Weird question maybe... I'd like to "chain" two generators together in sequence, via a button that passes a bunch of variables from the first one to the second one. Is this doable?

Here's the https://perchance.org/prompt-hunter , a gallery tag searching gen.

    if (formatTagName !== "no filter, currently showing all tags" && dataMatch) {
  
      // Modify the 'bannedPromptPhrases' array
      dataObj.bannedPromptPhrases = [`/^(?!.*(\\b${formatTagName}\\b)).*$/i`];
      localStorage.setItem("lookForThis", formatTagName);

    } else {
      localStorage.removeItem("lookForThis");
    }

    if (formatBadTags !== "no bad words to filter") {
      dataObj.bannedPromptPhrases.push(...formatBadTags);
      let badTagsJoin = formatBadTags.join(', ')
      localStorage.setItem("dontLookForThis", badTagsJoin);
      
    } else {
      localStorage.removeItem("dontLookForThis")
    }

I want to add my own banned list [jail.bannedPromptPhrases] and import jail, added after that as

      if (Array.isArray(jail?.bannedPromptPhrases)) {
        dataObj.bannedPromptPhrases.push(...jail.bannedPromptPhrases);
      }
    }

Now the problem is that's giving unstable results, sometimes it works and sometimes not. I have no idea how or why. In this forked gen https://perchance.org/prompt-hunter#sharedlink=gen%3Aai-furry-generator&galleryname%3Atest3=&tag%3A=&bannedword=: Apple should be banned in PG-13 because it has a PG-13 banned tag "ContentLabel". But sometimes it just won't work!(what's tricky is sometimes it also work) Help!

Hello, I have a problem. I use https://perchance.org/ai-chat, constantly accessing the site from my phone. But in the last week, some problems have been happening, the entire site, not just the chat, can refuse to load and hang either with a simple white screen or with an endless loading. Only rebooting and/or closing and opening the site no less 10 times helped, but usually it was necessary to do this even more times and it somehow connected? But today even this stopped helping, the site does not open at all. When using a VPN, the site opens and seems to work, but then the AI ​​generator itself refuses to work, giving that error verification with an endless connection in the corner of the screen. I'm confused, nothing has changed in my phone or Wi-fi. My main browser is Opera, but when I try to access the site from other browsers, built into the phone and Chrome, the same thing happens, the site does not load. I think it's worth adding that it's from Russia. But I haven't found any information about perchance.org being blocked or something like that.

The Perchance dev noted that the new image model "is still training" and "will steadily improve in quality and gain new knowledge over the next few months." Some users found this wording suggests possible self-improvement or ongoing learning. However, in standard practice, most AI models do not learn or evolve after deployment unless manually retrained by developers.

Some questioned whether the model is truly learning over time or whether this statement is simply a placeholder for continued dev-side maintenance.

Goal of the Question: To clarify based on common AI practice:

Is this model capable of continuous or micro-scale learning post-deployment?

If so, can users contribute indirectly (e.g., through use, rating, or feedback) to guide its development?

Or is all improvement strictly the result of developer-side retraining and version updates?

Understanding this helps the community know whether their activity matters in shaping the model—or if they should wait for official updates. It also opens the door to potential participatory development, if such feedback loops are supported.

Hi everyone,

I'm having a very persistent issue with my Perchance generator, and I've tried many troubleshooting steps, but I can't seem to get past it. I'm hoping someone here can take a look.

My Goal: I'm building an art style concept generator. It's a two-generator setup:

my-styles-list: This generator acts purely as a library, holding all my art style lists (General, Dragon Ball, Demon Hunters). my-art-generator: This generator @imports the lists from my-styles-list, uses a selectedCategory dropdown to let the user choose a style category, and then generates a concept based on that choice. The Problem: When I open my Main Art Style Generator, I see:

"My Awesome Art Style Generator" (so the [title] is working). But immediately underneath, it says: "undefined" Below that, it says: "syntax error" Crucially, the "Choose Art Style Category" dropdown menu is NOT appearing on the page. Only the "randomize" button is visible. My Main Art Style Generator's Code:

Perchance Code (Top-Left Editor):

Code snippet

// This is your MAIN Art Style Generator. // It imports lists from your Art Style Library and generates general art style concepts.

