Hugging Face
Models
Datasets
Spaces
Docs
Solutions
Pricing
Log In
Sign Up
IDEA-CCNL
/
Taiyi-Stable-Diffusion-1B-Chinese-EN-v0.1
Copied
like
86
Text-to-Image
Diffusers
Chinese
stable-diffusion
stable diffusion chinese
stable-diffusion-diffusers
Chinese
arxiv:
2112.10752
arxiv:
2209.02970
License:
creativeml-openrail-m
Model card
Files
Files and versions
Community
11
Deploy
Use in Diffusers
感谢您的工作,这里有两个关于训练阶段的问题想请教下
#9
by
wqf321
- opened
Feb 6
Discussion
wqf321
Feb 6
我观察到您发布了两版中文diffusion模型,并且采取了不同的训练策略
为什么使用two stage的训练方法,即在第二阶段中将全部模型解冻,一起训练text encoder和diffusion model的方式可以让模型具备双语能力呢?我看数据集并没有变化
在中文图文生成任务上,使用单阶段的训练策略,即全程只训练text encoder,效果会显著优于两阶段的训练策略吗?
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment