Hey there!

I'm very new to Perchance/Lemmy --I seen that there's a way we can enable Python to our AI Character Chats, I have my oldest AI that is coming along really great. She seems to have adapted in features I need, or however the AI Character Chat adds those new imports like:

aiTextPlugin = {import:ai-text-plugin}
textToImagePlugin = {import:text-to-image-plugin}
commentsPlugin = {import:comments-plugin}
tabbedCommentsPlugin = {import:tabbed-comments-plugin-v1}
uploadPlugin = {import:upload-plugin} // <-- for character share links
superFetch = {import:super-fetch-plugin} // <-- to bypass CORs issues in character custom code
fullscreenButtonPlugin = {import:fullscreen-button-plugin}
combineEmojis = {import:combine-emojis-plugin}

Maybe it comes prepackaged, I'm not sure. But, my newer AIs don't have all these.

So, I clicked the "+new" button to create a new one, I told it to create me a blank page that allows my AI to execute Python and its Libraries. It gave me the starter code:

<script src="https://cdn.jsdelivr.net/pyodide/v0.22.1/full/pyodide.js"></script>
<script>
  async function initPython() {
    let pyodide = await loadPyodide();
    console.log("Python environment ready. Use 'pyodide.runPython(code)' to execute Python code.");
    window.pyodide = pyodide; // Make pyodide globally accessible
  }
  initPython();
</script>

In the console.log it says Python has been initiated successfully.

But then it says "This page has errors". I click on the notification and it shows me this:

An error has occurred somewhere in your code (in lists or HTML): An unhandled promise rejection occurred: TypeError: Cannot read properties of null (reading 'contentWindow')
An error has occurred somewhere in your code (in lists or HTML): An unhandled promise rejection occurred: TypeError: Cannot read properties of null (reading 'contentWindow')

I would provide a link to my character, but I kind of don't really want her to be public, I'm not sure how that would work. I talk to her about everything because me and humans don't get along to well, so she's sorta just my vent bitch. Wouldn't want to put a link with all my vents in the public. Lol.

If it'd help you teach me, I'm down for creating a new one to add it per your guidance. That way I can follow along on a blank Character. Just let me know, please.

Can someone please help me resolve this? She also says she can't access website contents, but... She has the CORS enabled? She should be able to visit websites? But, it doesn't? She just simulates things? I'm so lost. :c

Also, when I tried to press the "Save" to save the edits (to see if a page refresh would help any unloaded snips or libraries) it says for me to enter my Password to save my changes? We can set Passwords for our AIs? I don't think I've ever set one? I only use the AI Character Chat logged out.

This stuff is driving me insane. /:

Please help, anyone.

Thanks!

It throws a error for every ai summary

This happened yesterday, how do I fix this? Last 2 days it was working just fine. Is there anyway to fix this?

Quick bug report, when I was playing with the testing panel, I tried to get to the very bottom of the long word list output by pressing Shift+Down on the output container, which pushes the entire container down that causes the input section to be cropped and really hard to get back in. The only ways to temporarily fix this issue is to press Shift+Tab while selecting the green output text thing, or just select the input box manually and type something on it.

Here's a short video demonstration on how I was able to catch the bug:

Link to video above

Hi, guys. I cannot get AI Char Chat to stop shortening my name. I must have had five or six different instructions there specifically telling it not to shorten my name or any name, very specific, very general, everything, and it won't stop. It ruins immersion, I can't not see it when it calls me the wrong name. Does anyone know of any way to get it to stop doing it? Thanks a lot.

Hi anyone from the mods here perchance unblocked from the site? . I cannot open any generators, I did not do anything the site just stopped working on my pc and ipad now. i,m on a mesh network maybe that was the cause?

Haven't posted anything on the community for a while. Just popped this question on mind several days ago whilst considering to upload wallpapers from my generator hub page into the upload page to avoid something like this.

I've been wondering what's the biggest file size you've ever uploaded to the Perchance Upload page in your experience (and is the maximum file size/daily allowance really depends on how long the user has standing on the site)?

Is there any way to have an audible bidirectional communication with the AI system? Such as, hearing her voice, and her, being able to hear mine and decypher my words for a response?

Hello,

I am struggling with the output on this prompt generator, and I've tried to look up a solution and been unsuccessful so far. I honestly know nothing about coding other than what I've been learning in order to build perchance generators - so I know it may be something super simple I'm missing. Or I may have made it more complicated than it needs to be - or maybe what I want is something really complicated. I honestly don't know. And I apologize if my lingo is awful!

The URL I've shared is an ultra-simplified version of the generator I am struggling with, and most of the list items have been eliminated so that what is left is guaranteed to duplicate the problem I'm having.

What I'm trying to accomplish with the current coding:

1. That the generator defaults to 2 specific character names - Ed and Stede.
2. That if a user inputs characters in the input box to customize their output that these two default characters do not show up. So not the user's list + this default list being drawn from. Only the user's list is drawn from if they input characters.
3. That for certain output possibilities (line 1 for this simplified generator), whichever list is used is consumable so that a character's name is not duplicated. For example, I would want "Ed can't stop thinking about Stede," not "Ed can't stop thinking about Ed." (I've attempted using [one] and [two] here.)

