One thing noticeable - I am never seeing any of those “Failed: Retrying” or “Image failed to download” messages you sometimes see in the inline frames. Instead, it just seems to fail, not try again, display no message, and just drop the attempt, leaving a blank frame in Firefox, or a frame containing the text of the prompt in Chrome.

Same thing happens in Chrome.

Firefox v158.0b5 (64-bit) (most recent). All plugins disabled. No VPN. This issue started in the last week. Timing is weird… sometimes it happens very quickly, others it sits on “Processing” quite some time before giving me the blank frame. The “blank frame” has buttons for download, refresh, etc, just no actual image.

Also, maybe unrelated, but getting a “interactionPointerMoveHandler” error on load of page often as well ?

The “Anti-Bot verification failed” message has changed, and now ends with “Error: undefined” or “Waited too long for token.”

The problem will continue randomly until, at some point, verification passes and it will work for a few hours, then this will start again.

Every attempt to use Image Gen on Perchance turns into an hour of fighting for verification before anything else can be done.

This happens all the time. Been happening for months. Works like a champ right up until it doesn’t. No changes on this side. Never permanent. Happens randomly throughout the day, every day. Always annoying. I’d bet dollars to doughnuts this IS a config error on the Perchance side… if this was a Cloudfare issue, it would happen almost EVERYWHERE.

Some garbage shit that repeatedly ignores prompt data.

Would be great to have an infobox in the sidebar that showed these generator details all the time. Current platform, version, and information about key settings that are both hard set and/or adjustable via prompt. Click through it to get a one-page rundown of current engine and known tendencies and prompt methods. Maybe just a pinned “The Engine” thread with admin/dev updates locked to the top?

Thank you so much for taking the time! That is great progress, I will try to play with this one. Hopefully I can get the same foreground with fewer fences in the background, and/or more space between the camera and the horses (I’ve NEVER had any luck pulling the camera back.) I’ll see what I can do with this, thank you!

Front view of Woman with her hair slicked back. You see a ponytail raised up from behind her head.

Thank you for trying to help! I should have specified within the “Professional Photo” style, I need to retain a stylistic consistency across various images. When I do that with your prompt, none of them result in a tight style. Of 16, 6 of the images were from the back. Two more were from the front, but with the ponytail hanging in front of the face. All but one had quite loose hair and a fuck ton of flyaways Several had hair buns instead of ponytails, all also loose. Also, I need the woman to be looking into the camera, not downward, which most of the “Casual Photo” attempts yielded. I do appreciate your input though!

Also, this will be incorporated as a detail in a larger description… adding basically any detail to this is likely to wipe it out (color, length, facial features and expressions.) What I am looking for is specific word choices/descriptors that will consistently generate this style. I have used “slicked back” on its own (and repetitively within the prompt) over and over again to no avail.

I am not one to use a very short prompt and accept what is given… that is letting the AI imagine a thing. I want to imagine a thing myself, and have the AI depict it as close to I describe as possible. My prompts tend to be much longer, so complex specificity must be combined with brevity.

Thank you again though!

It’s like at 11:30AM, someone just flipped a switch… deny all other users. Was working fine, then BAM, “anti-bot blah blah blah” and nothing loads. Is it unregulated testing being done in the live environment, or is it intentional ?!?

Img Gen is down again… looks like someone is using the production environment as their own personal sandbox again…

“relatively new under the hood it is a highly technical model at that, and so lota solutions experimenting, and developmental research is needed.”

In other words, they are using the production environment as a test platform. Brilliant.

Devs switched to a new model. To save $$$ it does things differently to use less resources. Images now completely hit or miss, so you have to generate 10x more images to get usable results. Resource use ACTUALLY being reduced??? Hard to say when I have to generate SOOOO many more images because this one ignores MUCH prompt data. Seems like “Cut off nose to spite face.”

I appreciate your answer, it appears I had some other background syntax error. Decided to rearrange my inputs just a moment ago and somehow fixxored it accimagically.