theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix usp dependency

Browse Source
This commit is contained in:
Artiprocher
2025-03-25 19:26:24 +08:00
parent d0fed6ba72
commit 4e43d4d461
5 changed files with 29 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/wanvideo/README.md
View File

@@ -58,7 +58,7 @@ pip install xfuser>=0.4.3
```
```bash
torchrun --standalone --nproc_per_node=8 ./wan_14b_text_to_video_usp.py
torchrun --standalone --nproc_per_node=8 examples/wanvideo/wan_14b_text_to_video_usp.py
```
2. Tensor Parallel

2
examples/wanvideo/wan_14b_text_to_video.py
View File

@@ -33,4 +33,4 @@ video = pipe(
num_inference_steps=50,
seed=0, tiled=True
)
save_video(video, "video1.mp4", fps=25, quality=5)
save_video(video, "video1.mp4", fps=25, quality=5)

3
examples/wanvideo/wan_14b_text_to_video_usp.py
View File

@@ -54,4 +54,5 @@ video = pipe(
num_inference_steps=50,
seed=0, tiled=True
)
save_video(video, "video1.mp4", fps=25, quality=5)
if dist.get_rank() == 0:
save_video(video, "video1.mp4", fps=25, quality=5)