Total runs:
4.6K
Run Growth:
497
Growth Rate:
10.52%
Sponsored by
ThumbnailCreator.com
IDEA-CCNL / Taiyi-Stable-Diffusion-1B-Chinese-v0.1
Model's Last Updated: May 25 2023
text-to-image
Introduction of Taiyi-Stable-Diffusion-1B-Chinese-v0.1
Model Details of Taiyi-Stable-Diffusion-1B-Chinese-v0.1
Taiyi-Stable-Diffusion-1B-Chinese-v0.1
- Main Page: Fengshenbang
- Github: Fengshenbang-LM
简介 Brief Introduction
首个开源的中文Stable Diffusion模型，基于0.2亿筛选过的中文图文对训练。
The first open source Chinese Stable diffusion, which was trained on 20M filtered Chinese image-text pairs.
在线体验 Gradio Web UI
可以在 Taiyi-Stable-Diffusion-Chinese 体验我们的模型。
We support a Gradio Web UI to run Taiyi-Stable-Diffusion-1B-Chinese-v0.1: Taiyi-Stable-Diffusion-Chinese
简介 Brief Introduction
首个开源的中英双语Stable Diffusion模型，基于0.2亿筛选过的中文图文对训练。
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 Noah-Wukong 数据集(100M)和 Zero 数据集(23M)用作预训练的数据集，先用 IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese 对这两个数据集的图文对相似性进行打分，取CLIP Score大于0.2的图文对作为我们的训练集。 我们使用 IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese 作为初始化的text encoder，冻住 stable-diffusion-v1-4 ( 论文 )模型的其他部分，只训练text encoder，以便保留原始模型的生成能力且实现中文概念的对齐。该模型目前在0.2亿图文对上训练了一个epoch。 我们在 32 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 Noah-Wukong (100M) 和 Zero (23M) as our dataset, and take the image and text pairs with CLIP Score (based on IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese ) greater than 0.2 as our Training set. We use IDEA-CCNL/Taiyi-CLIP-RoBERTa-102M-ViT-L-Chinese as our init text encoder. To keep the powerful generative capability of stable diffusion and align Chinese concepts with the images, We only train the text encoder and freeze other part of the stable-diffusion-v1-4 ( paper ) model. It takes 100 hours to train this model based on 32 x A100. This model is a preliminary version and we will update this model continuously and open sourse. Welcome to exchange！
Result
Basic Prompt
| 铁马冰河入梦来，3D绘画。 | 飞流直下三千尺，油画。 | 女孩背影，日落，唯美插画。 |
|---|---|---|
|
|
|
Advanced Prompt
| 铁马冰河入梦来，概念画，科幻，玄幻，3D | 中国海边城市，科幻，未来感，唯美，插画。 | 那人却在灯火阑珊处，色彩艳丽，古风，资深插画师作品，桌面高清壁纸。 |
|---|---|---|
|
|
|
使用 Usage
全精度 Full precision
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1").to("cuda")
prompt = '飞流直下三千尺，油画'
image = pipe(prompt, guidance_scale=7.5).images[0]
image.save("飞流.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
。
# !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-Chinese-v0.1", torch_dtype=torch.float16)
pipe.to('cuda')
prompt = '飞流直下三千尺，油画'
image = pipe(prompt, guidance_scale=7.5).images[0]
image.save("飞流.png")
使用手册 Handbook for Taiyi
怎样微调 How to finetune
webui配置 Configure webui
https://github.com/IDEA-CCNL/stable-diffusion-webui/blob/master/README.md
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 ：
If you are using the resource for your work, please cite the our paper :
@article{fengshenbang,
author = {Jiaxing Zhang and Ruyi Gan and 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},
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 :
You can also cite our website :
@misc{Fengshenbang-LM,
title={Fengshenbang-LM},
author={IDEA-CCNL},
year={2021},
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}
Runs of IDEA-CCNL Taiyi-Stable-Diffusion-1B-Chinese-v0.1 on huggingface.co
789
Total runs
0
24-hour runs
-9
3-day runs
15
7-day runs
282
30-day runs
More Information About Taiyi-Stable-Diffusion-1B-Chinese-v0.1 huggingface.co Model
Url of Taiyi-Stable-Diffusion-1B-Chinese-v0.1
Taiyi-Stable-Diffusion-1B-Chinese-v0.1 huggingface.co Url
Provider of Taiyi-Stable-Diffusion-1B-Chinese-v0.1 huggingface.co
Other API from IDEA-CCNL
Updated:May 25 2023
Total runs:
4.2K
Run Growth:
-1.3K
Growth Rate:
-25.94%
Total runs:
3.1K
Run Growth:
-784
Growth Rate:
-24.52%
Total runs:
1.1K
Run Growth:
30
Growth Rate:
2.66%
Total runs:
557
Run Growth:
403
Growth Rate:
72.35%
Total runs:
506
Run Growth:
170
Growth Rate:
33.60%
Total runs:
455
Run Growth:
36
Growth Rate:
7.91%
Total runs:
387
Run Growth:
54
Growth Rate:
11.56%
Total runs:
370
Run Growth:
