adds Seia LoRA

README.md

@@ -64,6 +64,11 @@ Here you will find the various LoRAs I've trained, typically of Blue Archive cha
 
 [![Reisa](reisa/chara-reisa-v3.png)](https://huggingface.co/khanon/lora-training/blob/main/reisa/README.md)
 
+### Seia
+[Yurizono Seia / 百合園セイア / 유리조노 세이아 / 百合園圣娅](https://huggingface.co/khanon/lora-training/blob/main/seia/README.md)
+
+[![Seia](seia/chara-seia-v1.png)](https://huggingface.co/khanon/lora-training/blob/main/seia/README.md)
+
 ### Shizuko
 [Kawawa Shizuko / 河和シズコ / 카와와 시즈코 / 河和靜子](https://huggingface.co/khanon/lora-training/blob/main/shizuko/README.md)
 

seia/README.md

@@ -0,0 +1,46 @@
+# Yurizono Seia (Blue Archive)
+百合園セイア (ブルーアーカイブ) / 유리조노 세이아 (블루 아카이브) / 百合園圣娅 (蔚藍檔案)
+
+[**Download here.**](https://huggingface.co/khanon/lora-training/blob/main/seia/chara-seia-v1.safetensors)
+
+## Table of Contents
+- [Preview](#preview)
+- [Usage](#usage)
+- [Training](#training)
+- [Revisions](#revisions)
+
+## Preview
+![Seia portrait](chara-seia-v1.png)
+![Seia preview 1](example-001-DefmixRed-v1.png)
+![Seia preview 2](example-003-DefmixRed-v1.png)
+
+## Usage
+Use any or all of the following tags to summon Arona: `seia, 1girl, fox ears, parted bangs, halo, multicolored eyes, flower wreath, blonde hair`
+
+For her normal outfit: `white dress, sleeveless dress, blue necktie, sleeves past wrists, sleeves past fingers, detached sleeves, white pantyhose, high heels`
+- Her dress was also tagged with `collared dress` and `frilled dress` if those elements were visible.
+- Choose `sleeves past wrists` or `sleeves past fingers` depending on whether her fingers should be visible.
+- Negative prompt `detached sleeves` for alternative outfits where she should not be wearing the dress.
+
+For her expressions: `expressionless` / `light smile` / `parted lips`
+- Use `half-closed eyes`, `sleepy` or `tareme` if her eyes are too wide.
+
+## Training
+*Exact parameters are provided in the accompanying JSON files.*
+- Trained on a set of 96 images.
+  - 13 repeats
+  - 3 batch size, 4 epochs
+  - `(96 * 13) / 3 * 4` = 1664 steps
+- Initially tagged with WD1.4 swin-v2 model. Tags pruned/edited for consistency.
+- `constant_with_warmup` scheduler
+- 1.5e-5 text encoder LR
+- 1.5e-4 unet LR
+- 1e-5 optimizer LR
+- Used network_dimension 128 (same as usual) / network alpha 128 (default)
+- Training resolution 832x832.
+- Trained without VAE.
+- [Dataset can be found on the mega.co.nz repository.](https://mega.nz/folder/SupXFCiC#C992OYnVa8svZt3PdUObww)
+
+## Revisions
+- v1 (2023-02-12)
+  - Initial release.

seia/chara-seia-v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ac912355ace8adb41ffb8af91db4235427bd90038b1d1ec819722221e84306
+size 151119103

seia/lora_chara_seia_v1_96i13r.json

@@ -0,0 +1,54 @@
+{
+  "pretrained_model_name_or_path": "G:/sd/repo/models/Stable-diffusion/nai-animefull-final-pruned.safetensors",
+  "v2": false,
+  "v_parameterization": false,
+  "logging_dir": "",
+  "train_data_dir": "G:/sd/training/datasets/seia/dataset",
+  "reg_data_dir": "",
+  "output_dir": "G:/sd/lora/trained/chara/seia",
+  "max_resolution": "832,832",
+  "learning_rate": "1e-5",
+  "lr_scheduler": "constant_with_warmup",
+  "lr_warmup": "5",
+  "train_batch_size": 3,
+  "epoch": "4",
+  "save_every_n_epochs": "",
+  "mixed_precision": "fp16",
+  "save_precision": "fp16",
+  "seed": "31337",
+  "num_cpu_threads_per_process": 32,
+  "cache_latents": true,
+  "caption_extension": ".txt",
+  "enable_bucket": true,
+  "gradient_checkpointing": false,
+  "full_fp16": false,
+  "no_token_padding": false,
+  "stop_text_encoder_training": 0,
+  "use_8bit_adam": true,
+  "xformers": true,
+  "save_model_as": "safetensors",
+  "shuffle_caption": true,
+  "save_state": false,
+  "resume": "",
+  "prior_loss_weight": 1.0,
+  "text_encoder_lr": "1.5e-5",
+  "unet_lr": "1.5e-4",
+  "network_dim": 128,
+  "lora_network_weights": "",
+  "color_aug": false,
+  "flip_aug": false,
+  "clip_skip": 2,
+  "gradient_accumulation_steps": 1.0,
+  "mem_eff_attn": false,
+  "output_name": "chara-seia-v1",
+  "model_list": "",
+  "max_token_length": "150",
+  "max_train_epochs": "",
+  "max_data_loader_n_workers": "",
+  "network_alpha": 128,
+  "training_comment": "Character: `seia, fox ears, parted bangs, halo, multicolored eyes, flower wreath, blonde hair`\nStandard outfit: `sleeveless dress, blue necktie, collared dress, frilled dress, sleeves past wrists, sleeves past fingers, detached sleeves, white pantyhose, high heels` (you don't need to add all of these)\nExpressions: `expressionless` /  `light smile` / `:o`\n96 images * 13 repeats / 3 batch size * 4 epochs = 1664 steps",
+  "keep_tokens": 2,
+  "lr_scheduler_num_cycles": "",
+  "lr_scheduler_power": "",
+  "persistent_data_loader_workers": true
+}