Microsoft Windows [Version 10.0.19045.2486]
(c) Microsoft Corporation. All rights reserved.
C:\WINDOWS\system32>cd\
C:\>cd kohya_ss
C:\kohya_ss>cd kohya_ss
C:\kohya_ss\kohya_ss>.\venv\Scripts\activate
(venv) C:\kohya_ss\kohya_ss>python lora_gui.py
Load CSS...
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Copy C:/delete/RM_TRY1 to C:/delete/4\img/5_sks man...
Regularization images directory is missing... not copying regularisation images...
Done creating kohya_ss training folder structure at C:/delete/4...
Folder 5_sks man: 25 steps
max_train_steps = 25
stop_text_encoder_training = 0
lr_warmup_steps = 2
accelerate launch --num_cpu_threads_per_process=8 "train_network.py" --enable_bucket --pretrained_model_name_or_path="C:/_MODELS/f222.ckpt" --train_data_dir="C:/delete/4\img" --resolution=512,512 --output_dir="C:/delete/4\model" --use_8bit_adam --xformers --logging_dir="C:/delete/4\log" --network_module=networks.lora --text_encoder_lr=5e-5 --unet_lr=1e-3 --network_dim=8 --output_name="last" --learning_rate="1e-5" --lr_scheduler="cosine" --lr_warmup_steps="2" --train_batch_size="1" --max_train_steps="25" --save_every_n_epochs="1" --mixed_precision="fp16" --save_precision="fp16" --seed="1234" --cache_latents --xformers --use_8bit_adam
prepare tokenizer
Use DreamBooth method.
prepare train images.
found directory 5_sks man contains 5 image files
25 train images with repeating.
loading image sizes.
100%|รขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโห| 5/5 [00:00<00:00, 320.00it/s]
make buckets
number of images (including repeats) / รฅ๏ฟฝโbucketรฃ๏ฟฝยฎรงโยปรฅฦ๏ฟฝรฆลพลกรฆโขยฐรฏยผหรงยนยฐรฃโล รจยฟโรฃ๏ฟฝโรฅโบลพรฆโขยฐรฃโโรฅ๏ฟฝยซรฃโโฌรฏยผโฐ
bucket 0: resolution (256, 832), count: 0
bucket 1: resolution (256, 896), count: 0
bucket 2: resolution (256, 960), count: 0
bucket 3: resolution (256, 1024), count: 0
bucket 4: resolution (320, 704), count: 0
bucket 5: resolution (320, 768), count: 0
bucket 6: resolution (384, 640), count: 0
bucket 7: resolution (448, 576), count: 0
bucket 8: resolution (512, 512), count: 25
bucket 9: resolution (576, 448), count: 0
bucket 10: resolution (640, 384), count: 0
bucket 11: resolution (704, 320), count: 0
bucket 12: resolution (768, 320), count: 0
bucket 13: resolution (832, 256), count: 0
bucket 14: resolution (896, 256), count: 0
bucket 15: resolution (960, 256), count: 0
bucket 16: resolution (1024, 256), count: 0
mean ar error (without repeats): 0.0
prepare accelerator
Using accelerator 0.15.0 or above.
