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
Hi, not sure if it's a bug or not, but when i want to continue a textual inversion it doesn't doit from the last step done.
i tried to train model with my face, i first run it with 5000 steps, not enough, so i did again for 10000 steps, it started again from the 5000 one. But it wasn't enough so i run with this time 50 000 steps, and surprises, instead to start from the 10 000 already done, it started from the 5 000 one.
on my folder i see embedding saved till 26 500 steps (my colab disonnected so couldn't continue more), but if i try to run it again, it will start at 9 500 and i will lose all the work already done.
Any idea why? is it a bug?
My set up:
Colab, with self hosted automatic111 on my drive.
On drive, last embedding ) 26500
When i mount the drive in colab, last embedding = 9500
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi, not sure if it's a bug or not, but when i want to continue a textual inversion it doesn't doit from the last step done.
i tried to train model with my face, i first run it with 5000 steps, not enough, so i did again for 10000 steps, it started again from the 5000 one. But it wasn't enough so i run with this time 50 000 steps, and surprises, instead to start from the 10 000 already done, it started from the 5 000 one.
on my folder i see embedding saved till 26 500 steps (my colab disonnected so couldn't continue more), but if i try to run it again, it will start at 9 500 and i will lose all the work already done.
Any idea why? is it a bug?
My set up:
Colab, with self hosted automatic111 on my drive.
On drive, last embedding ) 26500
When i mount the drive in colab, last embedding = 9500
Thanks
Beta Was this translation helpful? Give feedback.
All reactions