Anyone know of a translation software that is fairly easy to setup and use for Japanese games whether it be premium or free?
Big thanks man!You must be registered to see the links+ DeepL is the only thing I use.
Can you tell me the name of that game??Any games where you know about the NTR by phone messages? I played one with bowser and peach and i enjoyed the idea!
rascou gamesAny games where you know about the NTR by phone messages? I played one with bowser and peach and i enjoyed the idea!
Smart girl, good video. Just needed to at least mention sperm competition. No discussion of NTR or cuck fantasies is complete without that.-------------
okay, custom module training recommendations:
- biggest rule of thumb: put in your data formatted the way you want the ai to generate it
- plain text in txt format, no formatting tags/markdown/html
- prose
- one line = one paragraph, no paragraphs split onto multiple lines
- no empty lines between paragraphs
- empty line could be used for chapter break, but recommend using *** instead
- no leading/trailing space, tab or other whitespace (easy to clean with notepad++)
- only one space character (no double/triple/... spaces)
- ideally, use regular quote and single quote characters " and ' not fancy ones (easier on the ai)
- make sure all included material is focused on what your module should achieve, no kitchen sink (e.g. tried to do steampunk, but most steampunk novels don't talk about steampunk stuff all the time, so ended up really weak)
- if you want to avoid leaking character names/other stuff, keep the data balanced and include many different stories with differen characters
- 1mb to 5mb seems like a good amount of text for an author style or theme style that can have low character leakage if varied enough (used 3k steps, but our pipeline may use different context size and batch size, which will change how many steps are needed)
- upper limit probably 10mb
- feel free to experiment with short data. nothing stops you from turning a short prompt into a module, will require much less steps too (maybe 50-100?)
- don't expect a module to memorize relational/factual data (e.g. if you feed it a story with pokemon descriptions, it'll probably bring up those pokemons, but it may still get their types wrong)
I finally got around to starting to clean up my module training data. Pretty sure the finetune team has a much more thorough pipeline, but I couldn't immediately find if they've published it, so here's the most obvious stuff I could come up with in 20 minutes while struggling to remember how to shot sed:
sed -i -E -e 's/\s+/ /g' -e 's/[“”]/"/g' -e "s/[‘’]/'/g" -e 's/…/.../g' -e 's/^ +([^ ])/\1/' -e 's/([^ ]) +$/\1/' -e '/^ *$/d' -e 's/^[^[:alnum:]]+$/***/' *txt
This processes all .txt files in the current directory. In order, the expressions:
- Replace all multiple whitespace with a single space
- Replace fancy double quotes with ordinary ones
- Replace fancy single quotes with ordinary ones
- Replace fancy ellipses with ordinary ones (though who knows, maybe you might want to not do this, or even reverse it)
- Strip leading whitespace
- Strip trailing whitespace
- Delete empty lines
- Replace lines consisting entirely of non-alphanumeric characters with a standardized chapter break
Trained on cleaned text from many Star Wars series novels including Legends and canon books across a variety of eras (though with a focus on Rise of the Empire), and even roleplaying sourcebooks.
try this oneare there any more games like Kedamono tachi no Sumu Ie de and Minako or really hard ntr, someone please help
i need something harder
Can you give a tutorial? I saw a post earlier but didnt read much to it. How good is this?This is my second NovelAI NTR Module. It is based on 260 HQ NTR short stories and one ghost story.
TAGS: cuckold, NSFW
Source: filtered `GPT-Shinen dataset`
Well, if you know how to use Textractor+Deepl (Check the tutoriali need something harder