-
Notifications
You must be signed in to change notification settings - Fork 9
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Am I missing something here? #3
Comments
Yes... I have the string output going into a context node as well as a "show text" node for fun. From there I have a link from the context conditioning to a combine conditioning node which also has the normal positive prompt connected. Maybe there's other ways to do it but this works perfect for me. The only issue is you'll obviously get all the triggers into the conditioning, not a specific one. Not home so can't provide a screenshot sorry. |
The keywords go through the optional string input and out from the string output |
Can you show example? |
@Extraltodeus but how do you select the specific subtype of keywords (for character packs and utility packs)? |
Many good questions but few good answers! :( |
I've never used such. The main goal is really to either have the entirety of the keywords joined to the prompt or to print them in the terminal and use/select them manually. That's how I use the node |
If it prints to terminal could it not also print to an integrated text box in the node itself? Rather than having to go out to a string or show text. Just parse on lora load and print triggers to a text box at the bottom of the node? |
How do you really use it? In the attached setting, it didnt really append the key words?
The text was updated successfully, but these errors were encountered: