<h3 id="ver-noob-v-pred-v3-eq"><strong>Ver </strong><span style="color:rgb(193, 194, 197)"><strong>NOOB V-PRED V3 EQ</strong></span></h3><p><span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Trained with improved parameters based on NOOB V-PRED EQ VAE exprimental version: </span><a target="_blank" rel="ugc" href="https://civarchive.com/models/1858821/noobai-v-pred-10-with-eq-vae">https://civarchive.com/models/1858821/noobai-v-pred-10-with-eq-vae</a></p><p></p><h3 id="updated-ver-noob-v-pred-v2">Updated Ver NOOB V-PRED V2</h3><p><span style="color:rgb(193, 194, 197)">Trained based on NOOB V-PRED 1.0 with OneTrainer. See about this version for training details.</span></p><p>It can do better wrinkles on pants and glans shape in this version. Sometimes it has text around but easily to remove with negative prompts.</p><p>The adaptability to art style has weakened in this version. In this case, upweight the style lora or doing a few more trials can be helpful.</p><p></p><h3 id="updated-ver-noob-v-pred-v1">Updated Ver NOOB V-PRED V1</h3><p>Trained based on NOOB V-PRED 1.0. Updated dataset to achieve better performance. It enhanced this concept on NOOB series models. See the examples first.</p><p>Only one trigger word in this version.</p><p></p><h3 id="updated">Updated</h3><p>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.</p><p><span style="color:rgb(193, 194, 197)">Seperated into two concepts: bulge down leg with pants/bulge down leg with dress.</span></p><p></p><h3 id="introduction">Introduction</h3><p>An experimental LyCORIS, used to generate futanari with bulge down leg.</p><p>Still a lot of room for improvement.</p><p></p><h3 id="pros">Pros</h3><ul><li><p>Can generate futanari with bulge down leg.</p></li></ul><h3 id="cons">Cons</h3><ul><li><p>Using 3D materials for training, the art style may become strange under high weights.</p></li><li><p>Penis twisted with legs.</p></li><li><p>Confused the glan with knees.</p></li><li><p>Bad penis shape.</p></li><li><p>A lot of trials needed.</p></li></ul><p></p><h3 id="how-to-use-it">How to use it</h3><p>I recommand using it in weight 0.7-0.8.</p><p></p><h3 id="training-details">Training details</h3><p>Traingset is of about 34 images. Half of them are chosen as regularization images. Total steps are about 1500.</p><p>resolution=768*768</p><p>batch_size=2</p><p>epoch=10</p><p>network_dim=16</p><p>network_alpha=16</p><p>conv_dim=4</p><p>conv_alpha=4</p><p>clip_skip=2</p><p>Using Prodigy as optimizer, setting as the author recommend.</p>

Bulge down leg

<pre><code>{
    "__version": 6,
    "training_method": "LORA",
    "model_type": "STABLE_DIFFUSION_XL_10_BASE",
    "debug_mode": false,
    "debug_dir": "debug",
    "workspace_dir": "G:/OneTrainer/outputs",
    "cache_dir": "workspace-cache/run",
    "tensorboard": true,
    "tensorboard_expose": false,
    "tensorboard_port": 6007,
    "validation": false,
    "validate_after": 1,
    "validate_after_unit": "EPOCH",
    "continue_last_backup": false,
    "include_train_config": "SETTINGS",
    "base_model_name": "G:/stable-diffusion-webui-reForge/models/Stable-diffusion/illustrious/noobaiXLNAIXL_vPred10Version.safetensors",
    "weight_dtype": "FLOAT_16",
    "output_dtype": "BFLOAT_16",
    "output_model_format": "SAFETENSORS",
    "output_model_destination": "G:/OneTrainer/outputs/bulge_down_leg-NOOB-VPRED1.0-V2-loha-32-drop0.1.safetensors",
    "gradient_checkpointing": "ON",
    "enable_async_offloading": true,
    "enable_activation_offloading": true,
    "layer_offload_fraction": 0.0,
    "force_circular_padding": false,
    "concept_file_name": "training_concepts/concepts.json",
    "concepts": [
        {
            "__version": 1,
            "image": {
                "__version": 0,
                "enable_crop_jitter": true,
                "enable_random_flip": true,
                "enable_fixed_flip": false,
                "enable_random_rotate": false,
                "enable_fixed_rotate": false,
