Ver Anima V1
Trained base on Anima V0.1 base with LoRA_Easy_Training_Scripts. See about this version for training details.
Ver NOOB V-PRED V1 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
Ver NOOB E-PRED V1
Trained based on NOOB E-PRED V1.0. Different trigger words set to precise concepts. See about the version for training details.
Updated
Used PonyXL to train this one. Updated dataset to achieve better performance. It enhanced this concept on PonyXL and related models.
With PonyXL many concepts can be easily generated. So I will focus on the weak concept in PonyXL. Concept like hyper_futanari that can easily generated with Pony model will not updated to XL version.
Strength 0.8 recommended.
Introduction
This is the subLyCORIS of hyperfuta | Stable Diffusion LORA | Civitai
Use this to generate futanari with larger glan. It can be used alone. But it seems a little overbaked.
How to use it
I recommand using it in weight 0.6-0.7 or lower combined with hyperfuta LyCORIS.
Not enough tests for other tags. It seemsworks well.
Training details:
Traingset is of about 130 images. They are mirrored before training. Total steps are about 5500.
Regularization = false
resolution=768
batch_size=1
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/big_glans_V1/5_bigglans"
keep_tokens = 1
name = "20"
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/big_glans_V1/5_hugeglans"
keep_tokens = 1
name = "5"
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"
save_precision = "bf16"
save_model_as = "safetensors"
save_every_n_epochs = 1
save_toml = true
save_toml_location = "G:/LoRA_Easy_Training_Scripts/output"
output_name = "big_glans-anima1.0-V1.1-loha-dim32conv16AR0.5-NewTag"
[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"