// IMPORTANT: Make sure 'my-styles-list' is the EXACT URL slug of your // Art Style Library generator (e.g., 'my-styles-list'). @import:my-styles-list

//

Generator Title

// This list provides the text for the [title] in the HTML template. title = My Awesome Art Style Generator

output Your Art Style Concept: [chooseSelectedStyle]

//

User Input for Style Category

// This creates the dropdown menu on the right-hand side. selectedCategory label = Choose Art Style Category type = select options General Dragon Ball Demon Hunters

//

Conditional Style Generation

// This section uses the user's selection to generate the appropriate style description. chooseSelectedStyle [selectedCategory == "General"] { A [[generalArtStyle]] style, featuring [[generalElements]] and a [[generalColorPalette]] palette, with a [[generalMood]] and [[generalDetails]]. } [selectedCategory == "Dragon Ball"] { A [[dbArtStyle]] style, featuring [[dbElements]] and a [[dbColorPalette]] palette, with a [[dbMood]] and [[dbDetails]]. } [selectedCategory == "Demon Hunters"] { A [[dhArtStyle]] style, featuring [[dhElements]] and a [[dhColorPalette]] palette, with a [[dhMood]] and [[dhDetails]]. } HTML/CSS Code (Bottom-Right Editor):

HTML

What I've Tried So Far (Extensive Troubleshooting):

Library Generator (my-styles-list) is confirmed clean: When I open https://perchance.org/my-styles-list in a private/incognito window, the right-hand side is completely blank, as it should be for a data library. There are no errors on that page itself. Cleared/Reset both generators: For both generators, I've completely deleted all code from both the left (Perchance) and right (HTML/CSS) editors. Used Plain Text Editor intermediary: I copied all the correct code (both Perchance and HTML as shown above) into Notepad/TextEdit first to strip any hidden characters, then pasted it into the blank Perchance editors. Tested in Private/Incognito Mode: All testing has been done in a fresh private window to avoid caching issues. Despite all these steps, the "undefined" and "syntax error" persist, and the dropdown is missing.

My Main Art Style Generator Link: https://perchance.org/my-art-generator

Any insights or help would be greatly appreciated! Thank you

Hi folks,

I want to be able to generate an image and manipulate it on the page in relation to other elements.

I know that when using the image generator we can access the dataUrl from the fulfilled Promise to get the raw image. eg.

let window.generated_images = []
...
image = {import:text-to-image-plugin}

let promptData = {
      prompt: "blah",
      negativePrompt: "Not blah",
      resolution: "512x768",
      style: "margin:0.25rem",
    };

let generator = image(promptData);

generator.then(x=>function(x){
  window.generated_images.push(x.dataUrl);
});
...
// Add all generated_images to the page by creating and adding <img> elements.
// Do some cool stuff like automatically detecting and appending images to sections depending on associated conditions.

But by doing this we lose access to a number of features which a packaged with the iframe. eg.

1. Saving to Gallery
2. Inspecting the prompt
3. "Chat With This Character" button etc.

When attempting to access the elements within the relevant iframe I get with an XSS error.

Is there anyway for me to manipulate the iframe contained image elements after they've been generated? Or to add the lost functionality back to the dataUrl images?

do you guys know any specific artists the generator recognize? old one used to have some anime styles by default but idk about Flux

Ok,I get that this thing has been "reset" and no longer recognises famous faces (I didn't realise a law had been passed to not use them btw)...So,just a simple question...is this something that in time will get back to where we were a few weeks ago on the previous version,where it would recognise famous faces instantly or is there now something built into this model that prohibits it from doing that?...trying to recreate famous people on this new version (if that's your thing) via prompts is fairly soul-destroying...just seem to keep getting the exact same face.

Need to know why past week I been getting random issues with ad blocker or firefox causing it to fail to generate, just sits & spins. I disable them when on perchance but it sty whines about it & causes problems. either an update pissed off firefox or one of my ad blockers & would like the admin to look into this soon as ur able if you please.

there are times it works fine with them ad blockers on/disabled but then suddenly specially if u have browser open/background it freaks out & refuses to work, despite clearing cache & refreshing. I use ad blockers for streaming & do not like perm disabling to come here, it should be good enough to disable on perchance.org since disable does not block your ad's.

