Sorry about that I accidentally deleted the topic lol
Every choice transforms your body and shapes your adventure · By
I had a few worlds like that the problem I found was either typos in world generation for the AI to fallow or the world is to complex for the settings in AI parameters. I've never actually come across a corrupt world yet I do play on a PC and smartphone I hope this helps a little I'm not really tech savvy.
Word discovery is a way to browse and download world's created by other players. By clicking on the menu button and selecting world discovery it. You can also create your own world by selecting new word from the menu button. The world's you created can also be uploaded for other players to download and play by clicking the upload world button on the menu I think.
That's the thing, I didn't due to me thinking the worlds were "finish" (definitely a dumb move on my end), if they somehow manage to get the fixed worlds back, I plan to download em right away as back up in case something like this happens again. Also I didnt loose ALL of my content on it, just 2 of my worlds got sent back like 3ish months and undid a bunch of fixes i made to them.
you can try checking in '..\AppData\Roaming\formamorph' and copying everything in there over to the 'userdata' folder in the new version. Either way though, all you need to do is export your worlds and then import them into the new version. it's all backwards compatible, including saves. Just takes a bit of time.
OMG I got it working.
I enabled the CORS (Cross-Origin Resource Sharing) setting on LLMStudio and now it works. So it was something on my end.
LLMStudio probably screwed up when it updated.
That is still managed by FieryLion, I have no control over that.
Something to keep in mind though. Renting GPUs to do anything is super expensive right now, especially so if the task is AI related. The model change was to try and get something that won't be unreasonably expensive to pay for. Best option if the current quality isn't good enough is to either create an account on an LLM hosting site or try out local stuff. Small LLMs able to run on <4GB of VRAM are surprisingly good for the hardware/effort required. The desktop app runs models natively and has a few suggestions of small models to try out which can be downloaded directly in the app itself, no technical skill required.
I keep getting errors about processing the AI request and the provider returning an error but the openai activity page shows no errors. sometimes it just goes through with no changes. Thoughts?
