Hello,
I am having this type of problem, when I use the notebook with the default values, only changing the number of subject images to 400, in the model training phase (not in the image generation phase) it throws the error shown below.
Steps: 0% 1/1500 [00:04<1:54:35, 4.59s/it, loss=0.0716, lr=2e-6]Traceback (most recent call last):
File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 688, in
main()
File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 648, in main
if args.save_n_steps >= 200:
TypeError: '>=' not supported between instances of 'NoneType' and 'int'
Steps: 0% 1/1500 [00:04<1:58:25, 4.74s/it, loss=0.0716, lr=2e-6]
Traceback (most recent call last):
File "/usr/local/bin/accelerate", line 8, in
sys.exit(main())
File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/accelerate_cli.py", line 43, in main
args.func(args)
File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/launch.py", line 837, in launch_command
simple_launcher(args)
File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/launch.py", line 354, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--train_text_encoder', '--pretrained_model_name_or_path=/content/stable-diffusion-v1-5', '--instance_data_dir=/content/data/JorgeGari', '--class_data_dir=/content/data/person', '--output_dir=/content/models/JorgeGari', '--with_prior_preservation', '--prior_loss_weight=1.0', '--instance_prompt=photo of JorgeGari person', '--class_prompt=a photo of a person, ultra detailed', '--seed=45576', '--resolution=512', '--mixed_precision=fp16', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--gradient_checkpointing', '--use_8bit_adam', '--learning_rate=2e-6', '--lr_scheduler=constant', '--lr_warmup_steps=0', '--center_crop', '--max_train_steps=1500', '--num_class_images=400']' returned non-zero exit status 1.
Something went wrong
Does anyone know why this error is thrown and how to fix it?
hi,
You're using an old notebook, use this link for the latest
https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb
@TheLastBen but only if the number of class images is not changed.
does your current notebook include the option : "Save_Checkpoint_Every_n_Steps" in the cell "start dreambooth" ?
does your current notebook include the option : "Save_Checkpoint_Every_n_Steps" in the cell "start dreambooth" ?
the error TypeError: '>=' not supported between instances of 'NoneType' and 'int' means that Save_Checkpoint_Every_n_Steps isn't defined in the notebook, it should be a number
@TheLastBen okay, I understand, thanks for the time invested in me, i will test it and close the issue when done
TheLastBen
