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.

This post isn’t related to perchance, just general AI. Can you in the future not post stuff unrelated to perchance please?

My apologies... I thought that since this was generated specifically with the perchance text-to-image plugin on the perchance site, it was relevant here. 😔

Found/fixed a typo... "Hilippe Druillet" fixed to Philippe Druillet

Are there still many artists left to add? 🤔

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

Seems to be working fine again right now. 🤞

Thanks for the details on where they came from!

I found and added another artist to my plugin: Louis-Léopold Boilly

I think there are a few others that can be added or might be missing (maybe a lot!). My list/plugin currently has 877, and I have a list of artists that I've used in the past that I haven't checked if they're on the big list yet.

I'll keep adding to the plugin as I find more... so you can check/compare/sync every once in a while if you want. There are also some minor case issues in some of the names that I will fix as I find them.

naturally tagging each artist by their properties...

Yep. I've also been messing around with categorizing the artist list by "style" or "genre". This will be quite a project. lol. I know a lot of sorting, etc. can be done with js or perchance output... but I think the big clean list is a great starting point.

I've also updated my Artist Demo Generator - I added a field to enter any Artist name, to easily check if the AI recognizes an artist that might be missing from the list: https://perchance.org/aa3den2ecy

Thanks @[email protected] !!!

I updated the artist plugin: https://perchance.org/artist-plugin

Alphabetized by first name, and added Allo credit to the code.

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

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

Yeah.. I guess I had it right, except I didn't really need to set the variable. It seemed like the right thing to do since I needed to use it for two different lists... but typing "by " in both outputs does the same thing, without any extra characters. lol. Thanks!

@[email protected] Is there a roadmap or existing discussion anywhere about your experiments with the t2i plugin or where you might be going with it? Or for user questions/feedback/requests?

I'm currently getting some fantastic results with it "as is"... but additional options are always appreciated. =)

Thanks for the reply!

Yeah.. my experiments have been showing the same things (although I didn't try deleting a generator and creating a new one with the old name).

Good info.. perhaps image deletion will be added at some point - though I can see the problem with allowing this currently on PUBLIC generators/galleries.

Unless you save the images into a different gallery name which the user with the link doesn’t know about, they wouldn’t.

I just confirmed that renamed galleries are also generator specific, not, as I had first assumed, user specific. So I guess if a generator is deleted, the renamed gallery won't be accessible at all. Unless another gen with the same name is created, as your test showed.

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.

[Feature request] Alternatively, it would be nice if the seed appeared in a field when clicking an image after the image is saved to a gallery (like the prompts do).

This was taken care of beautifully! - especially with the bonus of having the info button available before the image is saved to the gallery. Thanx again @[email protected] !

[Feature request (gallery)] I understand the (necessary) function of the overlay on the gallery images for content filtering purposes - and it works great... however as it is, it makes it impossible to view a gallery image at full size without downloading it or using browser dev tools. I don't know if it would be possible to add a "View Image" or "Open image in new tab" button? Perhaps having it appear only AFTER accepting the content warning popup? Really fancy would be invoking a lightbox gallery.. but that might be overkill.

This button could be optional on the normal image output container div because right-click > open image in new tab is currently possible.

I apologize... I didn't realize just one should be submitted.

Excellent.. Thanx!

EXTREMELY cool! 😎

Wow! That looks perfect... This will also allow me to easily add use user inputs, and add the prompt parameters all in one place.

Thanks so much for the help!

I'll be sure to post again if I run into any trouble. 🙂

@[email protected] Thanks for the reply! Much appreciated. 👍

Hmm... maybe I didn't explain properly. I tried your code and got weird results. Your output/prompt is concatenating the color list... which I don't want.

I'm basically trying to output 4 images with DIFFERENT prompts using ONE output. Here is my (almost) working generator: https://perchance.org/zh7u0fwp8q

As you can see, when randomizing, EACH of the outputs correctly outputs a distinct ethnicity and a distinct shirt color - with no duplicates.

It's almost perfect, but it's still using 2 prompts/outputs (because the consumable list seems to require it) which I think will be a problem if/when I set up a user input for the prompt.

I'm basically just trying to insert a single list item into the prompt... but don't want duplicates in the output which is why I thought consumable list was the way to do it. Is there some way to get/store the list items BEFORE inserting them into the prompt?