huggingface / huggingface/diffusers

examples\controlnet add only_mid_control=true and sd_locked=false

Open
#5,070 9 comments 1 reaction 0 assignees View on GitHub
contributions-welcome Good second issue
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.