| Loading settings from /content/LoRA/config/config_file.toml... |
| /content/LoRA/config/config_file |
| prepare tokenizer |
| update token length: 225 |
| Load dataset config from /content/LoRA/config/dataset_config.toml |
| prepare images. |
| found directory /content/LoRA/train_data contains 14 image files |
| 2800 train images with repeating. |
| 0 reg images. |
| no regularization images / 正則化画像が見つかりませんでした |
| [Dataset 0] |
| batch_size: 6 |
| resolution: (512, 512) |
| enable_bucket: True |
| min_bucket_reso: 256 |
| max_bucket_reso: 1024 |
| bucket_reso_steps: 64 |
| bucket_no_upscale: False |
|
|
| [Subset 0 of Dataset 0] |
| image_dir: "/content/LoRA/train_data" |
| image_count: 14 |
| num_repeats: 200 |
| shuffle_caption: True |
| keep_tokens: 0 |
| caption_dropout_rate: 0 |
| caption_dropout_every_n_epoches: 0 |
| caption_tag_dropout_rate: 0 |
| color_aug: False |
| flip_aug: False |
| face_crop_aug_range: None |
| random_crop: False |
| token_warmup_min: 1, |
| token_warmup_step: 0, |
| is_reg: False |
| class_tokens: mksks |
| caption_extension: .txt |
|
|
|
|
| [Dataset 0] |
| loading image sizes. |
| 100% 14/14 [00:00<00:00, 1641.01it/s] |
| make buckets |
| number of images (including repeats) / 各bucketの画像枚数（繰り返し回数を含む） |
| bucket 0: resolution (256, 832), count: 400 |
| bucket 1: resolution (448, 576), count: 800 |
| bucket 2: resolution (512, 512), count: 800 |
| bucket 3: resolution (704, 320), count: 800 |
| mean ar error (without repeats): 0.0496656946415151 |
| prepare accelerator |
| Using accelerator 0.15.0 or above. |
| loading model for process 0/1 |
| load StableDiffusion checkpoint |
| loading u-net: <All keys matched successfully> |
| loading vae: <All keys matched successfully> |
| Downloading (…)lve/main/config.json: 100% 4.52k/4.52k [00:00<00:00, 3.94MB/s] |
| Downloading pytorch_model.bin: 100% 1.71G/1.71G [00:23<00:00, 71.5MB/s] |
| loading text encoder: <All keys matched successfully> |
| Replace CrossAttention.forward to use xformers |
| [Dataset 0] |
| caching latents. |
| 100% 4/4 [00:08<00:00, 2.15s/it] |
| import network module: lycoris.kohya |
| Using rank adaptation algo: lora |
| Use Dropout value: 0.0 |
| Create LyCORIS Module |
| create LyCORIS for Text Encoder: 72 modules. |
| Create LyCORIS Module |
| create LyCORIS for U-Net: 278 modules. |
| enable LyCORIS for text encoder |
| enable LyCORIS for U-Net |
| prepare optimizer, data loader etc. |
| Deprecated: use prepare_optimizer_params(text_encoder_lr, unet_lr, learning_rate) instead of prepare_optimizer_params(text_encoder_lr, unet_lr) |
| CUDA SETUP: CUDA runtime path found: /usr/local/cuda-11.8/targets/x86_64-linux/lib/libcudart.so |
| CUDA SETUP: Highest compute capability among GPUs detected: 7.5 |
| CUDA SETUP: Detected CUDA version 118 |
| CUDA SETUP: Loading binary /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so... |
| use 8-bit AdamW optimizer | {} |
| override steps. steps for 2 epochs is / 指定エポックまでのステップ数: 938 |
| running training / 学習開始 |
| num train images * repeats / 学習画像の数×繰り返し回数: 2800 |
| num reg images / 正則化画像の数: 0 |
| num batches per epoch / 1epochのバッチ数: 469 |
| num epochs / epoch数: 2 |
| batch size per device / バッチサイズ: 6 |
| gradient accumulation steps / 勾配を合計するステップ数 = 1 |
| total optimization steps / 学習ステップ数: 938 |
| steps: 0% 0/938 [00:00<?, ?it/s]epoch 1/2 |
