Mushoku Tensei - 無職転生 - Collection

Collection of character LoRA's for the Mushoku Tensei (無職転生) series, intended to generate non-commercial fan art.

Character triggers:

See versions/previews for more recommended settings

sylphiette \(mushoku tensei\)
roxy migurdia
rudeus greyrat
eris greyrat 
ghislaine dedoldia 
elinalise dragonroad 
nanahoshi shizuka
pursena adoldia
rinia dedoldia

Advanced tip (A1111 or Forge users)

I recommend trying the merge collection LoRA with the sd-webui-regional-prompter or sd-forge-couple extensions.

I used sd-forge-couple and adetailer with [SEP] tags for the group shot generations in the previews.

Great article by FallenIncursio on how that works:

How to Generate Multiple Different Characters, Mix Characters, and/or Minimize Color Contamination

Recommended prompt structure:

I recommend using around a ~0.8 weight.

Positive prompt:

score_9, score_8_up, score_7_up, score_6_up, source anime, BREAK {{tags}}

Negative prompt:

score_4, score_5, score_6, monochrome, (censor), 3d, realistic, render, CGI, text, watermark, cartoon, sketch, greyscale

Description

Large dataset of 636 images
Large LoRA rank (48)
Manually tagged quality/aesthetic modifiers
- masterpiece, best quality, low quality, very aesthetic, aesthetic
Tagging of NSFW concepts
- nsfw, explicit

Training config (Kohya):

{
  "LoRA_type": "Standard",
  "LyCORIS_preset": "full",
  "adaptive_noise_scale": 0,
  "additional_parameters": " --optimizer_args \"decouple=True\" \"weight_decay=0.5\"  \"betas=0.9,0.99\" \"use_bias_correction=False\" --lr_scheduler_type \"CosineAnnealingLR\" --lr_scheduler_args \"T_max=35\"",
  "async_upload": false,
  "block_alphas": "",
  "block_dims": "",
  "block_lr_zero_threshold": "",
  "bucket_no_upscale": true,
  "bucket_reso_steps": 256,
  "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": 1,
  "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": 35,
  "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,
  "ip_noise_gamma_random_strength": false,
  "keep_tokens": 0,
  "learning_rate": 1,
  "log_tracker_config": "",
  "log_tracker_name": "",
  "log_with": "",
  "logging_dir": "E:/work/LoRa_work/logging",
  "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": 225,
  "max_train_epochs": 35,
  "max_train_steps": 0,
  "mem_eff_attn": false,
  "metadata_author": "motimalu",
  "metadata_description": "",
  "metadata_license": "",
  "metadata_tags": "",
  "metadata_title": "",
  "mid_lr_weight": "",
  "min_bucket_reso": 512,
  "min_snr_gamma": 5,
  "min_timestep": 0,
  "mixed_precision": "bf16",
  "model_list": "custom",
  "module_dropout": 0,
  "multi_gpu": false,
  "multires_noise_discount": 0.3,
  "multires_noise_iterations": 6,
  "network_alpha": 48,
  "network_dim": 48,
  "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": "",
  "output_dir": "D:/model_output",
  "output_name": "mushoku_tensei_collection_v2",
  "persistent_data_loader_workers": false,
  "pretrained_model_name_or_path": "C:/workspace/webui_forge_cu121_torch21/webui/models/Stable-diffusion/ponyDiffusionV6XL_v6StartWithThisOne.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": 10,
  "sample_every_n_steps": 0,
  "sample_prompts": "score_9, score_8_up, score_7_up, score_6_up, 1girl, upper body, looking at viewer, masterpiece, best quality, very aesthetic",
  "sample_sampler": "euler_a",
  "save_every_n_epochs": 35,
  "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": 339491249,
  "shuffle_caption": false,
  "stop_text_encoder_training_pct": 0,
  "text_encoder_lr": 1,
  "train_batch_size": 8,
  "train_data_dir": "C:/data/mushoku_tensei_collection",
  "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"
}