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

Quash memory leak when compel invocation called (#3633)

Browse Source 
This commit prevents each image generation from leaking ~160 MB of VRAM.
Thanks to @damian0815 and @StAlKeR7779 for helping to sort this out.
This commit is contained in:
blessedcoolant 2023-07-04 06:33:56 +12:00 committed by GitHub
commit b4b760d9e9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
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/compel.py
View File

@ -2,6 +2,7 @@ from typing import Literal, Optional, Union
from pydantic import BaseModel, Field
from contextlib import ExitStack
import re
import torch
from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
from .model import ClipField
@ -56,6 +57,7 @@ class CompelInvocation(BaseInvocation):
},
}
@torch.no_grad()
def invoke(self, context: InvocationContext) -> CompelOutput:
tokenizer_info = context.services.model_manager.get_model(