it is already customisted though - and has a lower barrior of entry versus sillytav. I do think though people should learn to not be intimidated by using sillytavern as its the best front end we have by miles.
You must be registered to see the links
step 1 open the website step 2 pick a character to you want step 3 hit refresh button till your at the top of the que (normaly takes a couple minutes) and enjoy.I've tried but I really don't understand how to get this shit to work. Explanations/guides are all over the place in this thread and the installation instructions seem outdated? I've seen multiple people ask but so far no decent explanation. How does a noob like me get this game to work, from the very start of downloading till being able to chat? I would really like to try it out!
If anyone wants to try a new UI for running uncensored models via llama.cpp locally, we just released our Windows desktop app - you can see the link in my profile!
These do not actually correspond with "detailed instructions." There is in fact, a decided lack of detail for anyone who is a novice to AI anything.
Making the messages for the API keys into clickable links would help people get to the sites required for the keys simpler as trying to type these out if you only have 1 monitor would be a bit of a pain. Some kind of intro that says WTF is going on and how to start the interactions would be good. I also noted that there seems to be only a Speak for the chat box, no actions? Like if I wanted to type in "I leave the room," it would as if I SAID "I leave the room" instead of my character leaving the room. Could just be me since I only played around with it for about an hour trying different random phrases and methods of input.
Okay, why does sometimes the character load works great sometimes and sometimes it doesn't work at all? I can't load anything anymore
I keep getting IMG error: {detail: "not found"}, I have stable diffusion set up correctly i think.
until the Dev makes this "game" a simple Click and Install application, I'm ignoring this post.
It's not hard to do. Just implement all your "Instructions" into a package, zip it, make an unpacker or installer for it, done.
You can easily build a UI for everything else too using Visual Studio and ChatGPT ironically.
You can't expect your Customers to build the game for you.
When I go to a bakery to buy bread, they don't give me Eggs and Flour... they give me a fucking Bread.
It's not hard to do. Just implement all your "Instructions" into a package, zip it, make an unpacker or installer for it, done.
You can easily build a UI for everything else too using Visual Studio and ChatGPT ironically.
You can't expect your Customers to build the game for you.
When I go to a bakery to buy bread, they don't give me Eggs and Flour... they give me a fucking Bread.
It looks like the OFFLINE AI folder from the older versions work, I just tried the folder from V0.3b
well i have no idea how to make that game/ thing work i think theres need to be better way to play that game its really complicated
might not be the right place to ask but after hearing about silly tavern here i just tried it out
i absolutely dont understand whats happening
every time i try to react to the prompt given by a character the next message just completely disregards anyting that happened/what the intro said and just starts generating some sort of new universe and adds shit like "chapter 1 the intruder" after asking where the character wants to go
what the f do i have to do?
I'm getting this error all the time: "IMG Error: Unable to connect, please check the URL"
I'm not using the image generator, I don't think my PC can handle a local version of it, I'm only using the GPT API. Is the error related to it?
I'm not using the image generator, I don't think my PC can handle a local version of it, I'm only using the GPT API. Is the error related to it?
- Nov 12, 2017
- 189
- 222
You must be registered to see the links
this is by far the best model I've tried, I've used wizard before this and it's a huge difference
being able to run models depends on your graphics card, the more vram the better, im running a 2080ti so i have 11gigs of gddr which is just barely enough to run mid to low end size models, 7b models was pushing i think about 9 gigs on my vram when it has a download size of 7gig's, the 2gig model was taking about 4 gigs on vram. The bigger the language model like 13b + will require a minimum of 12gig's vram which is why so many people want a 4090 since thats 24gigs.
so yeah if you go over the size of your video card it'll bog down to where it takes a really long time for a reply.
Last edited: