trigger word : aunt cass
recommended strength : 0.85 toi 1, do not use below 0.75
use lower strengths only if model is not following the prompt.
I recommend using Dream Shaper 5
you need this extension to run this file
then load like a normal lora file
if you like my stuff pls consider supporting me on Kofi
Description
FAQ
Comments (7)
and its nsfw capable
Hi, could you please clear my curiosity? How is it that in some positive and negative prompts some words are enclosed in parentheses? These to be clear ( and sometimes even 2 (( or 3 ((( parentheses. Could you explain the reason? It's not enough to simply use the Comma? , XD
for emphasis on what should be prioritized, the same principle as putting (xxxx:1.y), the program will give special priority to this part of the prompt. Like if you're generating something with a prompt and for example the eyes are coming out closed if you put (((open eyes))) or (open eyes:1.3) it should fix the problem. (tip: if you select the entire word and hold ctrl + up arror/low arrow you can easily change the weight)
Wrapping a tag in parentheses increases the strength of the tag in Automatic1111 and most other GUIs. If you want Stable Diffuion to focus more on a particular tag, you wrap it in parentheses. You can wrap it in more than one set of parentheses, too. For example: (hair ribbon) is weaker than ((hair ribbon)), although both would be given more attention than normal tags. In the case of the hair ribbon tag, more weight probably just makes the ribbon bigger or longer.
You can also use (hair ribbon:1.1), (hair ribbon:1.2), etc. instead. Increasing the number achieves the same effect as adding more parentheses. You can also make the tag have less weight by giving it a value lower than 1, like (hair ribbon:0.9), (hair ribbon:0.8), etc.
For some ungodly reason, some people choose to use this feature for almost every single tag. I personally don't get the point, I usually only emphasize a one or two tags if I feel it's needed.
How many images do you need for a dataset for commission?
is this better than lora? what are the benefits vs dreambooth vs lora?
Dreambooth is an entire model on its own, lora is a small model that acts as an extension to add stuff to any model,
While you can use Dreambooth on its own, you can't use lora on its own
And lycoris is the next step in lora-type models,
And to answer your question,
As far as I've tested lycoris, it has indeed proved to be better than LoRa
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