-56
Growth Rate:
-15.47%
Total runs:
350
Run Growth:
-317
Growth Rate:
-92.15%
Total runs:
275
Run Growth:
45
Growth Rate:
16.36%
Total runs:
265
Run Growth:
-78
Growth Rate:
-29.43%
Total runs:
227
Run Growth:
65
Growth Rate:
28.63%
Total runs:
216
Run Growth:
41
Growth Rate:
20.30%
Total runs:
209
Run Growth:
86
Growth Rate:
41.15%
Total runs:
195
Run Growth:
31
Growth Rate:
15.90%
Total runs:
189
Run Growth:
69
Growth Rate:
36.51%
Total runs:
186
Run Growth:
-58
Growth Rate:
-31.18%
Total runs:
183
Run Growth:
49
Growth Rate:
26.78%
Total runs:
163
Run Growth:
54
Growth Rate:
33.13%
Total runs:
161
Run Growth:
-32
Growth Rate:
-19.88%
Total runs:
145
Run Growth:
-47
Growth Rate:
-33.10%
Total runs:
131
Run Growth:
8
Growth Rate:
6.11%
Total runs:
116
Run Growth:
-67
Growth Rate:
-57.76%
Total runs:
105
Run Growth:
4
Growth Rate:
3.85%
Total runs:
105
Run Growth:
-262
Growth Rate:
-249.52%
Total runs:
102
Run Growth:
37
Growth Rate:
37.00%
Total runs:
100
Run Growth:
-16
Growth Rate:
-16.00%
Total runs:
93
Run Growth:
18
Growth Rate:
19.57%
Total runs:
90
Run Growth:
-14
Growth Rate:
-15.56%
Total runs:
86
Run Growth:
42
Growth Rate:
48.84%
Total runs:
79
Run Growth:
17
Growth Rate:
21.52%
Total runs:
69
Run Growth:
38
Growth Rate:
56.72%
Total runs:
63
Run Growth:
26
Growth Rate:
41.27%
Total runs:
62
Run Growth:
9
Growth Rate:
14.52%
Total runs:
58
Run Growth:
11
Growth Rate:
20.00%
Total runs:
56
Run Growth:
-6
Growth Rate:
-12.24%
Total runs:
55
Run Growth:
12
Growth Rate:
22.22%
Total runs:
55
Run Growth:
-7
Growth Rate:
-12.73%
Total runs:
53
Run Growth:
18
Growth Rate:
34.62%
Total runs:
48
Run Growth:
-27
Growth Rate:
-62.79%
Total runs:
47
Run Growth:
17
Growth Rate:
37.78%
Total runs:
46
Run Growth:
18
Growth Rate:
40.00%
Total runs:
45
Run Growth:
-13
Growth Rate:
-28.89%
Total runs:
44
Run Growth:
-6
Growth Rate:
-13.64%
Total runs:
43
Run Growth:
12
Growth Rate:
27.91%
Total runs:
42
Run Growth:
9
Growth Rate:
21.43%
Total runs:
41
Run Growth:
-3
Growth Rate:
-7.32%
Total runs:
41
Run Growth:
4
Growth Rate:
9.76%
Total runs:
41
Run Growth:
2
Growth Rate:
4.88%
Total runs:
41
Run Growth:
-2
Growth Rate:
-5.26%
Total runs:
37
Run Growth:
6
Growth Rate:
16.22%
Total runs:
36
Run Growth:
15
Growth Rate:
45.45%
Total runs:
36
Run Growth:
23
Growth Rate:
62.16%
Total runs:
35
Run Growth:
10
Growth Rate:
28.57%
Total runs:
34
Run Growth:
-52
Growth Rate:
-152.94%
Total runs:
34
Run Growth:
11
Growth Rate:
32.35%
Total runs:
33
Run Growth:
9
Growth Rate:
27.27%
Total runs:
30
Run Growth:
4
Growth Rate:
13.79%
Total runs:
30
Run Growth:
6
Growth Rate:
20.00%
Total runs:
29
Run Growth:
5
Growth Rate:
17.24%
Total runs:
27
Run Growth:
4
Growth Rate:
14.81%
Total runs:
27
Run Growth:
10
Growth Rate:
37.04%
Total runs:
27
Run Growth:
-4
Growth Rate:
-14.81%
Total runs:
26
Run Growth:
-6
Growth Rate:
-23.08%
Total runs:
25
Run Growth:
6
Growth Rate:
25.00%
Total runs:
24
Run Growth:
-10
Growth Rate:
-41.67%
Total runs:
24
Run Growth:
8
Growth Rate:
33.33%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
3
Growth Rate:
13.04%
Total runs:
23
Run Growth:
-1
Growth Rate:
-4.35%
Total runs:
23
Run Growth:
5
Growth Rate:
23.81%
Total runs:
23
Run Growth:
-10
Growth Rate:
-43.48%
Total runs:
21
Run Growth:
1
Growth Rate:
4.76%
Total runs:
20
Run Growth:
5
Growth Rate:
25.00%
Total runs:
19
Run Growth:
3
Growth Rate:
15.79%
Total runs:
19
Run Growth:
6
Growth Rate:
31.58%
Total runs:
18
Run Growth:
-4
Growth Rate:
-22.22%
Total runs:
18
Run Growth:
6
Growth Rate:
31.58%
Total runs:
18
Run Growth:
7
Growth Rate:
38.89%
Total runs:
17
Run Growth:
-2
Growth Rate:
-11.76%
Total runs:
17
Run Growth:
-2
Growth Rate:
-12.50%
Total runs:
16
Run Growth:
-8
Growth Rate:
-53.33%
Total runs:
15
Run Growth:
2
Growth Rate:
13.33%
Total runs:
15
Run Growth:
-3
Growth Rate:
-20.00%
Total runs:
15
Run Growth:
-6
Growth Rate:
-40.00%
Total runs:
15
Run Growth:
-10
Growth Rate:
-66.67%
Total runs:
15
Run Growth:
-12
Growth Rate:
-80.00%
Total runs:
14
Run Growth:
2
Growth Rate:
13.33%