CivArchive
    Condom Suit (NOOB and PonyXL version) - NOOB E-PRED V1
    NSFW
    Preview 39577152
    Preview 39577153
    Preview 39577155
    Preview 39577147

    Ver NOOB V-PRED V2 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 V-PRED V1

    Trained based on NOOB V-PRED V1.0 with OneTrainer. Added triggerwords again to contrl the size. See about this version for training details.

    Pros

    • Concept generation

    • Little impact on the art style

    • Responsive to trigger words

    Cons

    • Distortions of anatomy

    • Many trials needed

    Ver NOOB E-PRED V1

    Trained based on NOOB E-PRED V1.0. Cancelled triggerwords.

    Introduction

    A Pony based LyCORIS to generate the concept Condom Suit. Use triggerwords to control the size of condom suit. The size words also work but I didn't test them.

    Pros

    • Concept generation

    • Little impact on the art style

    Cons

    • Not responsive to trigger words, you need to upweight it or roll for it times to times.

    • Many trials needed

    Training details

    See about the version.

    Description

    Trained based on NOOB E-PRED V1.0. Cancelled Triggerwords.

    Training details:

    {
      "LoRA_type": "LyCORIS/LoCon",
      "LyCORIS_preset": "full",
      "adaptive_noise_scale": 0,
      "additional_parameters": "",
      "async_upload": false,
      "block_alphas": "",
      "block_dims": "",
      "block_lr_zero_threshold": "",
      "bucket_no_upscale": true,
      "bucket_reso_steps": 128,
      "bypass_mode": false,
      "cache_latents": false,
      "cache_latents_to_disk": false,
      "caption_dropout_every_n_epochs": 0,
      "caption_dropout_rate": 0,
      "caption_extension": ".txt",
      "clip_skip": 2,
      "color_aug": false,
      "constrain": 0,
      "conv_alpha": 4,
      "conv_block_alphas": "",
      "conv_block_dims": "",
      "conv_dim": 8,
      "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": 10,
      "extra_accelerate_launch_args": "",
      "factor": -1,
      "flip_aug": false,
      "fp8_base": false,
      "full_bf16": false,
      "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": 1,
      "learning_rate": 1,
      "log_tracker_config": "",
      "log_tracker_name": "",
      "log_with": "tensorboard",
      "logging_dir": "/root/autodl-tmp/output",
      "loss_type": "l2",
      "lr_scheduler": "cosine",
      "lr_scheduler_args": "",
      "lr_scheduler_num_cycles": 1,
      "lr_scheduler_power": 1,
      "lr_warmup": 1,
      "main_process_port": 0,
      "masked_loss": false,
      "max_bucket_reso": 4096,
      "max_data_loader_n_workers": 0,
      "max_grad_norm": 1,
      "max_resolution": "1024,1024",
      "max_timestep": 1000,
      "max_token_length": 225,
      "max_train_epochs": 0,
      "max_train_steps": 0,
      "mem_eff_attn": false,
      "metadata_author": "",
      "metadata_description": "",
      "metadata_license": "",
      "metadata_tags": "",
      "metadata_title": "",
      "mid_lr_weight": "",
      "min_bucket_reso": 1024,
      "min_snr_gamma": 5,
      "min_timestep": 0,
      "mixed_precision": "bf16",
      "model_list": "custom",
      "module_dropout": 0,
      "multi_gpu": false,
      "multires_noise_discount": 0.1,
      "multires_noise_iterations": 6,
      "network_alpha": 8,
      "network_dim": 16,
      "network_dropout": 0.1,
      "network_weights": "",
      "noise_offset": 0,
      "noise_offset_random_strength": false,
      "noise_offset_type": "Multires",
      "num_cpu_threads_per_process": 2,
      "num_machines": 1,
      "num_processes": 1,
      "optimizer": "Prodigy",
      "optimizer_args": "\"weight_decay=0.01\" \"d_coef=0.8\" \"use_bias_correction=True\" \"safeguard_warmup=True\" \"betas=0.9,0.99\" \"decouple=True\"",
      "output_dir": "/root/autodl-tmp/output",
      "output_name": "Condom suit-NOOB 1.0-drop0.1",
      "persistent_data_loader_workers": false,
      "pretrained_model_name_or_path": "/root/autodl-tmp/noobaiXLNAIXL_epsilonPred10Version.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": 1,
      "sample_every_n_steps": 0,
      "sample_prompts": "hugeload, 1girl, solo, long hair, breasts, blush, smile, blue eyes, blonde hair, large breasts, simple background, white background, ponytail, heart, penis, grin, bodysuit, squatting, testicles, skin tight, veins, futanari, veiny penis, huge penis, blue bodysuit, zero suit, samus aran, impossible bodysuit, cum in bodysuit, masterpiece, best quality, good quality, amazing quality, highres, absurdres, newest, highly detailed, uncensored, --n worst quality, low quality, normal quality, oldest, censored, mosaic censoring, bar censor, sketch, unfinished, comic, manga, doujinshi, concept art, flat color, greyscale, monochrome, lineart, bad anatomy, cropped, deformed, bad hands,mutated hands, bad proportions, multiple views, close-up, from below, blurry, lowres, scan artifacts, jpeg artifacts, text, logo, signature, watermark, username, english commentary, mammal, anthro, furry, ambiguous_form, feral, semi-anthro, --w 1024 --h 1024\n ",
      "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": false,
      "save_state_on_train_end": false,
      "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": 31337,
      "shuffle_caption": true,
      "stop_text_encoder_training_pct": 0,
      "text_encoder_lr": 1,
      "train_batch_size": 5,
      "train_data_dir": "/root/autodl-tmp/Condom_Suit_V2",
      "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": "/root/kohya_ss/models/sdxl_vae_fp16fix.safetensors",
      "vae_batch_size": 0,
      "wandb_api_key": "",
      "wandb_run_name": "",
      "weighted_captions": false,
      "xformers": "xformers"
    }

    FAQ

    Comments (2)

    MluacNov 12, 2024
    CivitAI

    Very good LoRa, even with a 1.0 weight, it doesn't have a big impact on the style of painting.

    12cmArtyJan 3, 2025· 1 reaction
    CivitAI

    For my purposes, these Cons are the biggest Pros. It's not too strict, it's highly flexible. Great.

    LoCon
    NoobAI

    Details

    Downloads
    657
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/11/2024
    Updated
    6/23/2026
    Deleted
    -

    Files

    Condom suit-NOOB 1.0-drop0.1-000006.safetensors