Midu commited on
Commit
0b98ddb
1 Parent(s): dd52bb4

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -5
README.md CHANGED
@@ -17,22 +17,20 @@ tags:
17
 
18
  ## Brief Introduction
19
 
20
-
21
-
22
  | ![cyberpunk](examples/cyberpunk.jpeg) | ![shiba](examples/shiba.jpeg) | ![ds](examples/ds.jpeg) |
23
  | ------------------------------------- | ----------------------------- | ------------------------------- |
24
  | ![waitan](examples/waitan.jpeg) | ![gf](examples/gf.jpeg) | ![ssh](examples/ssh.jpeg) |
25
  | ![cat](examples/cat.jpeg) | ![robot](examples/robot.jpeg) | ![castle](examples/castle.jpeg) |
26
 
27
- 大概是huggingface 社区首个开源的Stable diffusion 2 中文模型。该模型基于stable diffusion V2.1模型,在约500万条的中国风格特挑中文数据上进行微调,数据来源于多个开源数据集如[LAION-5B](https://laion.ai/blog/laion-5b/), [Noah-Wukong](https://wukong-dataset.github.io/wukong-dataset/), [Zero](https://zero.so.com/)和一些网络数据。
28
 
29
- Probably the first open sourced Chinese Stable Diffusion 2 model. This model is finetuned based on stable diffusion V2.1 with 5M chinese style filtered data. Dataset is composed of several different chinese open source dataset such as [LAION-5B](https://laion.ai/blog/laion-5b/), [Noah-Wukong](https://wukong-dataset.github.io/wukong-dataset/), [Zero](https://zero.so.com/) and some web data.
30
 
31
 
32
 
33
  ## Model Details
34
 
35
- ### 文本编码器
36
 
37
  文本编码器使用冻结参数的[lyua1225/clip-huge-zh-75k-steps-bs4096](https://huggingface.co/lyua1225/clip-huge-zh-75k-steps-bs4096)。
38
 
 
17
 
18
  ## Brief Introduction
19
 
 
 
20
  | ![cyberpunk](examples/cyberpunk.jpeg) | ![shiba](examples/shiba.jpeg) | ![ds](examples/ds.jpeg) |
21
  | ------------------------------------- | ----------------------------- | ------------------------------- |
22
  | ![waitan](examples/waitan.jpeg) | ![gf](examples/gf.jpeg) | ![ssh](examples/ssh.jpeg) |
23
  | ![cat](examples/cat.jpeg) | ![robot](examples/robot.jpeg) | ![castle](examples/castle.jpeg) |
24
 
25
+ 大概是Huggingface 🤗社区首个开源的Stable diffusion 2 中文模型。该模型基于stable diffusion V2.1模型,在约500万条的中国风格特挑中文数据上进行微调,数据来源于多个开源数据集如[LAION-5B](https://laion.ai/blog/laion-5b/), [Noah-Wukong](https://wukong-dataset.github.io/wukong-dataset/), [Zero](https://zero.so.com/)和一些网络数据。
26
 
27
+ Probably the first open sourced Chinese Stable Diffusion 2 model in Huggingface🤗 community. This model is finetuned based on stable diffusion V2.1 with 5M chinese style filtered data. Dataset is composed of several different chinese open source dataset such as [LAION-5B](https://laion.ai/blog/laion-5b/), [Noah-Wukong](https://wukong-dataset.github.io/wukong-dataset/), [Zero](https://zero.so.com/) and some web data.
28
 
29
 
30
 
31
  ## Model Details
32
 
33
+ ### 文本编码器/Text Encoder
34
 
35
  文本编码器使用冻结参数的[lyua1225/clip-huge-zh-75k-steps-bs4096](https://huggingface.co/lyua1225/clip-huge-zh-75k-steps-bs4096)。
36