                "random_rotate_max_angle": 0.0,
                "enable_random_brightness": false,
                "enable_fixed_brightness": false,
                "random_brightness_max_strength": 0.0,
                "enable_random_contrast": false,
                "enable_fixed_contrast": false,
                "random_contrast_max_strength": 0.0,
                "enable_random_saturation": false,
                "enable_fixed_saturation": false,
                "random_saturation_max_strength": 0.0,
                "enable_random_hue": false,
                "enable_fixed_hue": false,
                "random_hue_max_strength": 0.0,
                "enable_resolution_override": false,
                "resolution_override": "512",
                "enable_random_circular_mask_shrink": false,
                "enable_random_mask_rotate_crop": false
            },
            "text": {
                "__version": 0,
                "prompt_source": "sample",
                "prompt_path": "",
                "enable_tag_shuffling": true,
                "tag_delimiter": ",",
                "keep_tags_count": 1,
                "tag_dropout_enable": false,
                "tag_dropout_mode": "FULL",
                "tag_dropout_probability": 0.0,
                "tag_dropout_special_tags_mode": "NONE",
                "tag_dropout_special_tags": "",
                "tag_dropout_special_tags_regex": false,
                "caps_randomize_enable": false,
                "caps_randomize_mode": "capslock, title, first, random",
                "caps_randomize_probability": 0.0,
                "caps_randomize_lowercase": false
            },
            "name": "",
            "path": "F:/dataset/bulge_down_leg_V1/10_bdl",
            "seed": 818222669,
            "enabled": true,
            "validation_concept": false,
            "include_subdirectories": false,
            "image_variations": 1,
            "text_variations": 1,
            "balancing": 10.0,
            "balancing_strategy": "REPEATS",
            "loss_weight": 1.0
        }
    ],
    "aspect_ratio_bucketing": true,
    "latent_caching": true,
    "clear_cache_before_training": true,
    "learning_rate_scheduler": "COSINE",
    "custom_learning_rate_scheduler": null,
    "scheduler_params": [],
    "learning_rate": 1.0,
    "learning_rate_warmup_steps": 0.0,
    "learning_rate_cycles": 1.0,
    "learning_rate_min_factor": 0.0,
    "epochs": 10,
    "batch_size": 2,
    "gradient_accumulation_steps": 1,
    "ema": "OFF",
    "ema_decay": 0.999,
    "ema_update_step_interval": 5,
    "dataloader_threads": 2,
    "train_device": "cuda",
    "temp_device": "cpu",
    "train_dtype": "BFLOAT_16",
    "fallback_train_dtype": "BFLOAT_16",
    "enable_autocast_cache": true,
    "only_cache": false,
    "resolution": "1024",
    "frames": "25",
    "attention_mechanism": "XFORMERS",
    "align_prop": false,
    "align_prop_probability": 0.1,
    "align_prop_loss": "AESTHETIC",
    "align_prop_weight": 0.01,
    "align_prop_steps": 20,
    "align_prop_truncate_steps": 0.5,
    "align_prop_cfg_scale": 7.0,
    "mse_strength": 1.0,
    "mae_strength": 0.0,
    "log_cosh_strength": 0.0,
    "vb_loss_strength": 1.0,
    "loss_weight_fn": "CONSTANT",
    "loss_weight_strength": 5.0,
    "dropout_probability": 0.1,
    "loss_scaler": "NONE",
    "learning_rate_scaler": "NONE",
    "clip_grad_norm": 1.0,
    "offset_noise_weight": 0.0,
    "perturbation_noise_weight": 0.0,
    "rescale_noise_scheduler_to_zero_terminal_snr": true,
    "force_v_prediction": false,
    "force_epsilon_prediction": false,
    "min_noising_strength": 0.0,
    "max_noising_strength": 1.0,
    "timestep_distribution": "LOGIT_NORMAL",
    "noising_weight": 0.2,
    "noising_bias": 0.0,
    "timestep_shift": 1.0,
    "dynamic_timestep_shifting": false,
