Wan2.1/wan
Adrian Corduneanu 65819c1d08
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.
2025-02-25 23:31:46 -08:00
..
configs init upload 2025-02-25 22:07:47 +08:00
distributed init upload 2025-02-25 22:07:47 +08:00
modules init upload 2025-02-25 22:07:47 +08:00
utils init upload 2025-02-25 22:07:47 +08:00
__init__.py init upload 2025-02-25 22:07:47 +08:00
image2video.py init upload 2025-02-25 22:07:47 +08:00
text2video.py Update text2video.py to reduce GPU memory by emptying cache 2025-02-25 23:31:46 -08:00