Open loboere opened 1 year ago
colab free T4
I want to train lora in sdxl 1.0 but when training it gives me an error.
my images are of different sizes but I don't know if that has something to do with it.
Loading settings from /content/LoRA/config/config_file.toml... /content/LoRA/config/config_file prepare tokenizers update token length: 225 Training with captions. loading existing metadata: /content/LoRA/meta_lat.json metadata has bucket info, enable bucketing / メタデータにbucket情報があるためbucketを有効にします using bucket info in metadata / メタデータ内のbucket情報を使います [Dataset 0] batch_size: 4 resolution: (1024, 1024) enable_bucket: True min_bucket_reso: None max_bucket_reso: None bucket_reso_steps: None bucket_no_upscale: None [Subset 0 of Dataset 0] image_dir: "/content/LoRA/train_data" image_count: 23 num_repeats: 1 shuffle_caption: False keep_tokens: 0 caption_dropout_rate: 0.0 caption_dropout_every_n_epoches: 0 caption_tag_dropout_rate: 0.0 color_aug: False flip_aug: False face_crop_aug_range: None random_crop: False token_warmup_min: 1, token_warmup_step: 0, metadata_file: /content/LoRA/meta_lat.json [Dataset 0] loading image sizes. 100% 23/23 [00:00<00:00, 393750.99it/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 (704, 1024), count: 3 bucket 1: resolution (768, 1024), count: 1 bucket 2: resolution (832, 1024), count: 2 bucket 3: resolution (896, 1024), count: 1 bucket 4: resolution (1024, 576), count: 9 bucket 5: resolution (1024, 704), count: 2 bucket 6: resolution (1024, 960), count: 2 bucket 7: resolution (1024, 1024), count: 3 mean ar error (without repeats): 0.0 noise_offset is set to 0.0357 / noise_offsetが0.0357に設定されました preparing accelerator loading model for process 0/1 load StableDiffusion checkpoint: /content/pretrained_model/sd_xl_base_1.0.safetensors building U-Net loading U-Net from checkpoint U-Net: <All keys matched successfully> building text encoders ╭───────────────────── Traceback (most recent call last) ──────────────────────╮ │ /usr/local/bin/accelerate:8 in <module> │ │ │ │ 5 from accelerate.commands.accelerate_cli import main │ │ 6 if __name__ == '__main__': │ │ 7 │ sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) │ │ ❱ 8 │ sys.exit(main()) │ │ 9 │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.p │ │ y:45 in main │ │ │ │ 42 │ │ exit(1) │ │ 43 │ │ │ 44 │ # Run │ │ ❱ 45 │ args.func(args) │ │ 46 │ │ 47 │ │ 48 if __name__ == "__main__": │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:918 in │ │ launch_command │ │ │ │ 915 │ elif defaults is not None and defaults.compute_environment == Comp │ │ 916 │ │ sagemaker_launcher(defaults, args) │ │ 917 │ else: │ │ ❱ 918 │ │ simple_launcher(args) │ │ 919 │ │ 920 │ │ 921 def main(): │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:580 in │ │ simple_launcher │ │ │ │ 577 │ process.wait() │ │ 578 │ if process.returncode != 0: │ │ 579 │ │ if not args.quiet: │ │ ❱ 580 │ │ │ raise subprocess.CalledProcessError(returncode=process.ret │ │ 581 │ │ else: │ │ 582 │ │ │ sys.exit(1) │ │ 583 │ ╰──────────────────────────────────────────────────────────────────────────────╯ CalledProcessError: Command '['/usr/bin/python3', 'sdxl_train_network.py', '--sample_prompts=/content/LoRA/config/sample_prompt.toml', '--config_file=/content/LoRA/config/config_file.toml']' died with <Signals.SIGKILL: 9>.
this is not a vae, but a checkpoint
also you need colab pro
:( , is there any hope that it will work in colab for free? , someone do something to make it work
colab free T4
I want to train lora in sdxl 1.0 but when training it gives me an error.
my images are of different sizes but I don't know if that has something to do with it.