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

Temporary force set vae to same precision as unet

Browse Source
This commit is contained in:
Sergey Borisov 2023-08-10 23:17:09 +03:00 committed by Kent Keirsey
parent d0fee93aac
commit 2ef6a8995b
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -181,6 +181,8 @@ class InpaintInvocation(BaseInvocation):
device = context.services.model_manager.mgr.cache.execution_device device = context.services.model_manager.mgr.cache.execution_device
dtype = context.services.model_manager.mgr.cache.precision dtype = context.services.model_manager.mgr.cache.precision
vae.to(dtype=unet.dtype)
pipeline = StableDiffusionGeneratorPipeline( pipeline = StableDiffusionGeneratorPipeline(
vae=vae, vae=vae,
text_encoder=None, text_encoder=None,