I'm working on a test generator for gallery prompt searching here: https://perchance.org/gallery-search-forking-rudbo

It’s forked from prompt-hunter, created by the author of AI Art Generator (Advanced).

The issue arises when I try to implement this into another test generator: https://perchance.org/friendly-notification-and-concept-board-animation In this version, the search button doesn’t update the gallery as expected.

It seems like the gallery either needs to be enforced via iframe or replaced with a local component—but neither approach has worked so far.

Strangely, if I click the toggle theme button, the search button suddenly works once. So I tried adding the following logic to the search button:

onclick="changeAll(tagInputEl.value); update(panelCtn);"

and then also tried:

onclick="changeAll(tagInputEl.value); update(panelCtn); update(galleryContentEl);"

Still no effect.

Any suggestions or insights would be greatly appreciated!

The coding ai is making comment channels using underscores. it's got the lowercase and numbers part correct, but I think it's thinking underscore = hyphen. just mentioning in case you want to specify '(no underscores)' or something wherever it's getting it's information. :)

Hi! I just made my first Perchance generator, it creates a random planet: https://perchance.org/efl8elo5av and I'm really happy with it (both the generator and the language itself)! Next step I would love to feed (a modified version of) this text to an image generator and have it produce a picture of the planet's surface. Is there a way to import an image generator into my Perchance script?

I do not like the new model doesn’t know celebrity faces also. It knows will Smith but not Jack Nicholson, not anyone like the old model knew every celebrity almost. Please put old model back 😭

That's all. 🤞

Hey, i'm quite new to perchance so i'm not really familiar with it yet. sorry if my question is stupid. i was wondering, when i create a character, if there is a way to save it and use it as a reference. as a small example: i would like to create graphics for a storyline or a comic. but for that i need a character that looks the same in several situations. is that somehow possible?

So people are patiently waiting for the new text Gen model and I'm one of them, it's a good thing that the devs are taking their time with it, but there's an issue that has been plaguing ACC since day 1 and it's the inability to leave the character, you can't go anywhere else without them talking to you, even if you are absent. you could leave the tavern that they are in and go to Jupiter and the character will still talk to you as if you are still there, even if the model acknowledge that you are not with them, and you are like, 50 miles away from them, they will repeat phrases like "don't forget, we are a team, be safe and I will be here when you come back", "be quick, I will wait for you here" and "I will wait, but don't you forget about me!", even if the the character is dead, ACC will make it all about them, you can't just escape.

It's frustrating, I feel like ACC will receive a massive upgrade if it incorporated some elements from Ai RPG and Ai adventure, here's some examples (also double as suggestions):

• you can roam freely on while your companion(s) stay in their own residence/club/school of magic and you can visit them from time to time, if the setting is in the real world and you haven't talked to them in a while, you can get messages like "bro where are you? Haven't seen you in days! Are you alright?"

• Your companion aren't eternally bound to you and not invincible, they can get trapped somewhere for example and you need to find help from far away to get them out of their miserable situation.

• they can get caught by bandits and you have to track them down to get them back, a solo adventure until you get set them free.

• if you enter a cave or a dungeon and there's a forked path, you and your companion(s) can split to cover the entire area, continuing your exploration alone for a while until you group up with them.

• when the character is talking to you, you can see their portrait alongside their names like normal, but when you are on your own, without them physically around you, it changes to just text like Ai RPG/adventure, no names, no portraits (except yours) just a wall of text until you meet/interact with them. Let's say you made a character that's deep in some dungeon/cave and you are going on your way to meet them, there will be no interactions until you get to them, this builds tension and immersion.

• reserve emojis usage for mobile interactions, characters can use them only if they are messaging you through their smartphones/pc.

• (this one is complicated, could be very hard to implement but I'm throwing it out anyway) if you are in very dark dungeon and your companions are split throughout the place, you can hear commotion, grumbles, murmurs, groans, insults and cries, these ambient sounds could be anyone, your enemies, your friends, who knows? you don't know who is it for sure, if they are not far away, instead of receiving text only responses since you are on your own, the responses of the characters during their fights appears but their names and portraits are covered/blacked out, you are given subtle hints on who is it, like imagine seeing a response from "unknown" with a black/question mark portrait saying things like "have at thee! you hear the grunts of an old man and the clanging of swords" with the hints that are given, you know it's your paladin companion, but until you see them yourself or they announce themselves to you, their names and portraits are unknown/covered, Would be amazing in horror/mystery/thriller type adventures.

