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

Eliminate the need for IPAdapter.initialize().

Browse Source
This commit is contained in:
Ryan Dick
2023-09-14 15:02:59 -04:00
parent d114d0ba95
commit 781e8521d5
3 changed files with 44 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
invokeai/app/invocations/latent.py
View File

@ -434,10 +434,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
input_image = context.services.images.get_pil_image(ip_adapter.image.image_name)
if not ip_adapter_model.is_initialized():
# TODO(ryan): Do we need to initialize every time? How long does initialize take?
ip_adapter_model.initialize(unet)
# TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
# models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
with image_encoder_model_info as image_encoder_model: