• 25 Posts
  • 367 Comments
Joined 1 year ago
cake
Cake day: July 14th, 2023

help-circle
  • It’s definitely possible, since all the code for generators on Perchance is openly available and downloadable, but currently there’s unfortunately no “one-click” way to do this right now - and it still would require a bit of coding knowledge at this point.

    I think I wrote a comment related to this a few months back - basically you’d need to use something like ollama or llama.cpp or tabbyAPI or Aphrodite or vLLM or TGI (…etc) to run the AI text gen model (and for image gen, ComfyUI or Forge WebUI). Unfortunately even a top-of-the-line gaming GPU like a 4090 is not enough to run 70B text gen models fully in VRAM, so it may be slow. And then you’d need swap out some code in perchance.org/ai-text-plugin and perchance.org/text-to-image-plugin so that it references your localhost API instead of Perchance’s server. You’d just fork the plugins, make the changes, then swap out the imports of the ai plugin for your new copies in the gens you want to self-host.

    Someone in the community with some coding experience could do the work to make this easier for non-coders, and hopefully they share it in this forum if they do. I’ll likely get around to implementing something eventually, but probably won’t have time in the near future.









  • Yes, sorry about this. This is priority number 1 for me right now - I’ve been working for the last few days on fixing this. It has turned out to be harder to fix than I anticipated. Some sort of GPU memory error due to particular driver versions or something. That said, I should be able to fix it within the next day and a half (~36 hours from the time of this comment) unless something goes terribly wrong. I’m going to upgrade the whole stack, which should fix this issue, and also give a bit of a performance boost (slightly faster text generation) as a bonus.





  • I’ve solved the original issue already, but it sounds like you’ve found another (related) issue. If you answer each of these questions, I will hopefully be able to solve it:

    1. Can you please share a screenshot of the error?
    2. Which OS version and Safari version are you using?
    3. Does the import fail if you use incognito/private browsing mode?
    4. Does the import fail for newly created export files (e.g. open incognito, create a chat, export it, and then try to re-import it), or do you only get the error for old export files (e.g. ones you created a week ago or more, roughly)