Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-06-07 07:44:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
50 Commits 6 Branches 0 Tags 16 MiB
09f87601e2
Commit Graph

11 Commits

Author SHA1 Message Date
Bakhtiyor Sulaymonov
abdcd2b17d
Merge branch 'main' into macos-compatibility 2025-03-06 12:36:18 +05:00
Yingda Chen
d0a086800a
Update prompt_extend.py 2025-03-06 13:11:22 +08:00
Bakhtiyor Sulaymonov
f7bd4d149f
Merge branch 'main' into macos-compatibility 2025-03-04 13:43:53 +05:00
Alan May
82c18d91a1
fix: correct Chinese ISO language code typo (#10) 
Fix incorrect Chinese language ISO code abbreviation
from CH to ZH
 2025-03-03 17:04:13 +08:00
Bakhtiyor Sulaymonov
5cb67c67e8 Fix MPS compatibility for I2V by adjusting device usage and dtype 2025-02-27 18:55:10 +05:00
Bakhtiyor Sulaymonov
68ae7184df Merge main branch and resolve conflicts in README.md 2025-02-27 12:21:11 +05:00
Bakhtiyor Sulaymonov
cf578ab14b Adapted model for macOS with M1 Pro chip and other improvements 2025-02-27 11:38:29 +05:00
Adrian Corduneanu
e2287e5126 Update text2video.py to reduce GPU memory by emptying cache (#44) 
* Update text2video.py to reduce GPU memory by emptying cache

If offload_model is set, empty_cache() must be called after the model is moved to CPU to actually free the GPU. I verified on a RTX 4090 that without calling empty_cache the model remains in memory and the subsequent vae decoding never finishes.

* Update text2video.py only one empty_cache needed before vae decode
 2025-02-27 11:38:28 +05:00
Bakhtiyor Sulaymonov
9d3d4d784f Check for cuda is available for macos 2025-02-26 22:18:18 +05:00
Adrian Corduneanu
0e3c42a830
Update text2video.py to reduce GPU memory by emptying cache (#44) 
* Update text2video.py to reduce GPU memory by emptying cache

If offload_model is set, empty_cache() must be called after the model is moved to CPU to actually free the GPU. I verified on a RTX 4090 that without calling empty_cache the model remains in memory and the subsequent vae decoding never finishes.

* Update text2video.py only one empty_cache needed before vae decode
 2025-02-26 18:56:57 +08:00
WanX-Video-1
65386b2e03 init upload 2025-02-25 22:07:47 +08:00