Comments (9)
是的 pt文件就是训练出来的模型
from my_textual_inversions.
感谢回复,刚刚测试了一下,可以跑出来,只是nahida的眼睛似乎都不太像(眼睛很关键),样例图也是(十字),是不是样本问题呀
顺便说下,注意事项:
1.nahida.pt放到\stable-diffusion-webui\embeddings
2.模型选择novelaifinal-pruned.ckpt,而不要选择sd-v1-4.ckpt 否则没结果
3.生成大小选择512*512,否则可能没有结果
from my_textual_inversions.
感谢回复
1.样本没问题 样本图眼睛都有四叶草标志 但是ai学不会呀
2.模型的话我是用的animefull-latest.ckpt(7g左右), 如果使用animefull-final-pruned.ckpt(4g左右)的话,生成出来的图片是各种很奇怪的烂图
from my_textual_inversions.
是的 模型使用的是7G左右的那个 这个7G的模型生成速度快一些 但稳定性感觉不如4G左右的那个
from my_textual_inversions.
生成速度不清楚 我一开始就是使用的4g模型 那根本不能训练模型 出来的结果你看我训练的草神前边的图就知道了 5万多step开始我才换成7g模型 一换就开始转向正常了
from my_textual_inversions.
这个倒是没注意测试 按道理应该都能训练 输出的 具体肯定以实践为准了
我现在已经把4G的那个模型删掉了 主要是因为7G的模型生成效率可以提高一倍以上(同样tag同样分辨率的图,生成耗时只需要原来的二分之一以下,而生成效果甚至有所提升)。
顺便,novelAI真好玩→_→
from my_textual_inversions.
看文件名字
animefull-latest.ckpt(7g)是最新版
animefull-final-pruned.ckpt(4g)是修剪版本
可能是删掉了训练模型用的那部分?
from my_textual_inversions.
名字参考意义不大,看文件大小,因为名字可以随便改,只要和权重文件保持一致即可。
7.17 GB (7,703,828,146 字节)
from my_textual_inversions.
嗯
from my_textual_inversions.
Related Issues (4)
- Same file hash HOT 2
- 那西坦的图全是绿色头发 HOT 4
- 水叔模型的几个问题 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from my_textual_inversions.