<h1 id="heading-1855"><code>facialized</code>: a new LoRA for facials on women</h1><p>LoRA to generate photo-realistic images of women with cum on their face.</p><p>Include in your prompt <code>&lt;lora:facialized:1&gt;, cum, facial</code>.You might want to include in your negative prompt <code>cum on breasts, cum on body</code>.</p><p>The model works best with low steps and CFG, I get good results with 10 steps and a CFG of 3 or 4.</p><p><strong><u>I am open to advice/help to improve this LoRA.</u></strong> If you are willing to help, you can send me a mail at the mail address at the end of this description.</p><p>Training methodology below.</p><p></p><h2 id="heading-1856">Know issues with the model</h2><p>As rightly noted by some comments, the model is still imperfect. Here is a list of a few issues I found, along with ways to circumvent them when possible. <br />I will share tags present in the training dataset that might help you circumvent some of these issues in the format <code>the tag in question [number of images out of 2676 that were associated with this tag]</code>. For example <code>smiling at camera [486]</code> means that 486 images in the dataset (composed of 2676 images in total) had the tag <code>smiling at camera</code>.</p><h3 id="heading-1857">Cum on the body / torso</h3><p>Most of the generated images depict women with cum on their body / torso / breasts. It is currently hard to remove it and ensure that cum only appears on the face.</p><p>Here are some tags present in the training dataset that might help you with this issue:</p><ul><li><p><code>cum on breasts [195]</code></p></li><li><p><code>cum on body [472]</code></p></li><li><p><code>cum on clothes [10]</code></p></li></ul><h3 id="heading-1858">Bad eyes</h3><p>The model might generate faces with non-symmetrical eyes or ill-formed eyes. You can try to alleviate this by using tags such as:</p><ul><li><p><code>symmetric eyes</code></p></li><li><p><code>same color eyes</code></p></li><li><p><code>bad eyes</code> (negative prompt)</p></li><li><p><code>strange eyes</code> (negative prompt)</p></li></ul><p>These tags do not appear in the training data but help the underlying stable diffusion checkpoint generating correct faces.</p><p></p><h2 id="heading-1859">Training methodology explained</h2><p><strong>Disclaimer</strong>: this is my first time making a LoRA and I am more than open to advice to improve it! I am detailing my methodology below, if you have any idea on how to improve it please feel free to comment.</p><h3 id="heading-1860">Dataset</h3><p>The full dataset is composed of 2676 images, hand-picked from one source. Their quality varies greatly, but nearly all of them show a unique women with cum on her face. Some outliers show 2 women (~10 images).</p><p>The image sizes are very disparate, I am reproducing here a count of the number of images for each resolution that has 10 or more images (there are 1454 different resolutions in the whole dataset).</p><pre><code>    154 3024x4032
     98 1536x2048
     96 2316x3088
     51 960x1280
     46 750x1000
     36 768x1024
     27 853x1280
     25 510x680
     25 1920x1080
     22 1080x1920
     20 1000x1333
     19 1280x960
     17 1024x768
     14 1280x1707
     14 1000x750
     13 854x1280
     13 2268x4032
     13 1200x1600
     12 2448x3264
     11 1280x1920
     11 1067x1600
     11 1024x1365
     10 600x800
     10 2000x2666</code></pre><h3 id="heading-1861">Filtering and tagging</h3><p>I used <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/hollowstrawberry/kohya-colab/blob/main/Dataset_Maker.ipynb">https://colab.research.google.com/github/hollowstrawberry/kohya-colab/blob/main/Dataset_Maker.ipynb</a> to filter the dataset. Duplicates have been found with FiftyOne AI and a similarity threshold of 0.985.</p><p>Image tagging has been performed locally in stable-diffusion-ui <a target="_blank" rel="ugc" href="https://github.com/toriato/stable-diffusion-webui-wd14-tagger">stable-diffusion-webui-wd14-tagger</a> extension. Duplicate tags are removed, I used the <code>wd14-vit-v2-git</code> interrogator with a threshold of 0.35. I also added the additional tags <code>"facial", "cum", "1girl", "1women", "face", "sperm"</code>.</p><p>Below is a list of all the tags appearing on more than 20 images in the dataset. Note that these tags are mostly obtained from an auto-tagging procedure (as described above).</p><pre><code>                    1girl  2676
                   1women  2676
                      cum  2676
                     face  2676
                   facial  2676
                    sperm  2676
                realistic  2631
                     lips  2192
                     solo  2160
        looking at viewer  1459
                  breasts  1262
                long hair  1085
               brown hair  1031
                     nude  1011
               black hair   997
                    smile   946
                  nipples   885
                  jewelry   883
              closed eyes   804
              blonde hair   718
               brown eyes   706
               open mouth   663
                 freckles   592
                     1boy   554
                    teeth   539
                   hetero   513
               solo focus   496
           medium breasts   496
                   tongue   494
                 earrings   486
                    penis   479
              cum on body   472
                 necklace   449
               upper body   334
               tongue out   328
               uncensored   328
            small breasts   325
                     nose   298
                  indoors   290
            large breasts   279
                blue eyes   262
                     grin   255
                     mole   253
                   blurry   253
               short hair   246
              cum on hair   242
                 piercing   234
             cum in mouth   228
               from above   227
                 cleavage   224
             closed mouth   212
                   tattoo   209
