wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-03-22 17:43:33 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity

Inplace VAE output processing to reduce peak RAM consumption. (#13028)

Browse Source
This commit is contained in:
Jukka Seppänen 2026-03-18 02:20:49 +02:00 committed by GitHub
parent 8b9d039f26
commit 735a0465e5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/sd.py
View File

@ -455,7 +455,7 @@ class VAE:
self.output_channels = 3
self.pad_channel_value = None
self.process_input = lambda image: image * 2.0 - 1.0
self.process_output = lambda image: torch.clamp((image + 1.0) / 2.0, min=0.0, max=1.0)
self.process_output = lambda image: image.add_(1.0).div_(2.0).clamp_(0.0, 1.0)
self.working_dtypes = [torch.bfloat16, torch.float32]
self.disable_offload = False
self.not_video = False