    "unet": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": 0,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "prior": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": 0,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "text_encoder": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": false,
        "stop_training_after": 20,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "text_encoder_layer_skip": 0,
    "text_encoder_2": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": false,
        "stop_training_after": 20,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "text_encoder_2_layer_skip": 0,
    "text_encoder_3": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": 30,
        "stop_training_after_unit": "EPOCH",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "text_encoder_3_layer_skip": 0,
    "vae": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "FLOAT_32",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "effnet_encoder": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "decoder": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "decoder_text_encoder": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "decoder_vqgan": {
        "__version": 0,
        "model_name": "",
        "include": true,
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "learning_rate": null,
        "weight_dtype": "NONE",
        "dropout_probability": 0.0,
        "train_embedding": true,
        "attention_mask": false,
        "guidance_scale": 1.0
    },
    "masked_training": false,
    "unmasked_probability": 0.1,
    "unmasked_weight": 0.1,
    "normalize_masked_area_loss": false,
    "embedding_learning_rate": null,
    "preserve_embedding_norm": false,
    "embedding": {
        "__version": 0,
        "uuid": "491c91cb-4f84-4282-b0e2-cdc342cf8ea2",
        "model_name": "",
        "placeholder": "&lt;embedding&gt;",
        "train": true,
        "stop_training_after": null,
        "stop_training_after_unit": "NEVER",
        "token_count": 1,
        "initial_embedding_text": "*"
    },
    "additional_embeddings": [],
    "embedding_weight_dtype": "FLOAT_32",
    "cloud": {
        "__version": 0,
        "enabled": false,
        "type": "RUNPOD",
        "file_sync": "NATIVE_SCP",
        "create": true,
        "name": "OneTrainer",
        "tensorboard_tunnel": true,
        "sub_type": "COMMUNITY",
        "gpu_type": "NVIDIA GeForce RTX 4090",
        "volume_size": 100,
        "min_download": 0,
        "remote_dir": "/workspace",
        "huggingface_cache_dir": "/workspace/huggingface_cache",
        "onetrainer_dir": "/workspace/OneTrainer",
        "install_cmd": "git clone https://github.com/Nerogar/OneTrainer",
        "install_onetrainer": true,
        "update_onetrainer": true,
        "detach_trainer": false,
        "run_id": "job1",
        "download_samples": true,
        "download_output_model": true,
        "download_saves": true,
        "download_backups": false,
        "download_tensorboard": false,
        "delete_workspace": false,
        "on_finish": "NONE",
        "on_error": "NONE",
        "on_detached_finish": "NONE",
        "on_detached_error": "NONE"
    },
    "peft_type": "LOHA",
    "lora_model_name": "",
    "lora_rank": 32,
    "lora_alpha": 32.0,
    "lora_decompose": false,
    "lora_decompose_norm_epsilon": false,
    "lora_weight_dtype": "BFLOAT_16",
    "lora_layers": "attentions",
    "lora_layer_preset": "attn-mlp",
    "bundle_additional_embeddings": true,
    "optimizer": {
        "__version": 0,
        "optimizer": "PRODIGY",
        "adam_w_mode": false,
        "alpha": null,
        "amsgrad": false,
        "beta1": 0.9,
        "beta2": 0.999,
        "beta3": null,
        "bias_correction": false,
        "block_wise": false,
        "capturable": false,
        "centered": false,
        "clip_threshold": null,
        "d0": 1e-06,
        "d_coef": 1.0,
        "dampening": null,
        "decay_rate": null,
        "decouple": true,
        "differentiable": false,
        "eps": 1e-08,
        "eps2": null,
