Unfortunately, because of the randomness of the generator, this is not really possible at this time.

This is very strange behavior.

I have never lost ANY galleries or images - I can even access my old galleries from the previous t2i model. I’ve never had any problems saving images to any galleries. I switch between galleries frequently.

NOTE: The galleries ARE specific to the saved generator, so if you rename the gen, it WILL start new/clean galleries even if you use the same gallery name. By the same token, you should be able to access old galleries if you rename the gen back to the old save name, and then access the old gallery name.

ALL of my galleries are private - and nothing is ever voted on.

I have NOT noticed the image generation getting any better based on previous prompts/saved images (I wish it did!!!).

Sadly, this was one of the “downgrades” of the new model.

The old model was pretty darned accurate when simply using numeric ages (at least for humans/goblins), the new one is horrible.

My previous age prompt: [if (mlf.checked && cgr.checked) {“{40-58} year old”} else if (mlf.checked) {“{59-69} year old”} else if (cgr.checked) {“{40-58} year old”} else “{20-35} year old”]

Now, it’s a total crapshoot, and it definitely defaults to younger. Adding “mature” and/or “older” seems to make little to no difference.

In Firefox…

1. Open/View the gallery (scroll all the way to the end to see all images).
2. Choose File > Save As…
3. For Format, Choose “Web Page, complete”

This will save all gallery images to a folder on your hard drive. It should work similarly in other web browsers.

Interesting approach. I wanted to try playing with the code, but unfortunately saving a copy to edit doesn’t work for me. =/ I just end up with a white screen. I tried pasting the code into a new gen, and that didn’t work either. Might be my older browser.

I’m still using my negative prompt from the previous model, and signatures seem to be rare or minimized. I use multiple artists in my prompts.

extra limbs, extra fingers, too many fingers, deformed, text, (signature, signed, watermark, watermarked signature), picture frame, framed painting, brush, easel, holding paintbrush, bad art, bad composition, terrible lighting, bad anatomy, tattoo

Same error on line 18, except no function error.

Okay…

The browser that I use for Perchance is Floorp (based on Firefox). I’m using the latest version (11.14.1 (64-bit)) that will run on my older Mac OS.

On your example page (t2i-with-create-media-gallery), the “Add to” button shows the popup confirmation, but the “Show” button does nothing.

On the ai-text-to-image-generator page, The “Private Save” and “Show Private Gallery” buttons do nothing. The “Generate Persona” function seems to work fine.

Same results in Opera (Chromium version:116.0.5845.188)

Same results in Brave (Version 1.57.64 Chromium: 116.0.5845.188 (Official Build) (x86_64))

Out of curiosity, I tested Firefox - 102.6.0esr (64-bit)… … and it DOES work! At least on the ai-text-to-image-generator page.

On your t2i-with-create-media-gallery page however, when clicking the “Add to” button, it throws a perchance error.

I was surprised at these results, because usually the Chrome browsers handle newer code better than the older version of FF that I’m using.

I guess I’ll have to decide if I want to switch to the version of Firefox that works, and then implement the Private Gallery functionality into my generator(s). I’m not sure it’s worth it for what I’m doing.

Thanks again for your help.

Thanks for your help! I guess I misunderstood when you said “New private gallery option”. This doesn’t appear do anything different than the default t2i output provides - without using the additional plugin import:

I never even use the “Save to your device” button - I just use: Right-click generated image > “Open in new tab” > Save image

Also, in BOTH of your example links the “Show Gallery” buttons do nothing in my browser (Firefox).

Hm… that sounds REALLY cool, but I’m not sure I want to import the framework just for that functionality. My main gen is pretty clean, and the framework has a lot of stuff that I don’t need or use.

I’m not seeing the new private gallery interface on: https://perchance.org/ai-character-generator (?)

I see that it’s based on the “create-media-gallery-plugin” - but the demo gallery button on that page (https://perchance.org/create-media-gallery-plugin) doesn’t work for me. Clicking the button does nothing.

Do you have a working demo in any of your image gens that’s using it? Or better yet, a stripped down standalone “Private Gallery” plugin?

Several tries… I’ve seen it before, and yes, it always saved on the second try in the past. This time, it wouldn’t save at all after 5 or 6 tries - which is why I finally posted about it. I also tried saving to different galleries, etc.

This lasted for quite a few hours, but it seems to be working again, now.

I really liked the old model, even though it took me a LONG time to fine tune and get the results I liked.

I’m really having fun with the new model and will continue to play with it.

The differences that I currently find lacking with the new model are:

1. The lack of artist styles recognition.
2. a certain generic default e-girl sameness look… which is made worse by #1.
3. multiple images with the same prompt can look extremely and randomly different (paradoxically, considering #2… but also made worse by #1).

I think (hope) these can/will be improved with time, model training, and prompt tuning.

It’s funny… I’ve spent the past year and a half working on my prompts and fine-tuning my generator(s), for the style/results that I like. I got it to where I was very happy with the results - it was generally nothing resembling a lot of the “generic” images I’ve been seeing elsewhere on the web, and I used a lot of combinations of styles to get there - especially using the artist styles plugin.

Using the same prompts with the new model has generated some cool images, but it definitely seems to fall back to a “samey-ness”, and a definite “default style”.

Hopefully, prompt-tuning and model learning will help. I am having fun playing with it so far.

If you duplicate your generator, it creates a fresh gallery… though that won’t stop it from eventually getting polluted again.