I'm training a stable diffusion model in google collab, then I encountered an error, before that, here is my full code:
!wget -q https://github.com/ShivamShrirao/diffusers/raw/main/examples/dreambooth/train_dreambooth.py
!wget -q https://github.com/ShivamShrirao/diffusers/raw/main/scripts/convert_diffusers_to_original_stable_diffusion.py
%pip install -qq git+https://github.com/ShivamShrirao/diffusers
%pip install -q -U --pre triton
%pip install -q accelerate transformers ftfy bitsandbytes==0.35.0 gradio natsort safetensors xformers
from natsort import natsorted
from glob import glob
from PIL import Image
from torch import autocast
from diffusers import StableDiffusionPipeline, DDIMScheduler
from IPython.display import display
import json
import random
import os
import matplotlib.pyplot as plt
import torch
# load the model
model_sd = "runwayml/stable-diffusion-v1-5"
# create output dir
output_dir = "/content/stable_diffusion_weights/gg"
!mkdir -p $output_dir
# create instance and class prompts
concepts_list = [
{
"instance_prompt": "gg",
"class_prompt": "photo of a person",
"instance_data_dir": "/content/data/gg",
"class_data_dir": "/content/data/person"
}
]
# create directories and JSON file
for c in concepts_list:
os.makedirs(c["instance_data_dir"], exist_ok=True)
with open("concepts_list.json", "w") as f:
json.dump(concepts_list, f, indent=4)
# specifying learning parameters
num_imgs = 5
num_class_images = num_imgs * 12
max_num_steps = num_imgs * 100
learning_rate = 5e-6
lr_warmup_steps = int(max_num_steps / num_imgs)
print(num_imgs, num_class_images, max_num_steps, learning_rate, lr_warmup_steps)
# training the model
!python3 train_dreambooth.py \
--pretrained_model_name_or_path=$model_sd \
--pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" \
--instance_data_dir=$output_dir \
--output_dir=$output_dir \
--revision="fp16" \
--with_prior_preservation --prior_loss_weight=1.0 \
--seed=777 \
--resolution=512 \
--train_batch_size=1 \
--train_text_encoder \
--mixed_precision="fp16" \
--use_8bit_adam \
--gradient_accumulation_steps=1 \
--learning_rate=$learning_rate \
--lr_scheduler="constant" \
--lr_warmup_steps=$lr_warmup_steps \
--num_class_images=$num_class_images \
--sample_batch_size=4 \
--max_train_steps=$max_num_steps \
--save_interval=10000 \
--save_sample_prompt="gg" \
--concepts_list="concepts_list.json"
After running this lines of codes than i met the error like this:
Fetching 15 files: 100% 15/15 [00:11<00:00, 1.30it/s]
/usr/local/lib/python3.10/dist-packages/transformers/models/clip/feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
03/01/2024 04:00:04 - INFO - __main__ - Number of class images to sample: 60.
Generating class images: 100% 15/15 [03:17<00:00, 13.19s/it]
===================================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
================================================================================
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:105: UserWarning: /usr/lib64-nvidia did not contain libcudart.so as expected! Searching further paths...
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//172.28.0.1'), PosixPath('http'), PosixPath('8013')}
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('--logtostderr --listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https'), PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-eqky9bb41np1 --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true')}
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/datalab/web/pyright/typeshed-fallback/stdlib,/usr/local/lib/python3.10/dist-packages')}
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
warn(
/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/paths.py:27: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}
warn(
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 122
CUDA SETUP: TODO: compile library for specific version: libbitsandbytes_cuda122.so
CUDA SETUP: Defaulting to libbitsandbytes.so...
CUDA SETUP: CUDA detection failed. Either CUDA driver not installed, CUDA not installed, or you have multiple conflicting CUDA libraries!
CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.
Traceback (most recent call last):
File "/content/train_dreambooth.py", line 869, in <module>
main(args)
File "/content/train_dreambooth.py", line 571, in main
import bitsandbytes as bnb
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/__init__.py", line 6, in <module>
from .autograd._functions import (
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/_functions.py", line 5, in <module>
import bitsandbytes.functional as F
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/functional.py", line 13, in <module>
from .cextension import COMPILED_WITH_CUDA, lib
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cextension.py", line 41, in <module>
lib = CUDALibrary_Singleton.get_instance().lib
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cextension.py", line 37, in get_instance
cls._instance.initialize()
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cextension.py", line 27, in initialize
raise Exception('CUDA SETUP: Setup Failed!')
Exception: CUDA SETUP: Setup Failed!
Please, maybe anyone know how to resolve this so the training will be success and I can load the weight of the model. Thank you in advanced