| steps: 50% 469/938 [11:36<11:36, 1.48s/it, loss=0.0825]saving checkpoint: /content/drive/MyDrive/LoRA/output/megum_AnyLoRA_LocLys-000001.safetensors |
| generating sample images at step / サンプル画像生成 ステップ: 469 |
| prompt: (masterpiece, best quality, highres), 1 girl, solo, 20 years drunk japanese girl, big cute green eyes:1.3, cute sharp face, two side up:1.4, long pink hair, hair ribon, bangs, white shirt, brown plaid skirt, blue jacket around waist |
| negative_prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry |
| height: 768 |
| width: 512 |
| sample_steps: 28 |
| scale: 7.0 |
|
|
| 0% 0/28 [00:00<?, ?it/s] |
| 4% 1/28 [00:00<00:13, 1.95it/s] |
| 7% 2/28 [00:00<00:10, 2.49it/s] |
| 11% 3/28 [00:01<00:09, 2.70it/s] |
| 14% 4/28 [00:01<00:08, 2.79it/s] |
| 18% 5/28 [00:01<00:08, 2.86it/s] |
| 21% 6/28 [00:02<00:07, 2.91it/s] |
| 25% 7/28 [00:02<00:07, 2.94it/s] |
| 29% 8/28 [00:02<00:06, 2.96it/s] |
| 32% 9/28 [00:03<00:06, 2.97it/s] |
| 36% 10/28 [00:03<00:06, 2.97it/s] |
| 39% 11/28 [00:03<00:05, 2.98it/s] |
| 43% 12/28 [00:04<00:05, 2.99it/s] |
| 46% 13/28 [00:04<00:05, 2.99it/s] |
| 50% 14/28 [00:04<00:04, 2.99it/s] |
| 54% 15/28 [00:05<00:04, 2.99it/s] |
| 57% 16/28 [00:05<00:04, 2.99it/s] |
| 61% 17/28 [00:05<00:03, 2.99it/s] |
| 64% 18/28 [00:06<00:03, 2.99it/s] |
| 68% 19/28 [00:06<00:03, 2.99it/s] |
| 71% 20/28 [00:06<00:02, 2.99it/s] |
| 75% 21/28 [00:07<00:02, 2.99it/s] |
| 79% 22/28 [00:07<00:02, 2.99it/s] |
| 82% 23/28 [00:07<00:01, 2.99it/s] |
| 86% 24/28 [00:08<00:01, 2.99it/s] |
| 89% 25/28 [00:08<00:01, 2.99it/s] |
| 93% 26/28 [00:08<00:00, 2.99it/s] |
| 96% 27/28 [00:09<00:00, 3.00it/s] |
| 100% 28/28 [00:09<00:00, 2.94it/s] |
| epoch 2/2 |
| steps: 100% 938/938 [23:22<00:00, 1.50s/it, loss=0.0495]generating sample images at step / サンプル画像生成 ステップ: 938 |
| prompt: (masterpiece, best quality, highres), 1 girl, solo, 20 years drunk japanese girl, big cute green eyes:1.3, cute sharp face, two side up:1.4, long pink hair, hair ribon, bangs, white shirt, brown plaid skirt, blue jacket around waist |
| negative_prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry |
| height: 768 |
| width: 512 |
| sample_steps: 28 |
| scale: 7.0 |
|
|
| 0% 0/28 [00:00<?, ?it/s] |
| 4% 1/28 [00:00<00:08, 3.05it/s] |
| 7% 2/28 [00:00<00:08, 3.01it/s] |
| 11% 3/28 [00:01<00:08, 2.96it/s] |
| 14% 4/28 [00:01<00:08, 2.98it/s] |
| 18% 5/28 [00:01<00:07, 2.99it/s] |
| 21% 6/28 [00:02<00:07, 2.98it/s] |
| 25% 7/28 [00:02<00:07, 2.98it/s] |
| 29% 8/28 [00:02<00:06, 2.99it/s] |
| 32% 9/28 [00:03<00:06, 2.99it/s] |
| 36% 10/28 [00:03<00:06, 2.99it/s] |
| 39% 11/28 [00:03<00:05, 2.99it/s] |
| 43% 12/28 [00:04<00:05, 2.99it/s] |
| 46% 13/28 [00:04<00:05, 2.99it/s] |
| 50% 14/28 [00:04<00:04, 2.99it/s] |
| 54% 15/28 [00:05<00:04, 2.99it/s] |
| 57% 16/28 [00:05<00:04, 2.99it/s] |
| 61% 17/28 [00:05<00:03, 2.99it/s] |
| 64% 18/28 [00:06<00:03, 3.00it/s] |
| 68% 19/28 [00:06<00:03, 2.99it/s] |
| 71% 20/28 [00:06<00:02, 2.99it/s] |
| 75% 21/28 [00:07<00:02, 3.00it/s] |
| 79% 22/28 [00:07<00:02, 3.00it/s] |
| 82% 23/28 [00:07<00:01, 2.99it/s] |
| 86% 24/28 [00:08<00:01, 3.00it/s] |
| 89% 25/28 [00:08<00:01, 2.99it/s] |
| 93% 26/28 [00:08<00:00, 2.99it/s] |
| 96% 27/28 [00:09<00:00, 2.99it/s] |
| 100% 28/28 [00:09<00:00, 2.99it/s] |
| save trained model to /content/drive/MyDrive/LoRA/output/megum_AnyLoRA_LocLys.safetensors |
| model saved. |
| steps: 100% 938/938 [23:34<00:00, 1.51s/it, loss=0.0495] |