load StableDiffusion checkpoint
loading u-net: <All keys matched successfully>
loading vae: <All keys matched successfully>
Some weights of the model checkpoint at openai/clip-vit-large-patch14 were not used when initializing CLIPTextModel: ['vision_model.encoder.layers.21.self_attn.q_proj.weight', 'vision_model.encoder.layers.20.layer_norm2.bias', 'vision_model.encoder.layers.23.layer_norm2.bias', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.layer_norm1.bias', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.embeddings.position_ids', 'vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.encoder.layers.12.self_attn.k_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.bias', 'vision_model.encoder.layers.16.self_attn.k_proj.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.bias', 'vision_model.encoder.layers.13.layer_norm2.bias', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.21.layer_norm2.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.self_attn.out_proj.bias', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.23.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.18.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.12.self_attn.out_proj.weight', 'vision_model.encoder.layers.19.layer_norm2.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.bias', 'vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.bias', 'vision_model.encoder.layers.23.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.23.self_attn.k_proj.bias', 'vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.self_attn.q_proj.bias', 'vision_model.encoder.layers.15.layer_norm1.bias', 'vision_model.encoder.layers.20.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.layer_norm1.bias', 'vision_model.pre_layrnorm.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.weight', 'vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.16.layer_norm2.bias', 'vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.bias', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.21.layer_norm2.bias', 'vision_model.encoder.layers.23.self_attn.out_proj.bias', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.16.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.weight', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.layer_norm1.bias', 'logit_scale', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.weight', 'vision_model.encoder.layers.15.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.13.layer_norm2.weight', 'vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.encoder.layers.18.layer_norm2.bias', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.13.layer_norm1.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.20.layer_norm1.weight', 'vision_model.encoder.layers.14.layer_norm1.bias', 'vision_model.encoder.layers.14.layer_norm2.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.bias', 'vision_model.encoder.layers.7.layer_norm1.weight', 'vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.weight', 'vision_model.encoder.layers.18.layer_norm2.weight', 'vision_model.encoder.layers.13.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.out_proj.bias', 'visual_projection.weight', 'vision_model.encoder.layers.19.layer_norm2.bias', 'vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.15.self_attn.k_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.bias', 'vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.self_attn.k_proj.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.encoder.layers.21.layer_norm1.bias', 'vision_model.encoder.layers.13.self_attn.v_proj.bias', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.bias', 'vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.layer_norm1.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.19.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.bias', 'vision_model.encoder.layers.6.layer_norm1.bias', 'vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.self_attn.v_proj.bias', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.post_layernorm.weight', 'vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.encoder.layers.17.layer_norm2.weight', 'vision_model.encoder.layers.12.layer_norm1.bias', 'vision_model.encoder.layers.15.layer_norm1.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.pre_layrnorm.bias', 'vision_model.encoder.layers.19.layer_norm1.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.bias', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.weight', 'vision_model.post_layernorm.bias', 'vision_model.encoder.layers.23.layer_norm1.weight', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.16.layer_norm2.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.encoder.layers.20.layer_norm2.weight', 'vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.encoder.layers.16.self_attn.out_proj.bias', 'vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'text_projection.weight', 'vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.17.self_attn.out_proj.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.weight', 'vision_model.encoder.layers.19.layer_norm1.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.encoder.layers.14.self_attn.k_proj.weight', 'vision_model.encoder.layers.2.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.weight', 'vision_model.encoder.layers.12.layer_norm2.bias', 'vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.encoder.layers.23.self_attn.v_proj.bias', 'vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.21.self_attn.q_proj.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.self_attn.out_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.encoder.layers.12.self_attn.v_proj.bias', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.layer_norm2.weight', 'vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.layer_norm2.weight', 'vision_model.encoder.layers.16.layer_norm1.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.weight', 'vision_model.encoder.layers.13.self_attn.v_proj.weight', 'vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.weight', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.5.layer_norm2.weight', 'vision_model.encoder.layers.23.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.self_attn.v_proj.bias', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.12.self_attn.q_proj.bias', 'vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.layer_norm1.weight', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.encoder.layers.16.layer_norm1.weight', 'vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.encoder.layers.15.layer_norm2.bias', 'vision_model.encoder.layers.17.layer_norm2.bias', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.v_proj.bias', 'vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.encoder.layers.23.layer_norm1.bias', 'vision_model.encoder.layers.22.layer_norm1.weight', 'vision_model.encoder.layers.23.layer_norm2.weight', 'vision_model.encoder.layers.22.layer_norm2.bias', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.self_attn.v_proj.weight', 'vision_model.encoder.layers.14.self_attn.q_proj.bias', 'vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.layer_norm1.bias', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.21.layer_norm1.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.bias', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.self_attn.v_proj.bias', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.encoder.layers.23.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.encoder.layers.21.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.encoder.layers.14.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.encoder.layers.17.layer_norm1.weight', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.layer_norm2.weight', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.15.layer_norm2.weight', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.embeddings.class_embedding', 'vision_model.encoder.layers.17.self_attn.q_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.1.self_attn.v_proj.bias']
- This IS expected if you are initializing CLIPTextModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing CLIPTextModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
loading text encoder: <All keys matched successfully>
Replace CrossAttention.forward to use xformers
caching latents.
100%|รขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโหรขโห| 5/5 [00:10<00:00, 2.02s/it]
import network module: networks.lora
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
prepare optimizer, data loader etc.
