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
Copy file name to clipboardExpand all lines: examples/community/rerender_a_video.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -632,7 +632,7 @@ def __call__(
632
632
The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
633
633
instead.
634
634
frames (`List[np.ndarray]` or `torch.Tensor`): The input images to be used as the starting point for the image generation process.
635
-
control_frames (`List[np.ndarray]` or `torch.Tensor`): The ControlNet input images condition to provide guidance to the `unet` for generation or any callable object to convert frame to control_frame.
635
+
control_frames (`List[np.ndarray]` or `torch.Tensor` or `Callable`): The ControlNet input images condition to provide guidance to the `unet` for generation or any callable object to convert frame to control_frame.
636
636
strength ('float'): SDEdit strength.
637
637
num_inference_steps (`int`, *optional*, defaults to 50):
638
638
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
0 commit comments