Benutzer-LoRA

XL

Futanari centaur

#Centaur

Cover entfernt:\n Verstoß gegen Inhaltsregeln

  • Lade ein Coverbild erneut hoch\n
  • Du kannst dieses Modell weiterhin suchen und verwenden
Hochgeladen am
15.06.2024, 13:15
Verwendet
304
Bewertungen
Keine Bewertungen
Auslösende Worte

CFback, CFtwolegsup, CFlying

Erlaubnisse
  • Bildgenerierung und -freigabe erlauben
  • Erlaube den Nutzern, dein Modell herunterzuladen
  • Gewerbliche Nutzung

Beschreibung

UpdatedUsed PonyXL to train this one. Updated dataset to achieve better performance. It enhanced this concept on PonyXL and related models. See the examples first.Typo issue solved. Now undercarriage is correctly spelled.Fur color issue solved. See the examples.Please be sure to use trigger words and hires.fix in generation. Some of triggerwords seems to overbake the images or bring bad styles when upweighting them. Reason may be I used 3d images when training. Use highres.fix to prevent this from happening.Adding concepts: doggy, diphallia, undercarriageAbout V2.0In this version, finally I have different poses with weighted cation. Also with multires technque.Updated keywords will prevent the models from misreading the tokens like kneeling, standing, etc.Currently now have five keywords for different poses:CFFB: back to the viewer;CFKN: kneeling;CFLU: two legs up;CFLY: lyingCFST: standing or with single leg up.The bad thing is, still, prompt is not sensitive, and many times the penis will mistaken for hooves or the centaur having multiple legs. You can use some horse penis lora to improve it. But it still needs dozens of trials.Recommend using highres fix with good seeds to generate good images.WORKS BADLY IN 512X512Multires technique parameter:multires_noise_iterations="6"multires_noise_discount=0.3IntroductionThis LyCORIS is used to generate futanari centaur.How to use itI recommand using it in weight 0.7-0.8. It works well with other loras. But sometimes the cock will be mistaken for hooves.Training detailsTraingset is of about 220 images. They are mirrored before training. Half of them are chosen as regularization images. Total steps are about 15000.I divided the training set into 5 subsets and tag the gesture. It is to control the results. But it didn't work, sad. If you want to give it a try, the trigger tags is the folder name below.Regularization = trueresolution=512batch_size=2epoch=10network_dim=32network_alpha=32clip_skip=2Using AdamW8bits as optimizer:lr="1e-4"unet_lr="1e-4"text_encoder_lr="1e-5"Locon parameters:conv_dim=4conv_alpha=4

Kommentare