Skip to content

Potential bug in repaint? #9900

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.

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

Closed
jingweiz opened this issue Nov 10, 2024 · 3 comments · Fixed by #10185
Closed

Potential bug in repaint? #9900

jingweiz opened this issue Nov 10, 2024 · 3 comments · Fixed by #10185

Comments

@jingweiz
Copy link

prev_known_part = (alpha_prod_t_prev**0.5) * original_image + ((1 - alpha_prod_t_prev) ** 0.5) * noise

According to line5 of algorithm 1 in the paper, the second part in line 322 should remove the **0.5?
thanks!

@SahilCarterr
Copy link
Contributor

I also think that should be removed as mentioned in algorithm 1 Line 5 from the paper

$$x_{t-1}^{known} \ =\ \sqrt{\overline{\alpha }_{t}} x_0 \ +( 1-\ \overline{\alpha }_{t}) \epsilon$$

Corrected

prev_known_part = (alpha_prod_t_prev**0.5) * original_image + ((1 - alpha_prod_t_prev)) * noise 

I don't think Fixing this might cause any issue in RePaintScheduler
@sayakpaul WDYT?

@sayakpaul
Copy link
Member

Cc: @yiyixuxu

Copy link
Contributor

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

@github-actions github-actions bot added the stale Issues that haven't received updates label Dec 10, 2024
@yiyixuxu yiyixuxu removed the stale Issues that haven't received updates label Dec 16, 2024
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 a pull request may close this issue.

4 participants