kanshan/diffusers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

make style

Browse Source
This commit is contained in:
Patrick von Platen
2023-01-12 20:02:41 +00:00
parent 9a5d3322e7
commit 135567f18e
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/diffusers/schedulers/scheduling_pndm.py
+2 -2
View File
@@ -83,8 +83,8 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
step there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`, step there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
otherwise it uses the value of alpha at step 0. otherwise it uses the value of alpha at step 0.
prediction_type (`str`, default `epsilon`, optional): prediction_type (`str`, default `epsilon`, optional):
prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion process)
process) or `v_prediction` (see section 2.4 https://imagen.research.google/video/paper.pdf) or `v_prediction` (see section 2.4 https://imagen.research.google/video/paper.pdf)
steps_offset (`int`, default `0`): steps_offset (`int`, default `0`):
an offset added to the inference steps. You can use a combination of `offset=1` and an offset added to the inference steps. You can use a combination of `offset=1` and
`set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in