modelscope / modelscope/DiffSynth-Studio
通过配置显存管理和loadhot为True情况下，跑十几张图，每张图来回切不同lora方式，显存会不断往上涨，有什么办法解决吗，让显存能稳定下来？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
通过配置显存管理和loadhot为True情况下，跑十几张图，每张图来回切不同lora方式，显存会不断往上涨，有什么办法解决吗，让显存能稳定下来？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the report with memory management configured and loadhot set to true, generating more than ten images while switching between different LoRA methods for each image. Measure GPU memory throughout the run and compare whether it continues increasing. Done means the reproduction is understood and GPU memory remains stable or the issue has a documented limitation and workaround.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100