To create a public link, set `share=True` in `launch()`. 16:04:30-079585 INFO Loading config... 16:05:14-828109 INFO Copy /home/Ubuntu/Downloads/coke_bottle_lora to /home/Ubuntu/apps/kohya_ss/train2/img/2_coca-cola bottle... 16:05:14-842628 INFO Regularization images directory is missing... not copying regularisation images... 16:05:14-844100 INFO Done creating kohya_ss training folder structure at /home/Ubuntu/apps/kohya_ss/train2... 16:06:43-646580 INFO Start training Dreambooth... 16:06:43-648515 INFO Validating lr scheduler arguments... 16:06:43-650526 INFO Validating optimizer arguments... 16:06:43-651410 INFO Validating /home/Ubuntu/apps/kohya_ss/train2/log existence and writability... SUCCESS 16:06:43-652333 INFO Validating /home/Ubuntu/apps/kohya_ss/train2/model existence and writability... SUCCESS 16:06:43-653404 INFO Validating /home/Ubuntu/Downloads/flux1-dev.safetensors existence... SUCCESS 16:06:43-654292 INFO Validating /home/Ubuntu/apps/kohya_ss/train2/img existence... SUCCESS 16:06:43-655553 INFO Folder 2_coca-cola bottle: 2 repeats found 16:06:43-656412 INFO Folder 2_coca-cola bottle: 11 images found 16:06:43-657196 INFO Folder 2_coca-cola bottle: 11 * 2 = 22 steps 16:06:43-658002 INFO Regulatization factor: 1 16:06:43-658745 INFO Total steps: 22 16:06:43-659459 INFO Train batch size: 1 16:06:43-660190 INFO Gradient accumulation steps: 1 16:06:43-660951 INFO Epoch: 200 16:06:43-661655 INFO max_train_steps (22 / 1 / 1 * 200 * 1) = 4400 16:06:43-662561 INFO lr_warmup_steps = 0 16:06:43-663844 INFO Saving training config to /home/Ubuntu/apps/kohya_ss/train2/model/Quality_1_20241 121-160643.json... 16:06:43-665151 INFO Executing command: /home/Ubuntu/apps/kohya_ss/venv/bin/accelerate launch --dynamo_backend no --dynamo_mode default --gpu_ids 0 --mixed_precision bf16 --num_processes 1 --num_machines 1 --num_cpu_threads_per_process 2 /home/Ubuntu/apps/kohya_ss/sd-scripts/train_db.py --config_file /home/Ubuntu/apps/kohya_ss/train2/model/config_dreamboo th-20241121-160643.toml 16:06:43-667136 INFO Command executed. 2024-11-21 16:06:49.262708: I external/local_tsl/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used. 2024-11-21 16:06:49.304303: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-11-21 16:06:49.304355: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-11-21 16:06:49.305587: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2024-11-21 16:06:49.312778: I external/local_tsl/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used. 2024-11-21 16:06:49.313042: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-11-21 16:06:50.210290: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT 2024-11-21 16:06:52 INFO Loading settings from train_util.py:4174 /home/Ubuntu/apps/kohya_ss/train 2/model/config_dreambooth-202411 21-160643.toml... INFO /home/Ubuntu/apps/kohya_ss/train train_util.py:4193 2/model/config_dreambooth-202411 21-160643 2024-11-21 16:06:52 INFO prepare tokenizer train_util.py:4665 INFO update token length: 75 train_util.py:4682 INFO prepare images. train_util.py:1815 INFO found directory train_util.py:1762 /home/Ubuntu/apps/kohya_ss/train 2/img/2_coca-cola bottle contains 11 image files WARNING No caption file found for 11 train_util.py:1793 images. Training will continue without captions for these images. If class token exists, it will be used. / 11枚の画像にキャプションファイル が見つかりませんでした。これらの 画像についてはキャプションなしで 学習を続行します。class tokenが存在する場合はそれを使い ます。 WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1800 2/img/2_coca-cola bottle/8oz_glass_CC_red label_intrinsic1_no cap.png WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1800 2/img/2_coca-cola bottle/coke10.jpg WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1800 2/img/2_coca-cola bottle/coke11.jpg WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1800 2/img/2_coca-cola bottle/coke13.jpg WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1800 2/img/2_coca-cola bottle/coke2.jpg WARNING /home/Ubuntu/apps/kohya_ss/train train_util.py:1798 2/img/2_coca-cola bottle/coke3.jpg... and 6 more INFO 22 train images with repeating. train_util.py:1856 INFO 0 reg images. train_util.py:1859 WARNING no regularization images / train_util.py:1864 正則化画像が見つかりませんでした INFO [Dataset 0] config_util.py:572 batch_size: 1 resolution: (1024, 1024) enable_bucket: True network_multiplier: 1.0 min_bucket_reso: 256 max_bucket_reso: 2048 bucket_reso_steps: 64 bucket_no_upscale: True [Subset 0 of Dataset 0] image_dir: "/home/Ubuntu/apps/kohya_ss/trai n2/img/2_coca-cola bottle" image_count: 11 num_repeats: 2 shuffle_caption: False keep_tokens: 0 keep_tokens_separator: caption_separator: , secondary_separator: None enable_wildcard: False caption_dropout_rate: 0.0 caption_dropout_every_n_epoc hes: 0 caption_tag_dropout_rate: 0.0 caption_prefix: None caption_suffix: None color_aug: False flip_aug: False face_crop_aug_range: None random_crop: False token_warmup_min: 1, token_warmup_step: 0, alpha_mask: False, is_reg: False class_tokens: coca-cola bottle caption_extension: .txt INFO [Dataset 0] config_util.py:578 INFO loading image sizes. train_util.py:911 100%|████████████████████████████████████████| 11/11 [00:00<00:00, 35960.52it/s] INFO make buckets train_util.py:917 WARNING min_bucket_reso and train_util.py:934 max_bucket_reso are ignored if bucket_no_upscale is set, because bucket reso is defined by image size automatically / bucket_no_upscaleが指定された場合 は、bucketの解像度は画像サイズか ら自動計算されるため、min_bucket_ resoとmax_bucket_resoは無視されま す INFO number of images (including train_util.py:963 repeats) / 各bucketの画像枚数（繰り返し回数 を含む） INFO bucket 0: resolution (640, 640), train_util.py:968 count: 20 INFO bucket 1: resolution (640, 1408), train_util.py:968 count: 2 INFO mean ar error (without repeats): train_util.py:973 0.0016528925619834717 INFO prepare accelerator train_db.py:106 accelerator device: cuda INFO loading model for process 0/1 train_util.py:4823 INFO load StableDiffusion checkpoint: train_util.py:4779 /home/Ubuntu/Downloads/flux1-dev .safetensors Traceback (most recent call last): File "/home/Ubuntu/apps/kohya_ss/sd-scripts/train_db.py", line 529, in train(args) File "/home/Ubuntu/apps/kohya_ss/sd-scripts/train_db.py", line 123, in train text_encoder, vae, unet, load_stable_diffusion_format = train_util.load_target_model(args, weight_dtype, accelerator) File "/home/Ubuntu/apps/kohya_ss/sd-scripts/library/train_util.py", line 4825, in load_target_model text_encoder, vae, unet, load_stable_diffusion_format = _load_target_model( File "/home/Ubuntu/apps/kohya_ss/sd-scripts/library/train_util.py", line 4780, in _load_target_model text_encoder, vae, unet = model_util.load_models_from_stable_diffusion_checkpoint( File "/home/Ubuntu/apps/kohya_ss/sd-scripts/library/model_util.py", line 1005, in load_models_from_stable_diffusion_checkpoint converted_unet_checkpoint = convert_ldm_unet_checkpoint(v2, state_dict, unet_config) File "/home/Ubuntu/apps/kohya_ss/sd-scripts/library/model_util.py", line 267, in convert_ldm_unet_checkpoint new_checkpoint["time_embedding.linear_1.weight"] = unet_state_dict["time_embed.0.weight"] KeyError: 'time_embed.0.weight' Traceback (most recent call last): File "/home/Ubuntu/apps/kohya_ss/venv/bin/accelerate", line 8, in sys.exit(main()) File "/home/Ubuntu/apps/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 47, in main args.func(args) File "/home/Ubuntu/apps/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 1017, in launch_command simple_launcher(args) File "/home/Ubuntu/apps/kohya_ss/venv/lib/python3.10/site-packages/accelerate/commands/launch.py", line 637, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['/home/Ubuntu/apps/kohya_ss/venv/bin/python', '/home/Ubuntu/apps/kohya_ss/sd-scripts/train_db.py', '--config_file', '/home/Ubuntu/apps/kohya_ss/train2/model/config_dreambooth-20241121-160643.toml']' returned non-zero exit status 1. 16:06:55-011554 INFO Training has ended.