I came back from school and decided to take a look at my generator but instead it shows this, what's the meaning of this?, I'm sure I did not break anything or did something wrong, did anyone got this aswell?, @[email protected]
My cloudfare Id: a42055e5cc8b8567
This is also the error I got: GET https://perchance.org/favicon.ico 403 (Forbidden)
The thing that always bugged me about AI generators is you get one writing style and that's it. If the AI keeps saying stuff you don't like, you re-roll and hope. The instructions behind most of them are vague anyway, so it drifts wherever it wants.
So now you can write them yourself. A model is just the instructions that decide how the AI writes its cadence, its habits, the stuff it refuses to do. There are 12 presets in there already (Fantasy, RPG, Romance, Action, Horror, Comedy, Noir, Shoujo, and more) plus the 4 built-in MoeChat models, but the point is you don't have to settle for mine. Duplicate a preset and tweak it, or start from an empty box and build the voice you actually want.
How to find it: go to Settings, scroll down a bit to the Model section and click Browse models, Pick one of the presets to see the instructions inside, or hit New model and write your own name, icon, colour, page size, and the instructions themselves. If a blank box is intimidating, you can start from a preset and edit it from there. You can also export a model as JSON and send it to someone, or import once they made.
Also one thing worth knowing: a model changes how it writes, it doesn't overrule who your character is. Your character sheet always wins.
perchance.org/moechat
There a invite link you can share in the server, dms, even outside perchance, share the link you had for example: https://perchance.org/moechat#/invite/s2qyrc76
They will enter that in the Google and enter the desire nickname they want before joining in
This is what your server will look like while it doesn't have any banner or profile
You can create a server or browse a server you wanna join, it's currently don't have one since it's in it's early state.
You can decorate the background of your server, channels, which discord doesn't have.
Create invite links as many as you want.
You can customize your server card description to something catchy or something that people would join your server
You can configure and block all the url that you think is unsafe, once someone enter a scam url you can put that in block domains.
Ban some words you want to ban in your server, what your community hates, or you don't want to hear in your server.
You can see all your members here
Create a role in your server
Organized your channels to what you want, decorate them, and other stuff.
Server overview where you set up your server profile and banner and other else
And alot more of them in: https://perchance.org/moechat#/invite/s2qyrc76
I've heard that people been talking about wanting to create an anime website on perchance, and manga, people talk's about it being impossible but it isn't, and I made them actually, I been gatekeeping this and would still gatekeep It, this generator had been created a few years ago but I wanted to tell everyone that making a anime streaming platform and manga platform is very indeed possible in perchance.
Manga
Anime
Tired of those generic AI chat community sites that all look the same?
I made MoeChat, A full Discord-style experience running inside Perchance: https://perchance.org/moechat#/rooms
Channels, roles, member list, DMs, the real Discord layout and feel.
No more ugly AI-slop interfaces.
I spend a lot of time on perchance and I keep seeing the same complaint: story generators open with something completely random. You type a class reunion four states away and the first paragraph is about a stopped grandfather clock in the house. You ask for a business conference and get a seized truck motor. People blame the model, or they blame perchance. It's almost never either of those. It's the instructions the creator wrote, and the memory system (or lack of one) behind them.
I've been building one of these (perchance.org/moechat) and I've torn apart a bunch of other people's generators while doing it. Below is what actually improves your generator, and at the end are the real prompts I use, ready to copy. Steal them, cut them up, whatever.
One thing before you read: perchance is just a box that sends whatever you wrote to an AI. If the output is generic, the instructions were generic. The model has no idea what your story is about unless your prompt tells it.
1. The model only knows what you tell it
A two-line instruction gets a two-line effort. Something like {story idea} write a story leaves the model with a vacuum, and it fills vacuums with RP slop: rain on a window, a clock that stopped at 3am, "something unreadable flickered in his eyes." That's not the model being bad. That's an empty/bad prompt.
If you want an anchor, anchor it. Who is in the scene, what just happened, what each person wants in the next ten seconds, what the room looks like. Concrete setup means less invented nonsense.