                   makeup   201
           cum on breasts   195
                 forehead   185
                underwear   177
                    shirt   171
                 portrait   171
                  sitting   165
                 erection   163
                  glasses   141
                    navel   138
               looking up   136
               black eyes   127
                    lying   126
              parted lips   124
                      bra   119
                      pov   119
                     oral   118
                 fellatio   111
                 kneeling   110
                      bed   106
               male focus   103
        blurry background    96
            multiple boys    95
           mole on breast    89
                  handjob    86
                  on back    84
                  topless    84
                     ring    83
                  bukkake    82
              nail polish    81
               green eyes    78
               pubic hair    75
                   choker    73
           one eye closed    73
                   collar    73
          nipple piercing    73
         photo background    68
                    2boys    67
                eyelashes    64
            hoop earrings    63
          male pubic hair    62
                dark skin    59
            cum on tongue    57
         multiple penises    56
               downblouse    56
                 close-up    55
               thighhighs    55
                     what    55
                twintails    53
                  panties    52
                 outdoors    52
                testicles    52
        multicolored hair    52
                 censored    52
               flat chest    49
                 red hair    48
                 barefoot    48
                   pillow    48
                 tank top    47
                 bracelet    46
                group sex    44
                   selfie    44
                      wet    43
           bare shoulders    43
                    tears    43
             clothes lift    42
               collarbone    41
                watermark    41
          completely nude    41
                     bdsm    39
                 lingerie    38
         half-closed eyes    37
                    bangs    37
               shirt lift    36
                    bound    34
                    braid    34
            hair ornament    33
              black shirt    32
                    veins    32
                  cosplay    31
           depth of field    31
                 swimsuit    31
              white shirt    31
                    pants    30
          oral invitation    30
                    denim    29
                  bondage    29
                   saliva    28
                 fishnets    28
                    leash    28
                black bra    27
                 ponytail    27
          tongue piercing    27
                      tan    27
      dark-skinned female    27
                head tilt    27
             open clothes    27
                   window    27
             ear piercing    27
           multiple girls    26
                 lipstick    26
            breasts apart    26
              artist name    26
             body writing    26
           after fellatio    25
                 tanlines    25
                    couch    25
                    skirt    25
        simple background    24
               curly hair    24
                eyeshadow    24
            nose piercing    24
                   bikini    24
              ejaculation    24
                    heart    23
                 bathroom    23
                 sleeping    23
              breasts out    22
                grey eyes    22
                    plant    22
              twin braids    22
           navel piercing    22
     black-framed eyewear    21
                  sweater    21
                   2girls    21
                    watch    21</code></pre><h3 id="heading-1862">Training</h3><p>I used <a target="_blank" rel="ugc" href="https://colab.research.google.com/github/hollowstrawberry/kohya-colab/blob/main/Lora_Trainer.ipynb">https://colab.research.google.com/github/hollowstrawberry/kohya-colab/blob/main/Lora_Trainer.ipynb</a> to train the LoRA. The training model was <code>sd-v1-5-pruned-noema-fp16.safetensors</code>. Tags are automatically shuffled and there is no activation tags (<code>activation_tags</code> set to 0).</p><p>Due to the size of the dataset, each image is only repeated once (i.e., no repetition). I used 5 epochs, with a batch size of 2. The UNet learning rate was set to <code>5e-4</code>. The LoRA network dimension was set to 32, and the network alpha to 16.</p><h2 id="heading-1863">Further notes on other tentatives</h2><p>I tried to manually filter images to only include "nice" images:</p><ul><li><p>high enough resolution and quality</p></li><li><p>no cum on body</p></li><li><p>"pretty" women (according to my taste)</p></li></ul><p>I filtered down the dataset to 1170 images, re-trained a LoRA, but the resulting model is clearly under-performing. I even have hard times trying make cum appear on the generated images with this model.</p><p>I tried different LoRA network dimension and alpha dimension (<code>(16, 8)</code>, <code>(32, 16)</code> and <code>(64, 32)</code>), but the best performing one seems to be the <code>(32, 16)</code>.</p><p></p><h2 id="heading-2326">Contact for collaboration</h2><p>If you want to help me generate a <code>v0.2</code> or even <code>v1</code> of this model, please contact me at the address below by presenting what you think you can bring to the project. </p><p>For the address, everything enclosed in square braces should be replaced, spaces should be removed.</p><p><code>[my pseudo here in civitai] [dot] dev [at] protonmail.com</code></p>

facialized

<p>Initial version, I'm new to LoRA and I am open to suggestions to improve the model.</p>

Files with SHA256: a6cc3d0f3a5ecdddfeb8d78904cbce62ced8d60b103dedac33a529dc1148ccf3