This commit is contained in:
kijai 2024-10-23 18:56:51 +03:00
commit 4b9d43d318

View File

@ -4,6 +4,9 @@
# WORK IN PROGRESS # WORK IN PROGRESS
## Requires flash_attn ! ## Requires flash_attn !
Not sure if this can be worked around, I compiled a wheel for my Windows setup (Python 3.12, torch 2.5.0+cu124) that worked for me:
https://huggingface.co/Kijai/Mochi_preview_comfy/blob/main/flash_attn-2.6.3-cp312-torch250cu125-win_amd64.whl
Depending on frame count can fit under 20GB, VAE decoding is heavy and there is experimental tiled decoder (taken from CogVideoX -diffusers code) which allows higher frame counts, so far highest I've done is 97 with the default tile size 2x2 grid. Depending on frame count can fit under 20GB, VAE decoding is heavy and there is experimental tiled decoder (taken from CogVideoX -diffusers code) which allows higher frame counts, so far highest I've done is 97 with the default tile size 2x2 grid.