<h3 id="hip-slammin'-assertive-cowgirl!">🤠💖Hip-slammin' assertive cowgirl!💖🤠</h3><h2 id="wan-2.2-notes">WAN 2.2 NOTES</h2><h3 id="(wan-2.1-notes-down-below!)">(WAN 2.1 NOTES DOWN BELOW!)</h3><h3 id="update-there-are-much-better-2.2-cowgirl-loras-out-now.-use-this-high-noise-lora-if-you-want-the-aggressive-&quot;hip-slammin&quot;-body-motion-but-i-recommend-you-rely-on-other-loras-for-accurate-naughty-bits!">Update- There are <a target="_blank" rel="ugc" href="https://civarchive.com/models/1428098?modelVersionId=2156392">much better 2.2 cowgirl loras out now</a>. Use this High Noise lora if you want the aggressive "hip slammin" body motion, but I recommend you rely on other loras for accurate naughty bits!</h3><h3></h3>Trained on 2.2 I2V A14B model. Massively increased dataset over the 2.1 version. Other camera angles work much better now, but POV was still the focus of the training data.Weight 0.7~1.0 ... 1.0 is usually fineSome of the start images can be seen here: <a target="_blank" rel="ugc" href="https://civarchive.com/posts/21124019">https://civarchive.com/posts/21124019</a>Sample workflow in the 'training data' download. <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/training-data/2129122">https://civarchive.com/api/download/training-data/2129122</a>HIGH model is trained on the actual 'hip slammin' motion.LOW model is trained only on genital close-ups.My thinking is that this gives base Wan more freedom to work out her facial expressions in the low noise steps. The low noise lora only helps where it's really needed- the genitals... Whether this assumption is actually accurate 🤷‍♀️ but training both on the same dataset resulted in noticeably muted facial expressions.<h3 id="base-trigger:">Base trigger:</h3><pre><code>a woman is straddling a man and eagerly having sex with him. she is squatting.</code></pre><h3 id="helpful-(highly-recommended)-phrases">Helpful (highly recommended) phrases</h3>(trained-in to the low noise lora)<pre><code>The man's penis slides in and out of view as it enters her vagina.</code></pre><pre><code>His penis is penetrating her vagina. you can see his penis sliding in and out of her vagina.</code></pre><h3 id="helpful-movement-phrases:">Helpful movement phrases:</h3><pre><code>she moves quickly.</code></pre><pre><code>she moves energetically.</code></pre><pre><code>her hips move quickly down on his penis.</code></pre><pre><code>she vigorously slams her hips down on the man.</code></pre><pre><code>she is quickly moving her hips up and down. </code></pre>I also found that increasing the high noise CFG to ~6.0 helps a lot with movement on this lora.Still not perfect- penis often 'smooths out' losing any texture/veinyness. And sometimes it just totally breaks.You can run just the HIGH version, but may end up with accordion cocks (penis getting smashed under her hips rather than entering her pussy).Since the lownoise lora is only helping with genitals, you can probably substitute other NSFW/penetration lownoise loras. No guarantees.<hr /><h1 id="wan-2.1-notes">WAN 2.1 NOTES</h1>DISCLAIMER: Trained on 14B T2V model. But REALLY meant for I2V. Listed on Civit as I2V.I made this for personal use and decided to share. I offer no warranty.<hr />Input images including prompts can be seen here. <a target="_blank" rel="ugc" href="https://civarchive.com/posts/16809770">https://civarchive.com/posts/16809770</a>I love the other Wan cowgirl's, but I wanted something a little more aggressive and in-your-face.So this one is trained on "squatting, face focus, assertive" cowgirl, where the woman slams her hips down on the cock while her upper body remains mostly stationary.weight 1.0 works fine for most I2V. But try range 0.7~1.0No trained trigger word, but I took some hints from other Wan sex loras for base prompt suggestion:<pre><code>a woman is straddling a man and having sex with him. she is squatting. you can see his penis sliding in and out of her vagina.</code></pre>Optional 🤠🏇<pre><code>she slams her hips down aggressively on his penis. </code></pre>Landscape-orientation inputs seem to give the most consistent results.It does also work with reverse/ass-view cowgirl, but no anus data was trained, so beware...Training data was mostly SFM clips, plus a couple anime clips, and some MMD clips. But no photorealistic, which is probably why T2V with this lora is so hideous.Cock'n'pussy close-ups were included to reduce likelihood of cock horror.If you do T2V, use weight 0.7 but you can still expect some ugly-ass remi-real waifus.

Files with SHA256: 1157e29fb15fdaefc1db16421b72bbbd8b3e9eaa4501d766ca0650be5320a252