<h1 id="large-rank-lora-experiments-towards-full-finetuning-lqq5c5npi">Large Rank LoRA - Experiments towards full finetuning</h1><h3 id="what-is-this-l500q8s0d">What is this?</h3>This is a collection of large rank (dimension), large dataset LoRA's which are mostly for testing full-finetuning settings with combined datasets which have been used for individual LoRA's. (see each version notes for lists)Goal is to land on a single dataset and training settings that can<ul><li>Express all the concepts well in a single checkpoint/lora</li><li>Improve the base output quality aesthetics and anatomy</li></ul>Then I will use that dataset and training settings for new full-finetune models.<h3 id="who-is-this-for-b3a93ieq7">Who is this for?</h3>If you enjoy any of the LoRA's datasets included, you might enjoy the combined results of these as well - in testing the individual concepts/characters are also still fairly well respresented so far. (See <a target="_blank" rel="ugc" href="https://civarchive.com/posts/5640299">this post</a> for comparisons)These might also be useful to other creators for use in model mixing/finetuning, I've trained on base Pony for compatibility with the largest amount of merge mixes.<h3 id="datasets-khezyk4uh">Datasets</h3>Datasets included have:<ul><li>Manual curating of quality and aesthetic tags:<ul><li><code>masterpiece, best quality, low quality, very aesthetic, aesthetic</code></li></ul></li><li>Around ~1000 images each</li></ul>e.g. <a target="_blank" rel="ugc" href="https://civarchive.com/models/666101?modelVersionId=764569">Fantasy Anime v.1 [Pony] version</a> includes 3374 images from LoRA datasets:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/398623">Konosuba - この素晴らしい世界に爆焔を！- Collection</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/680304">Sousou no Frieren - 葬送のフリーレン - Collection</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/393632?modelVersionId=595266">Delicious in Dungeon - ダンジョン飯 - Collection</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/411895/mushoku-tensei-collection?modelVersionId=762083">Mushoku Tensei - 無職転生 - Collection</a></li></ul>Recommended prompt structure:Positive prompt:<pre><code>{{tags}}
score_9, score_8_up, score_7_up, score_6_up, absurdres, masterpiece, best quality, very aesthetic</code></pre>Negative prompt:<pre><code>(worst quality, low quality:1.1), score_4, score_3, score_2, score_1, error, bad anatomy, bad hands, watermark, ugly, distorted, signature</code></pre>

Large Rank LoRA - Experiments towards full finetuning

Datasets (from existing LoRA's):Prompts and previews from these pages can be referenced for more of what this LoRA has learnedTotal 3374 images across:<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/398623">Konosuba - この素晴らしい世界に爆焔を！- Collection</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/680304">Sousou no Frieren - 葬送のフリーレン - Collection</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/393632?modelVersionId=595266">Delicious in Dungeon - ダンジョン飯 - Collection</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/411895/mushoku-tensei-collection?modelVersionId=762083">Mushoku Tensei - 無職転生 - Collection</a></li></ul>Training settings (Kohya):I used a batch size of 10, which was right at the limit of what I could push it to while maintaining a s/it under 3.After epoch 20, s/it gradually increased, which resulted in a total training time of 36hrs:<pre><code>epoch 21/30
steps: 70%|██████████████████████████████████▎ | 7287/10410 [7:09:19&lt;3:03:59, 3.53s/it, avr_loss=0.0897]
epoch 22/30
steps: 73%|███████████████████████████████████▏ | 7634/10410 [12:11:19&lt;4:25:56, 5.75s/it, avr_loss=0.0898]
epoch 23/30
steps: 77%|████████████████████████████████████▊ | 7981/10410 [16:27:01&lt;5:00:23, 7.42s/it, avr_loss=0.0887]
epoch 24/30
steps: 80%|██████████████████████████████████████▍ | 8328/10410 [19:53:56&lt;4:58:29, 8.60s/it, avr_loss=0.0878]
epoch 25/30
steps: 83%|████████████████████████████████████████ | 8675/10410 [22:45:11&lt;4:33:02, 9.44s/it, avr_loss=0.0891]
epoch 26/30
steps: 87%|█████████████████████████████████████████▌ | 9022/10410 [25:32:23&lt;3:55:45, 10.19s/it, avr_loss=0.0892]
epoch 27/30
steps: 90%|███████████████████████████████████████████▏ | 9369/10410 [28:18:39&lt;3:08:44, 10.88s/it, avr_loss=0.0858]
epoch 28/30
steps: 93%|████████████████████████████████████████████▊ | 9716/10410 [31:04:01&lt;2:13:08, 11.51s/it, avr_loss=0.0892]
epoch 29/30
steps: 97%|█████████████████████████████████████████████▍ | 10063/10410 [33:51:14&lt;1:10:02, 12.11s/it, avr_loss=0.0874]
epoch 30/30
steps: 100%|█████████████████████████████████████████████████| 10410/10410 [36:41:58&lt;00:00, 12.69s/it, avr_loss=0.0894]2</code></pre>Kohya Config:I don't recommend these settings for a 24gb VRAM system (reduce to batch size of 8 at least):<pre><code>{
 "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=30\"",
 "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": 30,
 "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": 30,
 "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": 128,
 "network_dim": 128,
 "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": "fantasy_superlora_v1",
 "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, frieren, white hair, twintails, green eyes, earrings, white capelet, masterpiece, best quality, very aesthetic",
 "sample_sampler": "euler_a",
 "save_every_n_epochs": 30,
 "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": 10,
 "train_data_dir": "C:/data/superlora_fantasy",
 "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"
}</code></pre>

Files with SHA256: c9d032c59be219803fd441c34d071ad385671b549c8bca00bfbc6efd2e807bac