        "foreach": false,
        "fsdp_in_use": false,
        "fused": false,
        "fused_back_pass": false,
        "growth_rate": "inf",
        "initial_accumulator_value": null,
        "initial_accumulator": null,
        "is_paged": false,
        "log_every": null,
        "lr_decay": null,
        "max_unorm": null,
        "maximize": false,
        "min_8bit_size": null,
        "momentum": null,
        "nesterov": false,
        "no_prox": false,
        "optim_bits": null,
        "percentile_clipping": null,
        "r": null,
        "relative_step": false,
        "safeguard_warmup": true,
        "scale_parameter": false,
        "stochastic_rounding": true,
        "use_bias_correction": false,
        "use_triton": false,
        "warmup_init": false,
        "weight_decay": 0.0,
        "weight_lr_power": null,
        "decoupled_decay": false,
        "fixed_decay": false,
        "rectify": false,
        "degenerated_to_sgd": false,
        "k": null,
        "xi": null,
        "n_sma_threshold": null,
        "ams_bound": false,
        "adanorm": false,
        "adam_debias": false,
        "slice_p": 11,
        "cautious": false
    },
    "optimizer_defaults": {
        "PRODIGY": {
            "__version": 0,
            "optimizer": "PRODIGY",
            "adam_w_mode": false,
            "alpha": null,
            "amsgrad": false,
            "beta1": 0.9,
            "beta2": 0.999,
            "beta3": null,
            "bias_correction": false,
            "block_wise": false,
            "capturable": false,
            "centered": false,
            "clip_threshold": null,
            "d0": 1e-06,
            "d_coef": 1.0,
            "dampening": null,
            "decay_rate": null,
            "decouple": true,
            "differentiable": false,
            "eps": 1e-08,
            "eps2": null,
            "foreach": false,
            "fsdp_in_use": false,
            "fused": false,
            "fused_back_pass": false,
            "growth_rate": "inf",
            "initial_accumulator_value": null,
            "initial_accumulator": null,
            "is_paged": false,
            "log_every": null,
            "lr_decay": null,
            "max_unorm": null,
            "maximize": false,
            "min_8bit_size": null,
            "momentum": null,
            "nesterov": false,
            "no_prox": false,
            "optim_bits": null,
            "percentile_clipping": null,
            "r": null,
            "relative_step": false,
            "safeguard_warmup": true,
            "scale_parameter": false,
            "stochastic_rounding": true,
            "use_bias_correction": false,
            "use_triton": false,
            "warmup_init": false,
            "weight_decay": 0.0,
            "weight_lr_power": null,
            "decoupled_decay": false,
            "fixed_decay": false,
            "rectify": false,
            "degenerated_to_sgd": false,
            "k": null,
            "xi": null,
            "n_sma_threshold": null,
            "ams_bound": false,
            "adanorm": false,
            "adam_debias": false,
            "slice_p": 11,
            "cautious": false
        }
    },
    "sample_definition_file_name": "training_samples/samples.json",
    "samples": [],
    "sample_after": 1,
    "sample_after_unit": "EPOCH",
    "sample_skip_first": 0,
    "sample_image_format": "JPG",
    "sample_video_format": "MP4",
    "sample_audio_format": "MP3",
    "samples_to_tensorboard": true,
    "non_ema_sampling": true,
    "backup_after": 10,
    "backup_after_unit": "NEVER",
    "rolling_backup": false,
    "rolling_backup_count": 3,
    "backup_before_save": false,
    "save_every": 1,
    "save_every_unit": "EPOCH",
    "save_skip_first": 0,
    "save_filename_prefix": "bulge_down_leg-NOOB-VPRED1.0-V2-loha-32-drop0.1"
}</code></pre>

Files with SHA256: f092de35160212bfe9280dfb9ef3d9b2b0367870088af2da295adaa9e73e3d8e