I don't know if anyone else is experiencing this, but ever since the update to what I understand is Flux.1 from SD, the generator has been horrible about defaulting human figures to the anime-inspired, digital painting style that people generally refer to as AI slop, regardless of your style inputs.

Previously, if you specified "middle-aged women, acrlyic paining" in your prompt - with "digital painting, anime style" in your negative - that's what you'd get: a woman who looks between 40 - 50, with a corresponding body type, rendered in a fairly true to life acrylic style. Now the same prompt will get you a My Hero Academia character who looks about 12 and drawn with Clip Studio.

While () still seems to work for emphasis, it also seems we've lost negative prompting, as another user pointed out in a previous thread. If you could prompt things like, "not a teenager, not anime" etc., that wouldn't be so bad ... except that now, it seems that including either or those terms will add it to your prompt because it doesn't seem to acknowledge "not" or "no".

Is anyone else experiencing this, and know of a viable workaround?

Thanks.

Does anyone have any idea how to reliably add specific colors to elements in your image using hex codes? The tutorials don't really mention it, and Google AI's suggestions don't seem reliable as they mostly seem to only add coloring to your prompt output, not the image itself.

Basically, it would be something like:

subject
   {man|woman}

color
   {#8000fb|#F2450B|#78452F}

clothing
   {shirt|pants}

prompt
   a [subject] wearing a [color] [clothing]

Thanks in advance for any help!

Hi! New to this community! Having a blast with the image generator.

I am trying to create the pose pictured in the attached image, where the subject is kneeling but not bending their knees where they rest on their butt. Google tells me this is alternately called 'Tall Kneeling,' 'High Kneeling,' and/or 'Standing on Knees.'

When I try this pose, it's more often a typical kneeling pose like this one.

I've tried specifying things like, 'Kneeling, {thighs upright|legs upright|tall kneeling|high kneeling}' etc, but nothing's working.

Any help would be appreciated. Thanks!