image models generally dont give satisfactory views of mid-action dressing/undressing.

This lora helps create mid-action top removal, specifically for women doing the arms-crossed pulling-up action with a little extra.

as usual, it's important to get your prompts right.

Try...

core prompt:

she is caught halfway through {arms-crossed|} removing an upper garment

describe her actions further:

with the garment lifted around the head, raised bent arms, hands actively gripping the fabric, face partially obscured, natural weight shift and slightly awkward mid-motion posture

some additional tweaks to add variation:

{pulling a shirt over her head|lifting a sweater upward|removing a blouse|pulling a top over her shoulders}

{garment partly obscuring her face|face mostly hidden behind the fabric|head emerging through the neckline}, {both arms raised|one arm higher than the other|elbows bent inward}

{hands gripping the garment near the hem|hands pulling the fabric upward|one hand holding the garment while the other helps remove it}

Yes, I know, it's frustrating seeing a lora on early access. Just wait a few days and it's free. Or, if you like this Lora and want to support me creating more, please buy-into early access. It's not much buzz and it helps me train more.

I dont make any money from any of this. I dont have a paid-account on Civitai.

This is a hobby for me and the training is paid for in buzz. The same buzz I get from early access downloads, tips, etc... mainly early access downloads. Without that, I have no buzz. No buzz, means no training. No training... well, no loras.

I do this because I enjoy it. I have a highly paid day job and this is just the stuff I enjoy doing on the side, lol. The moment it stops being fun is the moment I stop bothering with it.