kohya-ss / kohya-ss/sd-scripts
An error occurred while training sd1.5 controlnet using train_controlnet.py
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
I encountered the following error while training SD1.5 ControlNet using train_controlnet.py: “RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)”
Interestingly, I was able to train LoRA using train_network.py without any issues.
I run the scripts in cuda11.8 and pytorch 2.1.2.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with train_controlnet.py and the reported RuntimeError under CUDA 11.8 and PyTorch 2.1.2; compare the training path with train_network.py, which reportedly succeeds. Reproduce the SD1.5 ControlNet training failure and determine whether the issue is actionable in sd-scripts or depends on the reported PyTorch/CUDA environment.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100