===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link
================================================================================
CUDA SETUP: Loading binary C:\kohya_ss\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda116.dll...
use 8-bit Adam optimizer
running training / รฅยญยฆรงยฟโรฉโโนรฅยงโน
num train images * repeats / รฅยญยฆรงยฟโรงโยปรฅฦ๏ฟฝรฃ๏ฟฝยฎรฆโขยฐรโรงยนยฐรฃโล รจยฟโรฃ๏ฟฝโรฅโบลพรฆโขยฐ: 25
num reg images / รฆยญยฃรฅโฐโกรฅลโรงโยปรฅฦ๏ฟฝรฃ๏ฟฝยฎรฆโขยฐ: 0
num batches per epoch / 1epochรฃ๏ฟฝยฎรฃฦ๏ฟฝรฃฦฦรฃฦ๏ฟฝรฆโขยฐ: 25
num epochs / epochรฆโขยฐ: 1
batch size per device / รฃฦ๏ฟฝรฃฦฦรฃฦ๏ฟฝรฃโยตรฃโยครฃโยบ: 1
total train batch size (with parallel & distributed & accumulation) / รงยท๏ฟฝรฃฦ๏ฟฝรฃฦฦรฃฦ๏ฟฝรฃโยตรฃโยครฃโยบรฏยผหรคยธยฆรฅหโรฅยญยฆรงยฟโรฃโฌ๏ฟฝรฅโนยพรฉโฆ๏ฟฝรฅ๏ฟฝหรจยจหรฅ๏ฟฝยซรฃโโฌรฏยผโฐ: 1
gradient accumulation steps / รฅโนยพรฉโฆ๏ฟฝรฃโโรฅ๏ฟฝหรจยจหรฃ๏ฟฝโขรฃโโนรฃโยนรฃฦโ รฃฦฦรฃฦโรฆโขยฐ = 1
total optimization steps / รฅยญยฆรงยฟโรฃโยนรฃฦโ รฃฦฦรฃฦโรฆโขยฐ: 25
steps: 0%| | 0/25 [00:00<?, ?it/s]epoch 1/1
Traceback (most recent call last):
File "C:\kohya_ss\kohya_ss\train_network.py", line 427, in <module>
train(args)
File "C:\kohya_ss\kohya_ss\train_network.py", line 305, in train
noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\utils\operations.py", line 490, in __call__
return convert_to_fp32(self.model_forward(*args, **kwargs))
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\amp\autocast_mode.py", line 12, in decorate_autocast
return func(*args, **kwargs)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\diffusers\models\unet_2d_condition.py", line 381, in forward
sample, res_samples = downsample_block(
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\diffusers\models\unet_2d_blocks.py", line 612, in forward
hidden_states = attn(hidden_states, encoder_hidden_states=encoder_hidden_states).sample
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\diffusers\models\attention.py", line 216, in forward
hidden_states = block(hidden_states, context=encoder_hidden_states, timestep=timestep)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\diffusers\models\attention.py", line 484, in forward
hidden_states = self.attn1(norm_hidden_states) + hidden_states
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "C:\kohya_ss\kohya_ss\library\train_util.py", line 997, in forward_xformers
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None) # รฆลโฌรฉ๏ฟฝยฉรฃ๏ฟฝยชรฃ๏ฟฝยฎรฃโโรฉ๏ฟฝยธรฃโโรฃ๏ฟฝยงรฃ๏ฟฝ๏ฟฝรฃโลรฃโโน
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\xformers\ops.py", line 865, in memory_efficient_attention
return op.apply(query, key, value, attn_bias, p).reshape(output_shape)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\xformers\ops.py", line 319, in forward
out, lse = cls.FORWARD_OPERATOR(
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\torch\_ops.py", line 143, in __call__
return self._op(*args, **kwargs or {})
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
steps: 0%| | 0/25 [00:59<?, ?it/s]
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "C:\kohya_ss\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
simple_launcher(args)
File "C:\kohya_ss\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['C:\\kohya_ss\\kohya_ss\\venv\\Scripts\\python.exe', 'train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=C:/_MODELS/f222.ckpt', '--train_data_dir=C:/delete/4\\img', '--resolution=512,512', '--output_dir=C:/delete/4\\model', '--use_8bit_adam', '--xformers', '--logging_dir=C:/delete/4\\log', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=1e-3', '--network_dim=8', '--output_name=last', '--learning_rate=1e-5', '--lr_scheduler=cosine', '--lr_warmup_steps=2', '--train_batch_size=1', '--max_train_steps=25', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1234', '--cache_latents', '--xformers', '--use_8bit_adam']' returned non-zero exit status 1.
Keyboard interruption in main thread... closing server.
(venv) C:\kohya_ss\kohya_ss>
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot]")
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent