lllyasviel / lllyasviel/ControlNet
Training still OOM on 8GB gpu.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
It seems that I already used many tricks but training still OOM for 8GB gpu. But inference is good now.
This is strange because I know some textural inversion or dreambooth can be trained on 8GB.
What is the secrect of Automatic1111's optimization? Although xformers may help a bit, the currect sliced attention should require even smaller mem than xformers.
Does it make sence to move text encoder and vae outside gpu when training?
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
No file, test, or entry point is named. Start by tracing the training path and comparing its GPU memory use with inference, sliced attention, and the proposed text-encoder and VAE placement; done would mean identifying a concrete optimization that prevents out-of-memory failures on an 8GB GPU.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100