init commit
Browse files
README.md
CHANGED
|
@@ -32,7 +32,6 @@ extra_gated_prompt: |-
|
|
| 32 |
extra_gated_fields:
|
| 33 |
I have read the License and agree with its terms: checkbox
|
| 34 |
---
|
| 35 |
-
|
| 36 |
# Taiyi-Stable-Diffusion-1B-Chinese-v0.1
|
| 37 |
|
| 38 |
- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
|
|
@@ -47,9 +46,10 @@ The first open source Chinese Stable diffusion Anime model, which was trained on
|
|
| 47 |
|
| 48 |
## 模型分类 Model Taxonomy
|
| 49 |
|
| 50 |
-
|
| 51 |
-
|
|
| 52 |
-
|
|
|
|
|
| 53 |
|
| 54 |
## 模型信息 Model Information
|
| 55 |
|
|
@@ -58,24 +58,28 @@ The first open source Chinese Stable diffusion Anime model, which was trained on
|
|
| 58 |
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！
|
| 59 |
|
| 60 |
### Result
|
|
|
|
| 61 |
以下例子是模型在webui运行获得。
|
| 62 |
|
| 63 |
These example are got from an model running on webui.
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
| :
|
|
| 153 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 154 |
}
|
| 155 |
```
|
| 156 |
-
|
|
|
|
| 32 |
extra_gated_fields:
|
| 33 |
I have read the License and agree with its terms: checkbox
|
| 34 |
---
|
|
|
|
| 35 |
# Taiyi-Stable-Diffusion-1B-Chinese-v0.1
|
| 36 |
|
| 37 |
- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
|
|
|
|
| 46 |
|
| 47 |
## 模型分类 Model Taxonomy
|
| 48 |
|
| 49 |
+
|
| 50 |
+
| 需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
|
| 51 |
+
| :------------: | :-----------------: | :-----------: | :----------------: | :--------------: | :----------: |
|
| 52 |
+
| 特殊 Special | 多模态 Multimodal | 太乙 Taiyi | Stable Diffusion | 1B | Chinese |
|
| 53 |
|
| 54 |
## 模型信息 Model Information
|
| 55 |
|
|
|
|
| 58 |
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！
|
| 59 |
|
| 60 |
### Result
|
| 61 |
+
|
| 62 |
以下例子是模型在webui运行获得。
|
| 63 |
|
| 64 |
These example are got from an model running on webui.
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
| prompt1 | prompt2 |
|
| 68 |
+
| ----------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
|
| 69 |
+
| 1个男生,帅气,微笑,看着阅图者,简单背景,白皙皮肤,<br />上半身,衬衫,短发,单人 | 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 |
|
| 70 |
+
|  |  |
|
| 71 |
+
| 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,<br />风景,盘子,木地板,书架,蜡烛,架子,书堆,绿植,梯子,地毯,小地毯 |
|
| 72 |
+
|  |  |
|
| 73 |
+
| 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 | 建筑,科幻,城市,城市风景,摩天大楼,赛博朋克,人群 |
|
| 74 |
+
|  |  |
|
| 75 |
+
| 无人,动物,(猫:1.5),高清,棕眼 | 无人,动物,(兔子:1.5),高清,棕眼 |
|
| 76 |
+
|  |  |
|
| 77 |
|
| 78 |
|
| 79 |
## 使用 Usage
|
| 80 |
|
| 81 |
### webui配置 Configure webui
|
| 82 |
+
|
| 83 |
非常推���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。
|
| 84 |
|
| 85 |
It is highly recommended to use this model in a webui way. webui provides a visual interface plus some advanced retouching features.
|
|
|
|
| 124 |
|
| 125 |
https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/finetune_taiyi_stable_diffusion
|
| 126 |
|
|
|
|
| 127 |
### DreamBooth
|
| 128 |
|
| 129 |
https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/stable_diffusion_dreambooth
|
|
|
|
| 156 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 157 |
}
|
| 158 |
```
|
|
|