AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

Fix video shape error in full pipeline test script

Browse Source
This commit is contained in:
Daniel Gu
2025-12-23 11:14:05 +01:00
parent f9b947651f
commit e89d9c1951
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/ltx2_test_full_pipeline.py
View File

@@ -200,8 +200,6 @@ def main(args):
# Convert video to uint8 (but keep as NumPy array)
video = (video * 255).round().astype("uint8")
video = torch.from_numpy(video)
# video should already be frames first, reshape to channels-last (we want shape to be (*, F, H , W, C))
video = video.permute(0, 1, 3, 4, 2)
encode_video(
video[0],