AIUAI
Activity Calendar
Loading...
Radar Chart
Loading...
Release Chart
Loading...
Classification Chart
Loading...
Tag Chart
Loading...
New thing
New thing
Incredibly, compared with DALL-E 2 and Imagen, the Stable Diffusion model is a lot smaller. While DALL-E 2 has around 3.5 Billion parameters, and Imagen has 4.6 Billion, the first Stable Diffusion ...
July 19th, 2023 at 04:29 pm
Stable Diffusion model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and can run on ...
July 19th, 2023 at 12:38 pm
For example, using Stable Diffusion v1-5 with a ControlNet checkpoint require roughly 700 million(7亿) more parameters compared to just using the original Stable Diffusion model, which makes Control...
July 19th, 2023 at 10:36 am
username
password
Login
logging in...
刷新页面后登录
虚拟人技术 - 未来新世界
Author:
AIHGF
发布时间:
January 1, 2022
290views
No comments
0 words
Categories:
技术场景
Home
Text
Last modification:January 1st, 2022 at 10:32 pm
© 允许规范转载
Next
Previous
※相关文章推荐※
暂无相关推荐
※最新文章推荐※
恢复旧版本GitHub Feed
LLM 的几份资料
transformer-explainer
Leave a Comment
Cancel reply
Comment
*
Name
*
🎲
Email
*
Site
Leave a Comment
submitting...
虚拟人技术 - 未来新世界
AIHGF
•
2022 年 01 月 01 日
Article Directory