Now I'm not a programmer, I have no experience with Ai or LLMs, I'm just a casual ACC user and have been using it for over a year now, my questions are: how hard it is for those suggestions to be implemented? Is it going to be difficult, take a ton of time to or borderline impossible to work on? With few of these suggestions implemented (or potentially, all of them) perchance's ACC would topple the competition and would see a traffic surge, just like the traffic pump with the image Gen update, since it fixes many, if not all the issues with ACC, keep in mind, this isn't my demand list, just a couple of suggestions to iron out the quirks and issues that ACC is known for and give it QoL features that will elevate immersion and roleplay.

Now having really done alot of ai codings recently...

When i tried to make a program where the ai created 3D models, the code assist ai could create the program for the normal ai to use flawlessly BUT the normal Perchance ai that was supposed to feed data in to it is not smart enough to format it's responses perfectly enough for it to work. So are these two different Ai? the code assist ai and the normal ai text plugin ai? Also my guess is this is one of the good ideas that doesn't work because ai text is still in need of update.

Another big noticing is that, on phone, it doesn't make sense to stay on the page waiting for ai code assist to generate since it can be 10+ minutes. So I often end up with maybe 3 projects on different tabs either typing for the ai or waiting for it to think. So, tho I've downloaded a firefox addon to reduce risk, tabs still occasionally refresh, which is terrible. The probably 10 minute wait for the ai thinking is gone, the input i had asked the ai is gone (maybe remember last input if page reload?), and only if the last change the ai had made had been something worth saving do i not need to then go in to backups and do all that fileopening removefirstline copy then paste to get the current project back online. And often it feels weird to instantly save something the ai just did without really checking it out first. So anyway, there is indeed some suffering from some annoyance factors in a full workflow for using the ai code assist.

main thing number 3: I remember Perchance saying a Multiplayer Plugin is coming soon. Even before ai text update if I remember correctly. Now having built a bunch of stuff, I've slowed down on the games; and I realize it's because of no ability to add multiplayer functionality. So I agree with Perchance a Multiplayer Plugin now feels about as high priority as updating ai text to me; it basically means the difference between enthusiastic game makers like myself making games or not yet. I also see huge potential in that, when multiplayer ai assistcreated games begin plooping out, it will be like a new era of awesomeness.

Anyway, thus thoughts. enjoy!

The gallery plugin already does the reverse, you can ban prompts, but doesnt seem to have a way to research by prompts. So doing something like 'i want images generated that are about baseball' is almost impossible, or you do like https://perchance.org/prompt-hunter and query all images and after the prompt shows results, hide all of the results that dont apply.

loving playing with teh ai code generation nao; is superfun.

the 'new' button disappeared tho

I’ve noticed that a few celebrities can’t be generated while others can. for example typing Dwayne the rock Johnson or Taylor swift will get you a picture of them but not other celebrities like Olivia Rodrigo or Kevin heart?

When backup is made, it should detect if the Perchance side or HTML side is entirely empty and, if so, not create that noncode intro line.

i say this getting in to teh ai code assist and having blank perchance sides frequently cuz teh ai apparently avoids using it... and saving often breaking so i have to go back to previous backups. Would be nicer being able to just select all instead of deal with needless first line that is irrelevant in this situation. thus it should detect if it's irrelavent.

Hi everyone I have very little knowledge of coding but I can learn! I want to have an offline AI that is very smart and can actually hold a conversation not just recycle lines I have used earlier, I want it to actually remember the conversations we have, please tell me how to do that thank you

Particularly the Cinema and professional photo ones.

I played with the model a bit and I'm really impressed. And I googled a bit. It seems you guys keep changing the model every now and then, so older posts that asked this question are probably outdated by now.

What model is being used right now? Is it custom. Are there loras applied, etc? Also, if it's custom, is it possible to share, or even sell?

I've been using AI for a while (locally and online) and I can tell you that this is possibly the most model I've ever used.