CivArchive
    Preview 39561572
    Preview 39561561
    Preview 39561581
    Preview 39561559
    Preview 39561520

    NOOB V-PRED V3

    Trained based on NOOB V1.0 with Kohya SS. I switched to locon for smaller file size and better results. Setting min SNR = 3 and alpha = 1 improved the effectiveness of training. However it leads to more limb distortation. But I think it's acceptable when achieving better results in style generation.

    See about the version for training details.

    NOOB V-PRED V2

    Trained based on NOOB V1.0 with OneTrainer. Better in color and lora adapation. See about the version for training details.

    NOOB V-PRED V1

    Trained based on NOOB V0.65S. Recommend using it with V-PRED models.

    No trigger word set in this version.

    Introduction

    A LyCORIS to generate the style of AI artist mirham. Setting the artist name "mirham" as the trigger word during training, but not recommending its use, can cause over baking. Just use the trigger word when you feel necessary, eg. using together with other lora or being suppressed by other styles.

    Training details

    See about the version.

    Description

    Based on NOOB E-PRED V1.0

    { "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": "1536,1536", "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": 1536, "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, "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": "mirham-NOOB-V1-1536", "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": "koko, 1girl, solo, long hair, looking at viewer, simple background, shirt, skirt, black hair, long sleeves, white background, gloves, thighhighs, holding, ribbon, closed mouth, jewelry, standing, green eyes, white shirt, weapon, cowboy shot, earrings, pleated skirt, collared shirt, white gloves, grey background, holding weapon, mole, white thighhighs, vest, uniform, gun, zettai ryouiki, mole under eye, thigh strap, skindentation, holding gun, handgun, brown skirt, watch, shirt tucked in, wristwatch, holster, trigger discipline, thigh holster, magazine (weapon), holstered, suppressor, bulletproof vest, body armor, glock, newest, masterpiece, best quality, amazing quality, highres, absurdres --n oldest, old, worst quality, low quality, normal quality, bad anatomy, cropped, deformed, multiple views, bad hands, bad proportions, multiple legs, censored, mosaic censoring, bar censor, signature, watermark, username, lowres, scan artifacts, jpeg artifacts, text, manga, comic, sketch, unfinished, game cg, --w 1024 --h 768\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": 2, "train_data_dir": "/root/autodl-tmp/mirham", "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" }

    LoCon
    NoobAI

    Details

    Downloads
    1,037
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/11/2024
    Updated
    3/14/2026
    Deleted
    -
    Trigger Words:
    mirham

    Files

    mirham-NOOB-V1-1536.safetensors

    Mirrors

    Huggingface (1 mirrors)