Skip to content

Conversation

@dg845
Copy link
Collaborator

@dg845 dg845 commented Dec 24, 2023

What does this PR do?

This PR changes the SD and SD-XL LCM-LoRA README examples to use a learning rate of 1e-4 (instead of 1e-6) to match the script defaults. (1e-4 is also a better learning rate value.)

Fixes #6288.

Before submitting

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@patrickvonplaten
@patil-suraj
@sayakpaul
@Zeqiang-Lai

@sayakpaul sayakpaul merged commit a3d31e3 into huggingface:main Dec 25, 2023
@dg845 dg845 deleted the lcm-lora-scripts-fix-example-lr branch December 25, 2023 22:45
donhardman pushed a commit to donhardman/diffusers that referenced this pull request Dec 29, 2023
…face#6304)

Change README LCM-LoRA example learning rates to 1e-4.
antoine-scenario pushed a commit to antoine-scenario/diffusers that referenced this pull request Jan 2, 2024
…face#6304)

Change README LCM-LoRA example learning rates to 1e-4.
AmericanPresidentJimmyCarter pushed a commit to AmericanPresidentJimmyCarter/diffusers that referenced this pull request Apr 26, 2024
…face#6304)

Change README LCM-LoRA example learning rates to 1e-4.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

The default learning rate of LCM LoRA training is too small

2 participants