mirror of
https://github.com/ostris/ai-toolkit.git
synced 2026-01-26 16:39:47 +00:00
Actually use the correct timestep sampling instead of calculating it and moving on lol. Tested a few with it and it seems to work better.
This commit is contained in:
@@ -55,4 +55,6 @@ class CustomFlowMatchEulerDiscreteScheduler(FlowMatchEulerDiscreteScheduler):
|
||||
# Sort the timesteps in descending order
|
||||
timesteps, _ = torch.sort(timesteps, descending=True)
|
||||
|
||||
self.timesteps = timesteps.to(device=device)
|
||||
|
||||
return timesteps
|
||||
|
||||
Reference in New Issue
Block a user