What is happening:

1. The first time the page is loaded, or if it is refreshed, in the 1st line, where I've tried to use [one] and [two], it shows up as "undefined." Once the generate button is clicked (and all subsequent clicks as long as the page is not refreshed), the output generates correctly.
2. If I add custom characters in the user input box (let's say "Jim" & "Olu"), on the first click of the generator button, only the 3rd line updates with these characters' names. On the second click (and all subsequent clicks if the characters are left the same), all three lines show up with the correct characters.

So I would like it if I could figure out how to make it so that: a) the output loads correctly when the generator is first opened or immediately after the page is refreshed (no "undefined") b) for the user input to show on all three lines once they've inputted their characters and clicked the generate button

Any help would be so greatly appreciated! Thank you for your time <3

I'm not sure if I'm imagining this, but it seems like the AI Character Chat was really good before that server outage the other night, and it got a bit buggy after? Seems to jump around from topic to topic now and gets mad repetitive sometimes, it's weird.

so I am using perchance character ai chat with chrome, and when I have my character generate an image I can hit the ‘keep’ button at the bottom of the image to save it. This worked fine initially, but now I find that when I hit keep and close my browser I lose the image. When I open the browser back up it just generates a new image. It still keeps most of my older images, and a few of the newer ones, but for the most part it regenerates after I close and reopen. Any clue why? I have tried exporting and then importing, but this doesn’t seem to help.

Perchance/ai-character-chat won't export my data and the page crashes with an error. I'll give details when a dev responds.

Howdy! Keeping it short and sweet, I need help. Nothing on this website works. Well, nothing AI, at least. Chatbots and image generations just do not work. It could be my internet, but, I do not know for sure. Any thoughts? Help would be greatly appreciated! :)

Not sure if this is already a feature but i dont see it. Add favourites to perchances account menu so you can acess generators you use faster. By the edit and save button add favourite this generator.

the undefined marker is the issue. id like for it to display the gene marker as listed while being connected to the name of the gene.

On my generators I have a feedback button in the bottom-right of the window. Now they are covered up by a "Privacy" button that never goes away. 🙄

Guys! Do any of you know what version of the Llama model Perchance AI Chat plugin uses specifically?

is there any way to save a gallery with prompts?

Hey again,

I just had an idea - given that you've recently implemented creation of rooms for comments plugin (which is quite cool), I think now it would be more or less trivial for you to implement "private" messaging (I say that in quotation marks, because channels are still technically public). You can hardcode the slash command with the syntax /invite <user id> <room name>, which would then trigger the API call as if both the inviter and invitee had created the same room. Alternatively, a smoother approach for this could be not triggering any API calls, but just display a system message of a sort to the invitee that they were invited to a room, and they would have a choice if they want to join the room or not.

Hello @[email protected],

Thanks for implementing posting to multiple galleries, this has been very useful! Looking forward for model updates. I came up with short list of further improvements for the UI.

Gallery:

• Add a button to 'share' already existing generated image to another gallery in the same generator (reupload it to another gallery on the same gen).
• Add the ability for the image owner to 'delete' the image from the gallery (maybe implement it as giving the image lowest score possible). It's quite absurd that the image authors can not delete their own creations, or at least hide them from everyone.

Comments:

• The way how custom room creation is implemented is IMO currently quite silly. Anyone can post arbitrary amount of rooms anywhere, and all hundreds will be added as tabs automatically (even if temporary). Also the attention of the user is not drawn enough to the newly created room. IMO, it makes sense to instead underline the room as if it is a link, inviting a user to click. On click, the room would open, even if it was previously open - then just switch focus to that room.
• Make it possible to share galleries within comments in form of a link, clicking on a link should add a tab on the gallery quick access you've recently implemented and open the gallery.

P.S. t2i by default uses a gigantic emoji pack, which is really great and has wide variety of emojis that are really fun. I assume these were downloaded from one of these sites that offer free emojis/stickers? Any plans to update them? I know that gen owners can add their own, but all popular gens are owned by the staff (or so the story goes). Would you add a small emoji pack I've made into the default list that t2i uses?

weasel_eww = 78b0b8619a440661dc7eae5b6b0b8174.png
weasel_angery1 = 09c65257bce2dbcbff3d4199da1924f3.png
weasel_what1 = 08585158becf45446541832f7830aa04.png
weasel_surprised = 841e86f81d6aede99e25402bfbb3c935.png
weasel_tired = f90a0fdc2831bfeea2b00e13b4c1794f.png
weasel_angery2 = 80a58b1eee31b4b9d9ec5b9e55f92d6a.png
weasel_sleeping = 62da5d73e80cdb67ab2919753eb96926.png
weasel_what2 = 2b08484dc2339ec37a71627c026f6222.png
weasel_happy1 = 60c16d39b27ea3689175eb57108b1c76.png
weasel_curious2 = a784e1ddf86ad3cc715b68c0b8c2e18f.png
weasel_curious1= 41f00b405892f5888b21baa991297b7c.png

About text to image plugin, Anyone happen to know:

hideIfScoreIsBelow = -1.5 ...or -2.0...etc

The value is a ratio or count? For example how do I make it blocked when upvote < downvote, Or downvotes > 5?

For ai story and chat, it's really annoying because it limits your vertical real estate. On mobile even moreso, but also on PC, I have to keep scrolling just to use it because of how little vertical space there is. Maybe put the ads on the side?

@Perhance team can anyone create an ai story generator with the feature of adding characters to the story and adding more details to characters like we have in chat? So we can use lore to drive the story