kijai cc06d71ca0 Workaround for bug in pytorch 2.9.0 that makes the VAE use crazy amounts of VRAM ...

This is probably caused by:

https://github.com/pytorch/pytorch/pull/164027/files

That disables cudnn when using half precision VAE, this workaround simply uses fp32 for the Conv3D operations.

2025-10-16 17:10:05 +03:00

..

configs

init

2025-02-25 20:03:08 +02:00

modules

FlashVSR: Add strength setting

2025-10-15 19:11:41 +03:00

radial_attention

support sparse sageattn2 for radial attn

2025-07-23 00:27:14 +03:00

schedulers

Add FlowMatchSAODEStableScheduler

2025-10-02 00:53:49 +03:00

LICENSE

Add alternative offloading method from Diffsynth

2025-03-02 14:37:08 +02:00

wan_video_vae.py

Workaround for bug in pytorch 2.9.0 that makes the VAE use crazy amounts of VRAM

2025-10-16 17:10:05 +03:00