Could anyone point me in the right direction, what model exactly is used on Perchance? I've tried every Chroma Unlocked from version 30 to 50, including HD and Flash and none of them look about the same as Perchance. What other moduls are used to improve visual quality? I've tried all kind of ModelSampling settings giving the model freedom, as well as detailers. What else is there?
https://perchance.org/mytestgen#edit In this generator, I have a suit list that consists of 5 areas: mask, cape, boots etc. The other two lists are "camera" and "actor". So, camera can zoom-in on a certain body part, and I need it to output only that section of clothing, leaving everything else out-of-frame. That I solved. But there's a third dimension to it. The third list is Actor, some characters cannot wear certain clothes because of their characteristics, for example, mermaid can't wear bottom clothes. Help me add that third dimension into the output line to filter it out properly, please.
testing here: https://perchance.org/z7l103ul1q#edit I have quite a big list of variables, that cause errors if undefined or null. So, I wanted to run a FOR through all of them at the very beginning. But perchance functions always ask to return something. How do I do it?
Recently, text-to-image plugin has changed a lot. With respect to Perchance, I'd like to share my humble opinion about it. Take a horse in a medieval setting, for example, 2 pictures out of 5 have blurred/distorted faces. It's not a famous face or a nudity content but it's still getting heavily censored for some reason. I understand the need for censorship and such, but could we focus more on the end user not seeing what they don't want to see in the gallery section rather than messing with the t2i logic? It's a fake parts in fake parts out, at the end of the day, no real person is involved, but it's messing with normal images generation kinda defeating the whole purpose of the plugin and hindering the imagination flow.
https://perchance.org/tz4t341n8c#edit In this test generator, in the center, I have a select form which is just a pose list put into options. I have a lot of them in my main generator, and I want to make them a little be more user friendly and interactive, also bypassing language barrier, so I want to add pictures into the options instead( or in addition to words). That's what I did in the poseRadio list. I substituted radio label's background with pictures using CSS styles. I'm planning to have a second list of picture urls for each list, or I could create an array of URLs in the html part. Ideally, it should look like a dropdown with a picture and then the list item name next to it. And when selected, only the item name is stored in the variable without the picture. I'm not sure how to do that yet. Need your help combining select and input radio in some way, thanks!
Hi. I'm using a line like this [fileName="{0-9}{a-z}{A-Z}".selectMany(12).join("")] to create a set of numbers and letters at the beginning of the prompt. In the previous model I used to set the priority to 0, so the AI ignored it, but I noticed that the new model ignores :: and these numbers started to appear on objects inside the images. Could I assign a filename in any other way?
Hi, I'm looking for a way for the AI to understand a hex color in the format #fff000, for example, if I get it from a color html element. If you directly ask the flux plugin to show a #fff000 shirt he will use a random color instead, so ideally I need to translate it into words, if that's possible at all? Or perhaps, there's another way.
I have a list of clothing items and a variable [gender] that contains value for example "♂️" male. Some items on the list of clothing also contain emojis ♀️ or ♂️ in them, something like "Batman suit♂️". I'm trying to exclude all items with ♀️ if "gender==♂️" and vice versa. I've tried to use clothingTop.selectAll.filter(newlist =>newlist.tags.includes([gender])), ald also match(/♀️/i), I'm not sure how to proceed.
Hi, since the new model came out I struggle to create a middle-of-the-day atmosphere for my photos. "sunny", "very sunny", "the sun is in the zenith", "middle-of-the-day sunny lighting", "{bright|soft} natural day lighting" and many more produce early morning or late day close to sunset. I also tried to use Joy Caption to describe the photos from before, but the description of the lighting and the atmosphere is quite vague and it doesn't help to solve the problem. Any help, please?
Hello. I'm using something like this ["{red, blue, green, orange, lime}".selectMany(3).joinItems(", ")]. It works well enough, but when I try to implement uniqueSelect or consumableList it fails. These function seem to only work for lists but is there any way to select items from a string like that without repetition. Thanks!
Using the text-to-image plugin I generate a bunch of [output]'s in the container. How do I access the tag that the output object creates, for example if I want to get the title to get nseed from it using java script, or there's an easier way to do that? I'm trying to make a button over the image to perfect that seed easier. Also, how do I access the button with id "heartBtn" that [output] creates?
