kohya-ss / kohya-ss/sd-scripts
flux finetune always fills shared memory
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
I just noticed, that fine tuning FLUX with the command in the README (dataset image size 512,512, batch size 1) will result in 8GB of shared memory
Is this by design, or did I something wrong? Because a week ago I could fine tune without the need for any shared memory.
Also I noticed sampling images during fine-tune now takes double the time...
That's how it looks with commit 1286e00bb0fc34c296f24b7057777f1c37cf8e11
No shared memory, twice the speed during training and sampling images
Win10/4090
Thx
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the FLUX fine-tuning command in README and reproduce the reported behavior on Windows 10 with a 4090. Compare current shared-memory usage and sampling time with commit 1286e00bb0fc34c296f24b7057777f1c37cf8e11; done means identifying whether the change is an intentional design difference or a regression and documenting the relevant cause.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100