adds new Junko LoRA

README.md

@@ -36,6 +36,11 @@ Here you will find the various LoRAs I've trained, typically of Blue Archive cha
 ### Izuna
 [Available on old Mega.co.nz repository.](https://mega.nz/folder/SqYwQTRI#GN2SmGTBsV6S4q-L-V4VeA)
 
+### Junko
+[Akashi Junko / 赤司ジュンコ / 아카시 준코 / 赤司淳子](https://huggingface.co/khanon/lora-training/blob/main/junko/README.md)
+
+[![Junko](junko/chara-junko-v1c.png)](https://huggingface.co/khanon/lora-training/blob/main/junko/README.md)
+
 ### Koharu
 [Shimoe Koharu / 下江コハル / 시모에 코하루 / 下江小春](https://huggingface.co/khanon/lora-training/blob/main/koharu/README.md)
 

junko/README.md

@@ -0,0 +1,54 @@
+# Akashi Junko (Blue Archive)
+赤司ジュンコ (ブルーアーカイブ) / 아카시 준코 (블루 아카이브) / 赤司淳子 (碧蓝档案)
+
+[**Download here.**](https://huggingface.co/khanon/lora-training/blob/main/junko/chara-junko-v1c.safetensors)
+
+## Table of Contents
+- [Preview](#preview)
+- [Usage](#usage)
+- [Training](#training)
+- [Revisions](#revisions)
+
+## Preview
+![Junko portrait](chara-junko-v1c.png)
+![Junko preview 1](example-001-v1c.png)
+![Junko preview 2](example-002-v1c.png)
+![Junko preview 3](example-003-v1c.png)
+
+## Usage
+Use any or all of the following tags to summon Junko: `junko, slit pupils, demon horns, halo, twintails, hair ribbon, pointy ears, demon wings`
+- You can also use `low wings` if the wings appear too high.
+
+For her normal outfit: `military uniform, short sleeves, black shirt, plaid skirt, red necktie, thigh strap, black boots`
+
+For her New Year alt: `japanese clothes, yellow kimono, black hakama skirt, black boots, kinchaku`
+
+For her normal expression: `closed mouth, smile, :3`
+- You may need to prefix the colon with a backslash character.
+
+For her hangry expression: `open mouth, wavy mouth, skin fang, (tearing up, crying with eyes open:0.5)`
+- The AI is very aggressive about drawing tears/crying.  You may need to reduce the emphasis.
+
+## Training
+*Exact parameters are provided in the accompanying JSON files.*
+- Trained on a set of 140 images.
+  - 131 normal images (9 repeats)
+  - 9 "multiple views" images (6 repeats)
+    - These were reduced because the AI was generating too many "multiple views" images.
+  - 3 batch size, 4 epochs
+  - `(131 * 9 + 9 * 6) / 3 * 4` = 1644 steps
+- 0.0727 loss
+- 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)
+  - Resized to 32 after training
+- Training resolution 832x832.
+- Trained without VAE.
+- [Dataset can be found on the mega.co.nz repository.](https://mega.nz/folder/SnQDnCRD#ruLvChZGf2vQtWJN87Qs0Q)
+
+## Revisions
+- v1c (2023-02-15)
+  - Initial release.

junko/chara-junko-v1c.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179e0cf8bdd52ce09a4c71aef584eb8e39926b6732642981fdf358f613eab165
+size 37879476

junko/lora_chara_junko_v1_143i9r.json

@@ -0,0 +1,59 @@
+{
+  "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/junko/dataset",
+  "reg_data_dir": "",
+  "output_dir": "G:/sd/lora/trained/chara/junko",
+  "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-junko-v1",
+  "model_list": "",
+  "max_token_length": "150",
+  "max_train_epochs": "",
+  "max_data_loader_n_workers": "",
+  "network_alpha": 128,
+  "training_comment": "Character: `junko, slit pupils, demon horns, halo, twintails, hair ribbon, pointy ears, demon wings`\nStandard outfit: `military uniform, black shirt, plaid skirt, red necktie, thigh strap, black boots`\nNew Year alt: `japanese clothes, yellow kimono, black hakama, black boots, kinchaku`\n\nNormal expression: `smile, closed mouth, skin fang, :3, v-shaped eyebrows`\nHangry expression: `tearing up, open mouth, crying with eyes open`\n\n(143 images * 9 repeats) / 3 batch size * 4 epochs = 1716 steps",
+  "keep_tokens": 2,
+  "lr_scheduler_num_cycles": "",
+  "lr_scheduler_power": "",
+  "persistent_data_loader_workers": true,
+  "bucket_no_upscale": true,
+  "random_crop": false,
+  "bucket_reso_steps": 64.0,
+  "caption_dropout_every_n_epochs": 0.0,
+  "caption_dropout_rate": 0
+}

junko/lora_chara_junko_v1c_131i9r-9i6r.json

@@ -0,0 +1,59 @@
+{
+  "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/junko/dataset",
+  "reg_data_dir": "",
+  "output_dir": "G:/sd/lora/trained/chara/junko",
+  "max_resolution": "768,768",
+  "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-junko-v1c",
+  "model_list": "",
+  "max_token_length": "150",
+  "max_train_epochs": "",
+  "max_data_loader_n_workers": "",
+  "network_alpha": 128,
+  "training_comment": "Character: `junko, slit pupils, demon horns, halo, twintails, hair ribbon, pointy ears, demon wings`\nStandard outfit: `military uniform, black shirt, plaid skirt, red necktie, thigh strap, black boots`\nNew Year alt: `japanese clothes, yellow kimono, black hakama, black boots, kinchaku`\n\nNormal expression: `smile, closed mouth, skin fang, :3, v-shaped eyebrows`\nHangry expression: `tearing up, open mouth, crying with eyes open`\n\n(131 images * 9 repeats + 9 `multiple_views` images * 6 repeats) / 3 batch size * 4 epochs = 1644 steps",
+  "keep_tokens": 2,
+  "lr_scheduler_num_cycles": "",
+  "lr_scheduler_power": "",
+  "persistent_data_loader_workers": true,
+  "bucket_no_upscale": true,
+  "random_crop": false,
+  "bucket_reso_steps": 64.0,
+  "caption_dropout_every_n_epochs": 0.0,
+  "caption_dropout_rate": 0
+}