kohya-ss / kohya-ss/sd-scripts

crshed when use 2.1 SD ckpt, changed to 1.5,still crash

Open
#105 3 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.2k
Forks
1.2k
Avg merge
11m
Merged PRs (30d)
2

Description

when choose 2.1 ckpt,it crashed as misssize,like no yaml in webui
then i choose 1.5,it seems like this:
it is a cloud machine,i have no D:\ai folder.

steps: 0%| | 0/25 [00:00
File "C:\Users\Administrator\1\lora\sd-scripts\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "C:\Users\Administrator\1\lora\sd-scripts\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
simple_launcher(args)
File "C:\Users\Administrator\1\lora\sd-scripts\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:\\Users\\Administrator\\1\\lora\\sd-scripts\\venv\\Scripts\\python.exe', 'lora_train_popup.py']' returned non-zero exit status 1.

i have only C:\

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the checkpoint training failure through lora_train_popup.py and inspect the traceback around bitsandbytes/csrc/ops.cu and the accelerate launch command. Compare the 2.1 and 1.5 checkpoint paths and environment details. Done should be a confirmed diagnosis with a verified resolution or clearly documented incompatibility.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, tooling
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.