Ver Anima V1
Trained base on Anima V0.1 base with LoRA_Easy_Training_Scripts. See about this version for training details. See the examples first.
Back with taur frontal genital. No need for a seperate lora to generate it.
To control the size of penis I set XX taur penis/ XX taur testicles (XX here is large/huge/gigantic/hyper) as a second triggerwords. Works not well but you can add more weight to make it effective.
Ver NOOB V-PRED V3 EQ
Trained with improved parameters based on NOOB V-PRED EQ VAE exprimental version: https://civarchive.com/models/1858821/noobai-v-pred-10-with-eq-vae
In this version, I removed some trigger words. They are now serparte loras. Only 9 triggerwords left. See the examples first.
I changed the name of this lora to accurately describe its effect. Now it supports the generation of many types of taur.
Most trigger words mean same to the CF-prefix ones. Taurrearing means the taur standing on hind legs.
Trigger words explaination for previous versions:
CFback: back view of futanari centaur
CFonelegup: lifting one foreleg pose of futanari centaur
CFstanding: standing pose with all four legs on the ground
CFtwolegsup: lifting two forelegs pose of futanari centaur
CFlying: lying pose of futanari centaur
CFkneeling: kneeling pose of futanari centaur
CFdiphallia: standing pose of a futanari centaur with horse penis and humanoid penis
CFhuman: human taur concept
CFUCup: carrying girl with legs up under the belly of futanari centaur
CFUCdown: carrying girl with legs down under the belly of futanari centaur
CFUCfellatio: carrying girl under the belly of futanari centaur while giving oral
CFdoggy: a futanari centaur has sex with another in doggystyle position
CFmissionary: a futanari centaur has sex with another in missionary position
CFfellatio: a girl/boy is performing fellatio on a futanari centaur
CFreversedoggy: a futanari centaur has sex with another in reversedoggy position
Ver NOOB V-PRED V2.0
Trained based on NOOB V-PRED V1.0 with OneTrainer. See about this version for training details. Changed keywords and added serval concepts.
Ver NOOB V-PRED V1.0
Trained based on NOOB V-PRED V1.0. Change keyword CFundercarriage to CFUC to prevent the appearance of carriages.
Ver NOOB E-PRED V1.0
Trained based on NOOB E-PRED V1.0. Notice that some examples are generated with NOOB V-PRED 0.5.
Updated
Used 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, undercarriage
About V2.0
In 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: lying
CFST: 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 512X512
Multires technique parameter:
multires_noise_iterations="6"
multires_noise_discount=0.3
Introduction
This LyCORIS is used to generate futanari centaur.
How to use it
I 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 details
Traingset 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 = true
resolution=512
batch_size=2
epoch=10
network_dim=32
network_alpha=32
clip_skip=2
Using AdamW8bits as optimizer:
lr="1e-4"
unet_lr="1e-4"
text_encoder_lr="1e-5"
Locon parameters:
conv_dim=4
conv_alpha=4
Description
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_humantaur"
keep_tokens = 1
name = "5"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurfrontalpenis"
keep_tokens = 1
name = "5_1790613374084299600"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurfrontalpussy"
keep_tokens = 1
name = "5_1790613374099814600"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurhyper"
keep_tokens = 1
name = "5_1790613374114867000"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurkneeling"
keep_tokens = 1
name = "5_1790613374129750000"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_tauronback"
keep_tokens = 1
name = "5_1790613374144775100"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_tauronelegup"
keep_tokens = 1
name = "5_1790613374160265600"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_tauronside"
keep_tokens = 1
name = "5_1790613374175776200"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurrearing"
keep_tokens = 1
name = "5_1790613374190284200"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taursitting"
keep_tokens = 1
name = "5_1790613374206290200"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[[subsets]]
caption_extension = ".txt"
caption_tag_dropout_rate = 0.05
image_dir = "G:/dataset/concept/taur_futanari/5_taurstanding"
keep_tokens = 1
name = "5_1790613374221799300"
num_repeats = 5
random_crop_padding_percent = 0.05
shuffle_caption = true
[train_mode]
train_mode = "lora"
[general_args.args]
persistent_data_loader_workers = true
vae_batch_size = 5
pretrained_model_name_or_path = ""
mixed_precision = "bf16"
gradient_checkpointing = true
gradient_accumulation_steps = 1
seed = 42
max_data_loader_n_workers = 1
max_token_length = 225
prior_loss_weight = 1.0
sdpa = true
max_train_epochs = 20
cache_latents = true
cache_latents_to_disk = true
[general_args.dataset_args]
resolution = 1024
batch_size = 5
[network_args.args]
network_dim = 32
network_alpha = 16.0
min_timestep = 0
max_timestep = 1000
network_train_unet_only = true
[optimizer_args.args]
optimizer_type = "ProdigyPlusScheduleFree"
lr_scheduler = "constant"
loss_type = "l2"
learning_rate = 1.0
unet_lr = 1.0
max_grad_norm = 1.0
[saving_args.args]
output_dir = "G:/LoRA_Easy_Training_Scripts/output"
output_name = "taur_futanari-anima1.0-V1-loha-dim32conv16AR0.5-NewTag"
save_precision = "bf16"
save_model_as = "safetensors"
save_every_n_epochs = 1
save_toml = true
save_toml_location = "G:/LoRA_Easy_Training_Scripts/output"
[logging_args.args]
log_prefix_mode = "disabled"
run_name_mode = "default"
[anima_args.args]
pretrained_model_name_or_path = "G:/sd-webui-forge-neo/models/Stable-diffusion/ANIMA/anima_baseV10.safetensors"
qwen3 = "G:/sd-webui-forge-neo/models/text_encoder/qwen_3_06b_base.safetensors"
vae = "G:/sd-webui-forge-neo/models/VAE/qwen_image_vae.safetensors"
qwen3_max_token_length = 512
t5_max_token_length = 512
timestep_sampling = "sigmoid"
sigmoid_scale = 1.0
[edm_loss_args.args]
edm2_loss_weighting = false
[bucket_args.dataset_args]
enable_bucket = true
min_bucket_reso = 256
max_bucket_reso = 2048
bucket_reso_steps = 64
[network_args.args.network_args]
conv_dim = 16
conv_alpha = 8.0
algo = "loha"
train_llm_adapter = "false"
[optimizer_args.args.optimizer_args]
betas = "0.95,0.99"
beta3 = "None"
weight_decay = "0"
weight_decay_by_lr = "True"
d0 = "2e-5"
d_coef = "1"
d_limiter = "True"
schedulefree_c = "0"
eps = "None"
split_groups = "True"
split_groups_mean = "False"
factored = "True"
factored_fp32 = "True"
use_bias_correction = "True"
use_stableadamw = "True"
use_schedulefree = "True"
use_speed = "False"
stochastic_rounding = "True"
fused_back_pass = "False"
use_cautious = "False"
use_grams = "False"
use_adopt = "False"
use_orthograd = "False"
use_focus = "False"