Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Same fix for ImageToLatentsInvocation

Browse Source
This commit is contained in:
Martin Kristiansen 2023-07-19 11:38:13 -04:00
parent 2ec9dab595
commit fface339ae
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/app/invocations/latent.py
View File

@ -686,7 +686,7 @@ class ImageToLatentsInvocation(BaseInvocation):
tiled: bool = Field(
default=False,
description="Encode latents by overlaping tiles(less memory consumption)")
fp32: bool = Field(False, description="Decode in full precision")
fp32: bool = Field(default=choose_precision(choose_torch_device())=='float32', description="Decode in full precision")
# Schema customisation