Comments (6)
I can work on it in early dec, if you wish.
Probably will implement it in Python instead for ease of integration into the existing code for APIs
from novelai-2-local-prompt.
Have you or anyone else tested it to reproduce results on novelAI and the webui, especially the bracket part? I don't have a paid novelAI subscription so I cannot test myself.
I have not signed up, but it has been verified by an anonymous user and we know what the conditions are. If necessary, it can be further validated with a combination of existing NovelAI products and prompts.
You can check webUI's wiki here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#attentionemphasis
- their
{word}
= our(word:1.05)
- their
{{word}}
= our(word:1.1025)
- their
[word]
= our(word:0.952)
(0.952 = 1/1.05) - their
[[word]]
= our(word:0.907)
(0.907 = 1/1.05/1.05)
from novelai-2-local-prompt.
It's good idea!
As I don't have much time, please be patient :)
from novelai-2-local-prompt.
I can't speak too strongly about this code, as I only modified the code that anonymous wrote, but it is quite flawed.
(To be honest, I don't really know how to implement the core part, regarding the string handling...)
For now, the first priority should be to get the algorithm in place and rewrite it in Python.
from novelai-2-local-prompt.
Have you or anyone else tested it to reproduce results on novelAI and the webui, especially the bracket part? I don't have a paid novelAI subscription so I cannot test myself.
from novelai-2-local-prompt.
Just dropping this here for future reference when I start working on this:
AUTOMATIC1111/stable-diffusion-webui#3982
from novelai-2-local-prompt.
Related Issues (8)
- Repository Basics HOT 1
- i dont think this script works anymore HOT 4
- buttons too big, can you make it smaller, and fit with in the 5 buttons already exits?
- Issues with AUTOMATIC111 HOT 1
- [Request] Add more simple description HOT 1
- Known issues and Re-implementing in Python HOT 1
- May I ask that how it handles prompt like (()) HOT 1
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 novelai-2-local-prompt.