<h1 id="heading-769">Vaporunny - the most fluffable LoRA</h1>This LoRA generates the vaporeon/lopunny fusion know as Vaporunny. Both fusions, vaporeon_ears and lopunny_ears, are packed into this LoRA. Works at 0.7 to 1 scale, but will vary per model.<h3 id="heading-770">Triggers and Example Prompt:</h3><ul><li>vaporunny</li><li>lopunny_ears or vaporeon_ears (lopears and vapears in fluffyrock)</li><li>white_pupils (black sclera recommended), blue_eyes (white sclera recommended), purple_eyes, and red_eyes</li><li>white_collar, white_fluffy_collar, or leave out for no neck features</li><li>fins</li><li>tail (as always with tails, this produces mixed results)</li></ul>Example prompt:vaporunny, vaporeon_ears, white_pupils, white_fluffy_collar, fins, 1girl, blue_skin, :3, upper body, light_blush, sleeveless_shirt, &lt;lora:vaporunnyTheMost_full:1&gt;<h3 id="heading-771">Training details</h3>The LoRA was trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/23900/anylora-checkpoint">AnyLoRA</a> for 20 epochs using 54 images with 10 repeats. Clip skip = 2The fluffyrock version has been trained with fewer images and newer methodologies. It has less consistent anatomy, but more consistent image quality with less style preservation.

Vaporunny - the most fluffable LoRA

Dim size 32, this version uses new LoRA techniques and regularization data to improve on the first version

Files with SHA256: f7adf91da5ddf5629aeae5e9e3e3741ad89fdca970367997914baa3949f3391b