Thanks for you answer. Too bad. I looked through the website, and even some names used there are not understood by the AI. They basically created their own database and some names are newly introduced. I could create my own list but it defeats the purpose of getting rid of the color and pattern lists that I was looking to do with the html color element.

try adding "unfocused eyes" to the negative prompt

Try "camera" or "the first person" or "the viewer", works for me. Also, check if you have contradicting prompts, like "looking to the side/away" and then next line it's "looking at the camera".

As for the lips, the only solution I found so far is to use a specific photographer's name, and when the plugin tries to copy it, usually it helps with the lips. But it's not always the case. Sometimes and more frequently recently, a new face is generated with normal lips, which gives me hope in the future it learns to do it. As for the prompt question, it depends on the generator you're using. If you're using your own, you have full control over the prompt. I suggest that you edit the one you're using, find the "natural beauty" line and delete it, then save it. That'll create a new generator specifically for you.

Same. There's also a chance of pixilated screen, as though I set steps to high value.

Human Pose Estimation is already an existing technology, check the web for HPE.

Yeah that works, much appreciated! I noticed that the value was different from the name, it was lowerCase and no emoji that's why I couldn't call it.

How do I work with $output now in the list section to call an individual item from the list? I used to do it like this [clothingList[clothingGroup][clothingTop].joinItems(", ")] where clothingGroup is the html optgroup and clothingTop is the name of the item('this.value'). ${clothingTop[clothingGroup][clothingTop]} or clothingList[clothingGroup][clothingTop] returns undefined. Sorry for the noob question, as you can tell I'm new at this :-)

I put [clothingList.Top] in the HTML and $output line in the lists and it works. I just need to change the item references now in the lists itself. clothingList.Top[clothingGroup][clothingTop].joinItems(", ") doesn't work anymore since there are no items inside to join.

I'm pro new AI model because it generally tries to follow your description but I can agree that this insanity with lips contouring ruining it. I've tried negative and positive prompts with hundreds of "lip contouring", "lip surgery", "natural lips", "thin lips" etc, the same for brows. It's ugly in real life and it's ugly when AI tries to copy it, but unfortunately I couldn't get rid of it completely. The only hope is that it's still learning and we'll get the variety with time. And if someone found a solution, please make a post about it.

thanks a lot, VioneT!

thanks! I tried that and was super clunky to copy paste that. I tried to make the object clickable by doing like this <button id="nseed" onClick="toUserPromp([seed])>[output] but it's a layer on top and the image itself isn't clickable. is there any way to interact with the output to make it clickable or creating a button that is on top of the image just like the heartBtn and flagBtn?