theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 16:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

optimize stepvideo vae

Browse Source
This commit is contained in:
Artiprocher
2025-02-18 17:28:05 +08:00
parent f191353cf4
commit 9cff769fbd
7 changed files with 197 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/stepvideo/README.md
View File

@@ -10,6 +10,8 @@ StepVideo is a state-of-the-art (SoTA) text-to-video pre-trained model with 30 b
For original BF16 version, please see [`./stepvideo_text_to_video.py`](./stepvideo_text_to_video.py). 80G VRAM required.
We also support auto-offload, which can reduce the VRAM requirement to **24GB**; however, it requires 2x time for inference. Please see [`./stepvideo_text_to_video_low_vram.py`](./stepvideo_text_to_video_low_vram.py).
https://github.com/user-attachments/assets/5954fdaa-a3cf-45a3-bd35-886e3cc4581b
For FP8 quantized version, please see [`./stepvideo_text_to_video_quantized.py`](./stepvideo_text_to_video_quantized.py). 40G VRAM required.