huggingface / huggingface/diffusers
examples\controlnet add only_mid_control=true and sd_locked=false
- Dominant language
- Python
- Stars
- 34.5k
- Forks
- 7.3k
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 91
Description
**Is your feature request related to a problem? Please describe.**
The [original controlnet training tutorial](https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md#other-options) mentions the options
* `only_mid_control=True`: _This can be helpful when your computation power is limited and want to speed up the training, or when you want to facilitate the "global" context learning._
* `sd_locked=False`: _This will unlock some layers in SD and you will train them as a whole._
**Describe the solution you'd like**
Please make the option available as well.
**Describe alternatives you've considered**
Going back to the original training script without any optimizations implemented.
Contributor guide
Assessment
This issue has not been assessed yet.