Skip to content

NoiseScheduler parameters for StableDiffusion are wrong #2049

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
DaniyarM opened this issue Sep 5, 2023 · 6 comments · May be fixed by #2065
Open

NoiseScheduler parameters for StableDiffusion are wrong #2049

DaniyarM opened this issue Sep 5, 2023 · 6 comments · May be fixed by #2065
Labels
stale stat:awaiting response from contributor type:Bug Something isn't working

Comments

@DaniyarM
Copy link

DaniyarM commented Sep 5, 2023

NoiseScheduler https://github.com/keras-team/keras-cv/blob/master/keras_cv/models/stable_diffusion/noise_scheduler.py contains a bug with default parameters. For a pretrained SD it must be: NoiseScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule='scaled_linear', clip_sample=False). For now it is: NoiseScheduler(beta_start=0.0001, beta_end=0.02, beta_schedule='linear', clip_sample=True). As I understand it, this happened because of copy-paste with a hugging face (where the default parameters are taken for some old GANs).
@DaniyarM DaniyarM added the type:Bug Something isn't working label Sep 5, 2023
@jbischof
Copy link
Contributor

jbischof commented Sep 5, 2023

Thanks @DaniyarM! Can you share the source of the corrected parameters?

@DaniyarM
Copy link
Author

DaniyarM commented Sep 5, 2023

It can be obtained from huggingface's diffusers like that :
from diffusers import DDIMScheduler
scheduler = DDIMScheduler.from_pretrained('runwayml/stable-diffusion-v1-5', subfolder='scheduler')
print(scheduler)

Also, it can be found in that article: https://arxiv.org/pdf/2305.08891v2.pdf (Table 1).

@ianstenbit
Copy link
Contributor

Thanks @DaniyarM for pointing this out -- feel free to send a PR to update this!

@yuvraj-wale yuvraj-wale linked a pull request Sep 8, 2023 that will close this issue
Open
5 tasks
@github-actions GitHub Actions
Copy link

This issue is stale because it has been open for 180 days with no activity. It will be closed if no further activity occurs. Thank you.

@github-actions github-actions bot added the stale label Feb 14, 2025
@sachinprasadhs
Copy link
Collaborator

Thanks for reporting the issue! We have consolidated the development of KerasCV into the new KerasHub package, which supports image, text, and multi-modal models. Please read the announcement. KerasHub will support all the core functionality of KerasCV.

KerasHub can be installed with !pip install -U keras-hub. Documentation and guides are available at keras.io/keras_hub.

With our focus shifted to KerasHub, we are not planning any further development or releases in KerasCV. If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file an issue with KerasHub.

@github-actions GitHub Actions
Copy link

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

@github-actions github-actions bot added the stale label May 22, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
stale stat:awaiting response from contributor type:Bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix Incorrect Default Parameters in NoiseScheduler for StableDiffusion yuvraj-wale/keras-cv
4 participants
@jbischof @ianstenbit @DaniyarM @sachinprasadhs