kohya-ss / kohya-ss/sd-scripts
pls help, I am trying to start the training and getting the below error
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
accelerate launch --num_cpu_threads_per_process=2 "./train_db.py" --enable_bucket --min_bucket_reso=256 --max_bucket_reso=2048 --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5" --train_data_dir="C:/Users/afbaloch/Desktop/byd_car\img" --resolution="512,512" --output_dir="C:/Users/afbaloch/Desktop/byd_car\model" --logging_dir="C:/Users/afbaloch/Desktop/byd_car\log" --save_model_as=safetensors --output_name="bydcar" --lr_scheduler_num_cycles="1" --max_data_loader_n_workers="0" --learning_rate_te="1e-05" --learning_rate="1e-05" --lr_scheduler="constant_with_warmup" --lr_warmup_steps="66" --train_batch_size="1" --max_train_steps="660" --save_every_n_epochs="1" --mixed_precision="fp16" --save_precision="fp16" --cache_latents --cache_latents_to_disk --optimizer_type="AdamW8bit" --max_data_loader_n_workers="0" --bucket_reso_steps=64 --xformers --bucket_no_upscale --noise_offset=0.0
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by running the provided accelerate command with train_db.py and capture the error output, which is missing from the issue. Then inspect train_db.py and the reported failure path; the issue is ready to close when the startup error is reproduced, its cause is identified, and the training command completes successfully.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100