Skip to content

Commit 148b7cf

Browse files
authored
[Docs] refactor text-to-video zero (huggingface#3049)
* fix: norm group test for UNet3D. * refactor text-to-video zero docs.
1 parent db0e248 commit 148b7cf

File tree

1 file changed

+2
-3
lines changed

1 file changed

+2
-3
lines changed

pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -374,9 +374,8 @@ def __call__(
374374
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
375375
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
376376
tensor will ge generated by sampling using the supplied random `generator`.
377-
output_type (`str`, *optional*, defaults to `"pil"`):
378-
The output format of the generate image. Choose between
379-
[PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
377+
output_type (`str`, *optional*, defaults to `"numpy"`):
378+
The output format of the generated image. Choose between `"latent"` and `"numpy"`.
380379
return_dict (`bool`, *optional*, defaults to `True`):
381380
Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
382381
plain tuple.

0 commit comments

Comments
 (0)