Home
Artists
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register
Partychan Telegram ThePornDude
Home Artists Posts Import Register

AI Chat Updates - GPT-4, Continue Button, *New 12/30/23 - KoboldAI Speed Improved (Patreon)

Published:
2023-12-27 09:39:04
Imported:
2024-01

Content

Existing Users: You don't need to update vamX.
New Users: Download vamX for AI Chat 1.34.

Password Change
You must be subscribed to get new passwords. Get your new password from https://www.patreon.com/vamx/membership

GPT-4
ChatGPT-4 has been added as a model. This is more expensive than GPT 3.5 (which we were using). If we get flooded with use, we may need to ask people to use their own GPT-4 API keys, but we are going to try just offering it for free with the service and see how it goes. This is the latest GPT-4 model which has knowledge of events through April 2023 (previous GPT 3.5 and 4 model data was only through 2021).

Continue
You can now press Continue to have the AI continue talking. If the AI is in the middle of a story, or telling you what to do, and you want to hear more, you can press Continue to have the AI continue without you having to ask "tell me more" or "what next" or anything else. The Continue button is next to Send/Reset/Retry (on the AI Chat page where you can type a message to the AI from vamX).

KoboldAI Speed & Refresh
We've fixed something on our end and KoboldAI models will now run faster (as of 12/30/23). KoboldAI still takes a few seconds (a while) to return responses, but it will be faster than before and/or show more models. There is now also a refresh button by the KoboldAI model list. This way you can press Refresh to see if the available models have changed.

What's Next
More voices, animation, emotional expressions, quicker responses, and other improvements will be released as soon as we finish them :)

Comments

Heinrich

Hello, is there a way to add a personality preset to the UI menu? Currently I have to manually input into the window, and copy and pasting can be cumbersome especially when testing something which requires a scene reload or something. Thanks.

vamx
>>125644177

Yes, you can make your own personality list, but it's complicated. There are instructions in https://sxvr.com/ai (search for "bunny.net") but it requires uploading them to a server. The instructions are step-by-step and the server costs are basically one time and very cheap, but the personalities have to be hosted online to work.

AgentXXDC

well, koboldai is as slow as never before and all vanish at least once every 5 minutes over the 30 seconds limit. nothing to see from any model thatwas available before christmas. also the browser UI is laggy and often cuts connection.

AgentXXDC

the same for the other models.

vamx
>>126824666

KoboldAI speed is something I can't control, it's a cloud of individual users providing models. So the models and model speed is just based on how many people are using the KoboldAI cloud, and how many people are hosting models on the KoboldAI cloud. So which models are available, and how fast they are, is sort of "random" (well based on the above). In any case, it will change all the time. There is currently an issue with the US server, just reported to me, so that may also be something causing issues if you try non-KoboldAI models. Use the EU server if the US one breaks, and vice versa (after reporting it so we make sure to fix it in case we haven't noticed yet).