Akegarasu / Akegarasu/lora-scripts
What is the problem of using torch < 2.3.0 to train FLUX LoRA
Open
- Dominant language
- Python
- Stars
- 6.1k
- Forks
- 699
- PR merge metrics
- No merged PRs in 30d
Description
I notice there is a function `def check_torch_gpu()` says it may not be able to train FLUX model properly with torch version ≤ 2.3.0, what exactly is the problem ?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.