Detaches the foreskin and "peels (剝)" it back to about the middle of the penis
Trigger word for prompt:detached foreskinThe v5.9-Anima slider doesn't need a trigger word anymore
Check my images for prompts / LoRA combinations
See the "About this version" information on the right for which LoRA strength to use
Workflows should be embedded in the newest images
Generated using ComfyUI
Please share your creations so I can see how well it's working with other styles! :)
General Training Settings
LoRA_Easy_Training_Scripts to train the model
DatasetHelpers to crop and manage images
BooruDatasetTagManager to manage tags
See "About this version" for individual training details (right side)
v5.9 Training Details
Fizgig-8.9.95 to train the model (.json available under version info tab)
Fizgig-8.9.95 to mask and resize images to 1MP
DatasetHelpers WDv1.4 and WDv3 (tried using mixes of both) to generate tags
BooruDatasetTagManager to manage tags (the goat)
Works alright. Wish it actually had more levels of control, but I didn't have in-between images for training and Fizgig only has a "positive +1 and negative -1" folder set for training.
v4.6 Training Details
LoRA_Easy_Training_Scripts to train the model (.toml available under version info tab)
DatasetHelpers to crop and sort images
BooruDatasetTagManager to manage tags
Trained on different artist, grouped into subsets
Only 700 Steps (got lucky?)
Size of penis may be difficult to control at times
v3.2 and v3.3 Training Details
Set of 222 images, Repeats 2, Batch Size 4, Epochs 40 total but it only made 38?
Best results around 14 epochs (-0014) = ~6214 steps of training?
It didn't seem too overtrained even after 40 epochs
LoRA Type: LyCORIS/LoCon for smaller file size
Lower Network Rank = Lower File Size
Prodigy Optimizer automatically adjusts learning rate during training
v2.0 LoRA Training Details
Set of 240 images, Repeats 5, Epochs 6
Instance Prompt: detached foreskin, Class Prompt: penis
LoRA Type: standard
Max Train Steps: 7200 (because = 240x5x6)
bf16 precision
SDXL enabled, resolution of 1024x1024
Buckets enabled, don't upscale resolution. Resolution min: 256, max: 4096
Optimizer: Adafactor, args: scale_parameter=False relative_step=False warmup_init=False
LR Scheduler: constant
Learning Rate: 0.000025, Text Encode Rate: 0.0001, Unet Learning Rate: 0.0001
Network Rank: 64, Alpha: 1 <-- mess with these settings later, they seem important
Saved every 1 epoch, best results around 3 epochs (-0003) = ~3600 steps of training
Doesn't affect style too hard, appears with low weight (0.5), can go to very high weights (2.0) without completely destroying image
P.S. This is my first concept (idk what im doing most of the time). If you have any tips or advice, please comment on this model or DM me. It will improve this model and future ones that I make.
Thank you!
Description
LyCORIS LoCon. Smaller file size, better training data.
Trained on Illustrious-XL https://civitai.com/models/795765
Seems to work best with strength 0.8 to 1.2
Training Settings:
{
"LoRA_type": "LyCORIS/LoCon",
"LyCORIS_preset": "full",
"adaptive_noise_scale": 0,
"additional_parameters": "--network_train_unet_only --lr_scheduler_type \"CosineAnnealingLR\" --lr_scheduler_args \"T_max=40\"",
"async_upload": false,
"block_alphas": "",
"block_dims": "",
"block_lr_zero_threshold": "",
"bucket_no_upscale": true,
"bucket_reso_steps": 64,
"bypass_mode": false,
"cache_latents": true,
"cache_latents_to_disk": true,
"caption_dropout_every_n_epochs": 0,
"caption_dropout_rate": 0,
