If we open the gallery comment channel in the main comment tab like #image-7f11127feeec215969ad87b32 ;

The comment pop-up of that gallery post will be locked! Until you close the chat channel tab.

Have you recently noticed the submit function in the chat acting weird or buggy? It sometimes returns [undefined] when used — not sure if it’s broken or just lagging. Anyone else seeing this?

(the context of chat isn't having anything sus)

Some of users suggested a gallery comment notification, which is already possible via desktop notification pushing - but might harder to do anything further I supposed.

Another user suggests comment counter badge superimposed on top of it, which would work like chat unread channel - it seems need a hard work but might be more feasible??

It's obvious switching IP leads to ban evading. But some of those troll would not bother changing their names(or they don't care, or they want to brag, or don't even know they are banned).

Anyway, the suggestions is that user name, nickname in chat, and gallery title and description could also be moderated.

OMG they are emojis!!!! Arghhhhahhhhh 🔍⭐💬 oh no!!!!!

I still don't get it why we need 5 days on chat. The rule brings only hardship and path to bugs. People gonna abuse it? The storage on server is limited? Why we could instant create gen and Perchance account, but not the username?? (And why it needs a trust score?)

Ai chat bot outside of AI chat gen.... Under comment plugin such as t2i image gen.... They died. They can't populate text.

recently many users experience unstable pfp which shows a ?

this normally happens when WiFi sucks, but the frequency dramatically increased and being universal to more users...

! !

Is the server being laggy?

Across different gens: Several users are experiencing issues with the Perchance public gallery. While they are able to upload images and receive working image links, their content does not appear for other users. Additionally, after refreshing, their own posts may disappear from the gallery. Notably, this issue seems to affect only 18+ (NSFW) images—SFW posts appear to upload and remain visible without problems (though this is still a working hypothesis). Common troubleshooting steps like clearing the browser cache have produced inconsistent results.

With helps and efforts, finally, In this testing gen everything seems working and fine testing gen

HOWEVER, when trying to implement the searching function with a real live gallery in gen here, the gallery won't update at all!! (please note how the zoom function works smoothly)

because AI points that the iframe there isn't working <div style="width: 100%; height: calc(100% - 65px); overflow: hidden;"> <div id="galleryContentEl" style="width: 100%; height: 100%; transform: scale(1.0); transform-origin: 0 0;"> [image(settings.galleryOptions)] </div> </div>

So it recommended change it from that to this in this gen. <div style="width: 100%; height: calc(100% - 65px); overflow: hidden;"> <div id="galleryContentEl"> <iframe class="text-to-image-plugin-gallery" src="https://perchance.org/friendly-notification-and-concept-board-animation" style="width:100%; height:100%; border:none; transform-origin: top center;"></iframe> </div> </div> Yes, the searching function works!!. But now the zoom control is a mess; even if that's fixable(harder than it seems); the side panel gallery in the lower right blue button isn't loading at all. (the side gallery is here <div id="chatIframe4" style="width: 100%; height: 100%; overflow: auto; zoom: 0.55; border-radius: 0.25rem;" hidden>[image(settings.galleryOptions)]</div>)

Because I use and only only know vibe coding and now I am complete screwed and cannot vibing anymore. It seems somehow basic but I just cannot get it done because I know nothing.

Please, help!!!

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!

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.

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!

Has anyone experimented with secret annotations in prompts?

In older SD models, we could include things like \[some message::0\] in prompts — text that would be ignored by the model but still included in the raw input. This allowed us to embed metadata or trigger filters without affecting the image generation.

For example, we used \[ContentLabel::0\] to signal age restrictions. Our filter system treats this as a PG-13 banned prompt keyword, so users could self-label their content by adding it.

However, it seems that in newer models, this trick no longer works. Possibly because prompt weighting syntax like :: is no longer interpreted the same way — or ignored entirely.

Did anyone find a working alternative? It's important for us since we rely on this system to label and filter user submissions.

!

Here's my container or iframe for multiple plugin or link

... <div id="chatIframe4" style="width: 100%; height: 100%; overflow: auto; zoom: 0.55; border-radius: 0.25rem;" hidden>[image(settings.galleryOptions)]</div> ... Only the [image(settings.galleryOptions)] would be stuck in initial load in color scheme; the [commentsPlugin(settings.defaultCommentOptions)] ; [settings.introMessage] ; perchance uploader or private gallery would sync with the gen theme toggle.

Before this I use long src url methods and it could have theme updated too!!

What's the trick here?

There have been many banned users—whether from chat or gallery—who claim they never committed the violations in question. Maybe they’re not telling the truth, but sometimes it really seems like they share the same IP ID or are using the same VPN. I don't know if that's actually possible, but I tend to believe them.

This makes the need for individually deleting or hiding gallery images even more urgent. We shouldn't ban everyone affected just because of someone else’s actions.

Heads up: >Files will soon no long be accessible via the old user-uploads.perchance.org domain unless they're programmatically requested from a generator. I.e. images used as backgrounds for generators, JS files imported, etc. should all continue to work without switching to the new domain (though I still recommend that you switch to the new domain). But if you want to view your file in the browser (i.e. by pasting the URL in your browser's address bar), then you'll need to use the new user.uploads.dev domain.

now should the old custom emojis we uploaded be safe to use in user-uploads.perchance.org domain, if only used in comment plugin?

or should we start transferring them to the new domain?

The dev change the file uploader url from

user-uploads.perchance.org/file

To

user.uploads.dev/file

But the pfp authentic validation didn't change it's rule

Now people are prohibited from uploading new pfp

I wonder if new emojis will suffer the same fate

I've noticed that certain terms or tags are causing rendering issues with the new model. The outputs are highly unstable and inconsistent—beyond what I would consider normal variation.

This doesn't appear to be due to new interpretation logic or prompt strategy shifts. Instead, many of these generations look glitched, underprocessed, washed out, or as if rendering was prematurely stopped. The saturation is often low, and overall image quality degraded.

I suspect that some of these tags may be acting like "stop codons", halting generation early—possibly similar in effect to using guidance_scale = 1.

From my testing, the problematic tags seem to fall into two groups:

Furry-related terms: furry, fursona, anthro, etc.

Illustration-related terms: drawing, line work, cel shading, etc.

It’s possible these tags are being masked or diluted when mixed with stronger or more stable tags, which may explain why some prompts still produce acceptable or mixed results. However, when multiple of these unstable tags are combined, the generation almost always fails—suggesting a kind of cumulative destabilization effect.

By contrast, photography and painting-style tags remain mostly unaffected and render normally.

Thank you the developer 😀 Although there are many drawback especially with furry aspect, I think you might got overwhelming negative here and there, but the upgrade is indeed overall an improvement. You deserve the appreciation! 💕