2. Tell it the size of the reaction
This is the biggest thing people miss and it's why so much AI RP reads like a chatbot. Models default to maximum drama. The player shrugs and gets a three paragraph monologue about betrayal.
Say it in plain words in your instructions:
1.) A smile is a smile. Silence is silence.
2.) Looking at someone is not a confession or an invitation unless someone said so.
3.) Match magnitude, not energy. Do not upgrade a shrug into a love confession.
4.) Do not recap what the player just did. They were there.
Sounds obvious. It changes everything.
3. Ban the model's favorite words
Every model has a house style and it will reach for it every time. Put an actual banned list in the prompt. Not censorship, just a filter for its own clichés. It works better than you'd think, because the model notices it's about to write one and swerves.
Words that should be illegal in RP: velvet, predator, "the air grew thick", "a ghost of a smirk", "dangerously sweet", "simmering intensity", "almost imperceptibly", "despite himself", "something unreadable flickered in his eyes", "it's not X, it's Y", "she didn't X she Y".
Also ban labelling thoughts. He thought: I shouldn't do this is bad writing. The door was still open. He could still leave. He didn't. is good writing. There's a full list in the system prompt below.
4. Stop dumping the whole chat into the prompt
This is the other half of the problem, the memory half. Two lazy approaches and both fail:
1.) Send nothing but recent messages. The character forgets a promise made twenty turns ago, or the injury, or the name.
2.) Send everything. It gets expensive, slow, and the model drowns in old chatter and starts contradicting itself.
The fix is a small file of durable facts plus keyword recall. Each fact gets a few trigger words. On every reply you scan the newest few messages, and only the facts whose trigger words show up get injected. So the AI remembers a thing exactly when the conversation is about that thing.
That's what kills "the AI forgot" and also what fixes "the AI opened with something unrelated," because the current scene stays grounded in what's actually been established.
Here's the prompt that writes those facts. You run it in the background every few replies. It reads only the new exchange and the already known facts, so it never duplicates:
(I've put it in the pastebin since the ... seems to be broken here.)
https://pastebin.com/raw/16anEEEu
The KEY bit is the part most people skip and it's the part that keeps a character consistent over a hundred turns. When something changes (the character's arm gets broken, a goal gets resolved, an item changes hands) it writes the new value with the same key and retires the old one. The AI never sees both versions and never contradicts itself.
For recall, match the trigger words against the newest few messages plus the current scene state, and cap how much gets injected. Mine is roughly six facts and 1500 characters per reply. More than that and you're back to drowning the model.
5. Keep a live scene state
Memory is about the past. The scene state is about right now, and it's the cheapest fix for the AI forgetting who's standing in the room or whose arm is broken. Run it every few replies:
https://pastebin.com/raw/ANFJCj60
Notice it's told to always write all six keys, with "none" where empty. If you let it skip keys it drops "Present" and suddenly nobody knows who's in the room.
6. Summarize as you go
Old turns still have to go somewhere. Roll them into a running summary. Keep the newest ~20-25 messages verbatim and compress everything older into bullet points. It keeps long chats coherent without ballooning the prompt.
Summarize the first {{n}} messages of the conversation (stop at the message ending with: "{{boundary}}"). Fold the earlier summary in. Terse bullet points that preserve: established facts, names, relationships and their changes, feelings, decisions, items, goals, promises, unresolved threads, and the current location/scene. Output ONLY the new summary text.
On top of the automatic summary, give the user a manual "recap the whole story" button, /sum style. Mine writes a detailed recap card in the transcript, and there's a "Remember" button that pins it into permanent lore so the cast really does know it. That's for the user who wants control. The automatic memory runs either way.
7. Fold the pinned stuff into one document
At some point you accumulate pinned lore and notes and it stops fitting. Condense it into a single reference document that's always in the prompt, with a hard token cap:
https://pastebin.com/raw/0itX2QDD
8. The actual system prompt
This is the big one. It's the instruction that goes on every request, with your cast profiles, world, and the current scene appended after it. It's built around all the points above: identity first, match the size of the reaction, ban the clichés, let the scene breathe, don't summarize the player's own action.
