Several (like a lot) of pictures of this <a target="_blank" rel="ugc" href="https://civarchive.com/images/112309618">very sexy Goth Girl</a> were posted by @coolhotrod813 on New Mecha Gallery, enough to make me want to have a LoRA of her! 🥰And since i wanted to experiment a new setting, here we are! Happy New Year 🥳THIS OC IS BY @coolhotrod813, if you like it, don't tip the model, tip the original creator 💜Trigger (a bit long and descriptive for a change):<pre><code>C00lH0tG0th, 1girl, black hair, choker, large breasts, gothic girl, dark eyes, dark eyeshadow, black lipstick, mascara, eyeliner, eyelashes, high twintails, skull hair ornament</code></pre>If you check the showcase picture, you'll notice <a target="_blank" rel="ugc" href="https://civarchive.com/models/2268970/punkg0th">punkG0th </a>which is a temporary embedding i used to describe her basic outfit:<pre><code>black shirt, cleavage, black corset, pencil skirt, short skirt, black skirt, fishnet stockings, high heels</code></pre><h3 id="the-training-settings">The training settings</h3>I wanted to test a smaller dimension for a change, with a 1/4 ration alpha to dim.<pre><code>{
 "engine": "kohya",
 "unetLR": 0.0002,
 "clipSkip": 2,
 "loraType": "lora",
 "keepTokens": 1,
 "networkDim": 16,
 "numRepeats": 2,
 "resolution": 1024,
 "lrScheduler": "cosine",
 "minSnrGamma": 0,
 "noiseOffset": 0.03,
 "targetSteps": 1420,
 "enableBucket": true,
 "networkAlpha": 4,
 "optimizerType": "Prodigy",
 "textEncoderLR": 0.00002,
 "maxTrainEpochs": 10,
 "shuffleCaption": true,
 "trainBatchSize": 1,
 "flipAugmentation": false,
 "lrSchedulerNumCycles": 1
}</code></pre>Tagging was done using WD14 moat tagger v2 and some very small adjustment (essentially, removing some tags).Training was done against <a target="_blank" rel="ugc" href="https://civarchive.com/models/2108945?modelVersionId=2385810">Neural Lens Core</a>.<h3 id="the-sd-mecha-test">The sd-mecha test</h3>I wanted to test the N-average merge feature of sd-mecha, feeling it could be a great way to get something easily out of several epochs. From my training (done on-site), i took epoch 1, 2, 4, 5, 9 and 10 and then:<pre><code>from glob import glob
import sd_mecha
sd_mecha.set_log_level()

models = glob("*.safetensors")
models = list(map(sd_mecha.model,models))

recipe = sd_mecha.n_average(*models)
sd_mecha.merge(recipe, output="C00lH0tG0th.safetensors")</code></pre>Simple as that, i took all epoch from the folder where they were, mixed them all together and got this LoRA 😁PS: 3/4 of the showcase pictures are flagged for review 😣PS2: OK, got it, it was because i am using an embedding that is not published /o/ Well, let's publish it then 😋PS3: I have added the resource manually but i will probably have to delete/re-upload the corresponding pictures 😭

CoolHotGoth (OC by CoolHotRod813)

Posted on Civitai, upload found elsewhere are done without the author permission.OC by <a target="_blank" rel="ugc" href="https://civitai.com/user/coolhotrod813">Coolhotrod813</a>

Files with SHA256: 6c977ef9bad86f3944c888db4b50fde1464425fff04a400d4cbaa6338dafde01