patrickvonplaten's picture
Add FP16 docs
f68ed3c
|
raw
history blame
6.01 kB
metadata
license: creativeml-openrail-m
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - chinese
inference: false
extra_gated_prompt: >-
  One more step before getting this model.

  This model is open access and available to all, with a CreativeML OpenRAIL-M
  license further specifying rights and usage.

  The CreativeML OpenRAIL License specifies: 


  1. You can't use the model to deliberately produce nor share illegal or
  harmful outputs or content 

  2. IDEA-CCNL claims no rights on the outputs you generate, you are free to use
  them and are accountable for their use which must not go against the
  provisions set in the license

  3. You may re-distribute the weights and use the model commercially and/or as
  a service. If you do, please be aware you have to include the same use
  restrictions as the ones in the license and share a copy of the CreativeML
  OpenRAIL-M to all your users (please read the license entirely and carefully)

  Please read the full license here:
  https://huggingface.co/spaces/CompVis/stable-diffusion-license


  By clicking on "Access repository" below, you accept that your *contact
  information* (email address and username) can be shared with the model authors
  as well.
extra_gated_fields:
  I have read the License and agree with its terms: checkbox

Taiyi-Stable-Diffusion-1B-Chinese-v0.1

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.

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finetune了一个epoch。

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 model.

Result

飞流直下三千尺,摄影。

飞流直下三千尺,油画。

铁马冰河入梦来,3D绘画。

铁马冰河入梦来,概念画。

使用 Usage

完全精确 Full precision FP16

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.float16device_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
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1", torch_dtype=torch.float16, device_map="auto")

prompt = '飞流直下三千尺,油画'
image = pipe(prompt, guidance_scale=7.5).images[0]  
image.save("飞流.png")

引用 Citation

如果您在您的工作中使用了我们的模型,可以引用我们的论文

If you are using the resource for your work, please cite the our paper:

@article{fengshenbang,
  author    = {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 and Ruyi Gan and Jiaxing Zhang},
  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}},
}