Two notes before you paste it. First, {{user}} is the player's name, swap in your own placeholder. Second, this prompt assumes your engine also sends the cast profiles, the world, the current scene state and the memory block as separate sections (that's what it means by CAST & PROFILES, SCENE STATE, MEMORY FILES, and <CONV>). If you just paste this alone you'll get half the benefit.
https://pastebin.com/raw/DbqYQZCZ
9. Match the user's energy
Last thing, and it's free. The model mirrors you. If the user types one flat line, you get a flat reply. If they type in a mood, they get that mood back. So give the user obvious controls instead of making them fight the model.
Length control (short / balanced / long), a "hold the scene" option so it stops trying to advance plot, and a "focus" option so they can point the camera at someone. Mine writes those straight into the per-request TASK line so they don't disturb the cached prefix.
Wrap up
If you take one thing from this: the model isn't bad, it's under-briefed. Give it a real character sheet, tell it how big a reaction should be, ban its clichés, and build a small keyword-recall memory instead of dumping the transcript. Do that and the random grandfather clocks stop.
I run all of this in my own generator, perchance.org/moechat. Go try it, rate it, or break it and tell me what breaks. If you're building your own, the prompts above are yours.
perchance.org/moearchive
I have to edit my post because I genuinely don't know how some of you got “I dox people” from this. That doesn't make any sense.
I built an archive for Perchance generators. Not another link list. It opens the thing up and tells you what's inside before you press Run. It actually reads the code. Point it at a generator and it pulls the real source — main.pjs, the HTML, everything in src/, plus whatever libraries it imports — then runs it through a scanner.
If the generator's code tries to access someone's camera, read their clipboard, collect their IP address, steal credentials, send data to a Dropbox or another external server, hide an invisible iframe pointing somewhere else, or do other suspicious stuff:
THE SCANNER REPORTS IT IN PLAIN WORDS. IT IS ANALYZING WHAT THE GENERATOR'S CODE DOES. IT IS NOT COLLECTING THAT INFORMATION FROM YOU. MOEARCHIVE DOESN'T STORE OR STEAL YOUR IP, CAMERA DATA, CLIPBOARD, OR WHATEVER ELSE.
ACTUAL DANGEROUS GENERATORS LAND IN QUARANTINE with no “open” button, but you can still read the writeup and comment on it.
You can check anything yourself. Anything the archive hasn’t reviewed yet has a “check it yourself” button. Same scan, runs in your browser. Nothing is saved or sent, and if it couldn’t read part of the source, it tells you instead of handing you a fake source.
Not convinced? Ask for a real review. There’s a button for that. The requests stick around, so you can see that other people want the same generator looked at, and the queue works through the ones people asked for first.
Reviews don’t rot. Once something’s reviewed, it’s watched. When the creator edits it, the archive pulls the new code, and if the source really changed, it gets reviewed again. The entry page keeps a short change history so you can see what changed.
Kudos you can trust. Counts live on the server, one per account, so you can’t fake them from the dev console. Comments are threaded. You don’t need an account for either one.
The directory is cleaned up. 42,279 names, with machine-generated junk names filtered out. Reviewed ones come first, then credited creators, then everything else. Every row has a cover or a colored monogram, so there are no blank white boxes.
Creators get invited and can post what they’re working on. If a generator is publicly credited to you, your creator name shows up on it instead of “N/A”. THE ARCHIVE DOES NOT EXPOSE PRIVATE INFORMATION ABOUT CREATORS OR USERS.
It’s AO3-styled, because that’s the right vibe for an archive.
You can also vote with kudos to push the generators you want to see higher in the directory.
You don’t really have to sign up. Just go browse.
The AI can sometimes flag generators incorrectly or put them in Cautious. If that happens, there’s a report button where you can explain why you think the flag is wrong. Those reports can be reviewed and used to correct the classification.
