You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When generating images setting the seed doesn't give reproducible results, the images (and clip scores) are different every time the code is run with same seed, any idea why?
The text was updated successfully, but these errors were encountered:
andrea-gatto
changed the title
Setting the seed gives different samples
Setting the seed gives different results each time the code is run
Jun 15, 2022
@andrea-gatto Yes, it is because some components of the diffusion process use non-deterministic algorithms like for example: pytorch/pytorch#68961. There is no workaround for the moment.
When generating images setting the seed doesn't give reproducible results, the images (and clip scores) are different every time the code is run with same seed, any idea why?
The text was updated successfully, but these errors were encountered: