from diffusers import StableDiffusionPipeline
torch.backends.cudnn.benchmark = True
pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1", torch_dtype=torch.float16)
pipe.to('cuda')

prompt = '1个女孩,绿色头发,毛衣,看向阅图者,上半身,帽子,户外,下雪,高领毛衣'
image = pipe(prompt, guidance_scale=7.5).images[0]  
image.save("1个女孩.png")
```

### 使用手册 Handbook for Taiyi

https://github.com/IDEA-CCNL/Fengshenbang-LM/blob/main/fengshen/examples/stable_diffusion_chinese/taiyi_handbook.md

### 怎样微调 How to finetune

https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/finetune_taiyi_stable_diffusion


### DreamBooth

https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/stable_diffusion_dreambooth

## 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[总论文](https://arxiv.org/abs/2209.02970)：

If you are using the resource for your work, please cite the our [paper](https://arxiv.org/abs/2209.02970):

```text
@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](https://github.com/IDEA-CCNL/Fengshenbang-LM/):

You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):

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