"caption_extension": ".txt",
"clip_skip": 2,
"color_aug": false,
"constrain": 0,
"conv_alpha": 1,
"conv_block_alphas": "",
"conv_block_dims": "",
"conv_dim": 16,
"dataset_config": "",
"debiased_estimation_loss": false,
"decompose_both": false,
"dim_from_weights": false,
"dora_wd": false,
"down_lr_weight": "",
"dynamo_backend": "no",
"dynamo_mode": "default",
"dynamo_use_dynamic": false,
"dynamo_use_fullgraph": false,
"enable_bucket": true,
"epoch": 40,
"extra_accelerate_launch_args": "",
"factor": -1,
"flip_aug": false,
"fp8_base": false,
"full_bf16": true,
"full_fp16": false,
"gpu_ids": "",
"gradient_accumulation_steps": 1,
"gradient_checkpointing": true,
"huber_c": 0.1,
"huber_schedule": "snr",
"huggingface_path_in_repo": "",
"huggingface_repo_id": "",
"huggingface_repo_type": "",
"huggingface_repo_visibility": "",
"huggingface_token": "",
"ip_noise_gamma": 0.1,
"ip_noise_gamma_random_strength": false,
"keep_tokens": 3,
"learning_rate": 1,
"log_tracker_config": "",
"log_tracker_name": "",
"log_with": "",
"loss_type": "l2",
"lr_scheduler": "cosine",
"lr_scheduler_args": "",
"lr_scheduler_num_cycles": 1,
"lr_scheduler_power": 1,
"lr_warmup": 0,
"main_process_port": 0,
"masked_loss": false,
"max_bucket_reso": 2048,
"max_data_loader_n_workers": 0,
"max_grad_norm": 1,
"max_resolution": "1024,1024",
"max_timestep": 1000,
"max_token_length": 75,
"max_train_epochs": 0,
"max_train_steps": 0,
"mem_eff_attn": false,
"metadata_author": "itsukoko",
"metadata_description": "",
"metadata_license": "",
"metadata_tags": "detached foreskin,penis,",
"metadata_title": "",
"mid_lr_weight": "",
"min_bucket_reso": 256,
"min_snr_gamma": 1,
"min_timestep": 0,
"mixed_precision": "bf16",
"model_list": "custom",
"module_dropout": 0,
"multi_gpu": false,
"multires_noise_discount": 0.3,
"multires_noise_iterations": 0,
"network_alpha": 1,
"network_dim": 16,
"network_dropout": 0.1,
"network_weights": "",
"noise_offset": 0.03,
"noise_offset_random_strength": false,
"noise_offset_type": "Original",
"num_cpu_threads_per_process": 2,
"num_machines": 1,
"num_processes": 1,
"optimizer": "Prodigy",
"optimizer_args": "decouple=True weight_decay=0.1 d_coef=2 use_bias_correction=True betas=0.9,0.99",
"output_name": "detached_foreskin_v03.3_ILXL",
"persistent_data_loader_workers": false,
"pretrained_model_name_or_path": "illustriousXL_v01.safetensors",
"prior_loss_weight": 1,
"random_crop": false,
"rank_dropout": 0,
"rank_dropout_scale": false,
"reg_data_dir": "",
"rescaled": false,
"resume": "",
"resume_from_huggingface": "",
"sample_every_n_epochs": 0,
"sample_every_n_steps": 0,
"sample_prompts": "",
"sample_sampler": "euler_a",
"save_every_n_epochs": 1,
"save_every_n_steps": 0,
"save_last_n_steps": 0,
"save_last_n_steps_state": 0,
"save_model_as": "safetensors",
"save_precision": "bf16",
"save_state": true,
"save_state_on_train_end": true,
"save_state_to_huggingface": false,
"scale_v_pred_loss_like_noise_pred": false,
"scale_weight_norms": 0,
"sdxl": true,
"sdxl_cache_text_encoder_outputs": false,
"sdxl_no_half_vae": true,
"seed": 0,
"shuffle_caption": false,
"stop_text_encoder_training_pct": 0,
"text_encoder_lr": 1,
"train_batch_size": 4,
"train_norm": false,
"train_on_input": true,
"training_comment": "",
"unet_lr": 1,
"unit": 1,
"up_lr_weight": "",
"use_cp": false,
"use_scalar": false,
"use_tucker": false,
"v2": false,
"v_parameterization": false,
"v_pred_like_loss": 0,
"vae": "",
"vae_batch_size": 0,
"wandb_api_key": "",
"wandb_run_name": "",
"weighted_captions": false,
"xformers": "xformers"
}


















