init commit

README.md

@@ -12,9 +12,9 @@ tags:
 
 inference: true
 widget:
-- text: "1个女孩,美丽,可爱"
+- 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: "1个男孩,帅气脸"
+- 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
 
   
@@ -58,14 +58,30 @@ The first open source Chinese Stable diffusion Anime model, which was trained on
 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。
 
-|  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,衬衫 |
+These example are got from an model running on webui.
+
+|  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)  |
+| ![](result_examples/girl.png){:height="250px" width="250px"}  | ![](result_examples/boy.png){:height="250px" width="250px"}  |
+|  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){:height="250px" width="250px"}  | ![](result_examples/indoor.png){:height="250px" width="250px"}  |
+|  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){:height="250px" width="250px"}  | ![](result_examples/villege.png){:height="250px" width="250px"}  |
+|  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){:height="250px" width="250px"}  | ![](result_examples/rabbit.png){:height="250px" width="250px"}  |
 
 
 ## 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
@@ -73,7 +89,7 @@ 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,美丽,可爱'
+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")
 ```
@@ -91,16 +107,10 @@ 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,美丽,可爱'
+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")
 ```
-### 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
 
 ### 使用手册 Handbook for Taiyi