wuxiaojun commited on
Commit
811f1d6
1 Parent(s): a952935

init commit

Browse files
README.md CHANGED
@@ -12,9 +12,9 @@ tags:
12
 
13
  inference: true
14
  widget:
15
- - text: "1个女孩,美丽,可爱"
16
  example_title: 1个女孩
17
- - text: "1个男孩,帅气脸"
18
  example_title: 1个男孩
19
 
20
 
@@ -58,14 +58,30 @@ 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
 
62
- | 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 |
 
 
63
  | ---- | ---- |
64
- | ![](result_examples/girl.png) | ![](result_examples/boy.png) |
 
 
 
 
 
 
65
 
66
 
67
  ## 使用 Usage
68
 
 
 
 
 
 
 
 
69
  ### 全精度 Full precision
70
 
71
  ```py
@@ -73,7 +89,7 @@ from diffusers import StableDiffusionPipeline
73
 
74
  pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1").to("cuda")
75
 
76
- prompt = '1个女孩,美丽,可爱'
77
  image = pipe(prompt, guidance_scale=7.5).images[0]
78
  image.save("1个女孩.png")
79
  ```
@@ -91,16 +107,10 @@ torch.backends.cudnn.benchmark = True
91
  pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1", torch_dtype=torch.float16)
92
  pipe.to('cuda')
93
 
94
- prompt = '1个女孩,美丽,可爱'
95
  image = pipe(prompt, guidance_scale=7.5).images[0]
96
  image.save("1个女孩.png")
97
  ```
98
- ### webui配置 Configure webui
99
- 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。
100
-
101
- It is highly recommended to use this model in a webui way. webui provides a visual interface plus some advanced retouching features.
102
-
103
- https://github.com/IDEA-CCNL/stable-diffusion-webui/blob/master/README.md
104
 
105
  ### 使用手册 Handbook for Taiyi
106
 
 
12
 
13
  inference: true
14
  widget:
15
+ - 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"
16
  example_title: 1个女孩
17
+ - text: "单人,看向阅图者,短发,刘海,黑发,1个男孩,眼间刘海"
18
  example_title: 1个男孩
19
 
20
 
 
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
+ | 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 |
66
  | ---- | ---- |
67
+ | ![](result_examples/girl.png){:height="250px" width="250px"} | ![](result_examples/boy.png){:height="250px" width="250px"} |
68
+ | 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 |
69
+ | ![](result_examples/outdoor.png){:height="250px" width="250px"} | ![](result_examples/indoor.png){:height="250px" width="250px"} |
70
+ | 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 |
71
+ | ![](result_examples/city.png){:height="250px" width="250px"} | ![](result_examples/villege.png){:height="250px" width="250px"} |
72
+ | 无人,动物,(猫:1.5),高清,棕眼 | 无人,动物,(兔子:1.5),高清,棕眼 |
73
+ | ![](result_examples/cat.png){:height="250px" width="250px"} | ![](result_examples/rabbit.png){:height="250px" width="250px"} |
74
 
75
 
76
  ## 使用 Usage
77
 
78
+ ### webui配置 Configure webui
79
+ 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。
80
+
81
+ It is highly recommended to use this model in a webui way. webui provides a visual interface plus some advanced retouching features.
82
+
83
+ https://github.com/IDEA-CCNL/stable-diffusion-webui/blob/master/README.md
84
+
85
  ### 全精度 Full precision
86
 
87
  ```py
 
89
 
90
  pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1").to("cuda")
91
 
92
+ 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'
93
  image = pipe(prompt, guidance_scale=7.5).images[0]
94
  image.save("1个女孩.png")
95
  ```
 
107
  pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Anime-Chinese-v0.1", torch_dtype=torch.float16)
108
  pipe.to('cuda')
109
 
110
+ 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'
111
  image = pipe(prompt, guidance_scale=7.5).images[0]
112
  image.save("1个女孩.png")
113
  ```
 
 
 
 
 
 
114
 
115
  ### 使用手册 Handbook for Taiyi
116
 
result_examples/cat.png ADDED

Git LFS Details

  • SHA256: debd1af9e2b6818849640112d3fef1ca01f05e2eb86f04f2505adade71601424
  • Pointer size: 131 Bytes
  • Size of remote file: 380 kB
result_examples/city.png ADDED

Git LFS Details

  • SHA256: 477d4c3a7a0bb717d46a059c2fb3d781475a473fac3248bab7044a4411bc9d3c
  • Pointer size: 130 Bytes
  • Size of remote file: 41.7 kB
result_examples/girl.png CHANGED

Git LFS Details

  • SHA256: c70f6ac936cedc81fb49fde3d96dbde954f26c6fbb6279652900fc303e77cf7f
  • Pointer size: 131 Bytes
  • Size of remote file: 369 kB

Git LFS Details

  • SHA256: 681bd0eda9894f5db90a775a634a031f396b1ff13388b4b1602d448bf5c54e15
  • Pointer size: 131 Bytes
  • Size of remote file: 393 kB
result_examples/girl_.png ADDED

Git LFS Details

  • SHA256: c70f6ac936cedc81fb49fde3d96dbde954f26c6fbb6279652900fc303e77cf7f
  • Pointer size: 131 Bytes
  • Size of remote file: 369 kB
result_examples/indoor.png ADDED

Git LFS Details

  • SHA256: 8f3f80c4e8cc6ab65e2ab43d0d5be0211e803778d443d4cb2b6add472484ceab
  • Pointer size: 131 Bytes
  • Size of remote file: 377 kB
result_examples/outdoor.png ADDED

Git LFS Details

  • SHA256: 22de72befd5447da40144c1edc56e520b904704b021bba9dbc4da068b2767c2f
  • Pointer size: 131 Bytes
  • Size of remote file: 318 kB
result_examples/rabbit.png ADDED

Git LFS Details

  • SHA256: b110384c4acc732aefb7d731901ab965aa90c2281feb221bf5d8664a5dfb9dc3
  • Pointer size: 131 Bytes
  • Size of remote file: 379 kB
result_examples/villege.png ADDED

Git LFS Details

  • SHA256: a3597edf1f1e4447bf7e0cdd87601e0dd00c4c2ead123773b068cbaad402d3d8
  • Pointer size: 131 Bytes
  • Size of remote file: 367 kB