This one was really fkn hard to make. The dataset could be better and bigger with better tagging but I've done all I want to do with it. There's TWO versions (AND YOU'LL NEED BOTH) mostly because I don't know how to combine LoRA's. The anime one is a little more stylized and the proportions will be less realistic. I like to mix the LoRA's together. I find it only really works when you use more than one. This is basically a WIP that I will never finish. Thought I would release it since it kind of works.Trained on 1000 ish images with mediocre tagging on 80% of them. Putting 'lying on person' seems to help.

Reverse Headscissor

This one was trained on anime images. Again, use both versions in your generations

revscs_anim.safetensors

Anime

Photorealistic

&lt;p&gt;This one was really fkn hard to make. The dataset could be better and bigger with better tagging but I&#39;ve done all I want to do with it.&lt;br /&gt;&lt;strong&gt;There&#39;s TWO versions (AND YOU&#39;LL NEED BOTH)&lt;/strong&gt; mostly because I don&#39;t know how to combine LoRA&#39;s. The anime one is a little more stylized and the proportions will be less realistic. I like to mix the LoRA&#39;s together. I find it only really works when you use more than one. This is basically a WIP that I will never finish. Thought I would release it since it kind of works.&lt;/p&gt;&lt;p&gt;&lt;/p&gt;&lt;p&gt;&lt;/p&gt;&lt;p&gt;Trained on 1000 ish images with mediocre tagging on 80% of them.&lt;br /&gt;Putting &#39;lying on person&#39; seems to help.&lt;br /&gt;&lt;br /&gt;this lora is just a remake for tensorART&lt;br /&gt;original: &lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://civitai.com/models/111958/reverse-headscissor&#34;&gt;Reverse Headscissor - Anime | Stable Diffusion LoRA | Civitai&lt;/a&gt;&lt;/p&gt;

Reverse Headscissor v2 TensorARt Version

&lt;p&gt;This one was really fkn hard to make. The dataset could be better and bigger with better tagging but I&#39;ve done all I want to do with it.&lt;br /&gt;&lt;strong&gt;There&#39;s TWO versions (AND YOU&#39;LL NEED BOTH)&lt;/strong&gt; mostly because I don&#39;t know how to combine LoRA&#39;s. The anime one is a little more stylized and the proportions will be less realistic. I like to mix the LoRA&#39;s together. I find it only really works when you use more than one. This is basically a WIP that I will never finish. Thought I would release it since it kind of works.&lt;/p&gt;&lt;p&gt;Trained on 1000 ish images with mediocre tagging on 80% of them.&lt;br /&gt;Putting &#39;lying on person&#39; seems to help.&lt;/p&gt;

Files with SHA256: 852009e4a5da4c63971757a821aba515ac6fa1fb1ecf57979d85c59505a8efc4