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

Switch to using max for attention slicing in all cases for the time being. (#2569)

Browse Source
This commit is contained in:
Jonathan 2023-02-07 12:28:57 -06:00 committed by GitHub
parent 3efe9899c2
commit f0f3520bca
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ldm/invoke/generator/diffusers_pipeline.py
View File

@ -317,7 +317,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
# fix is in https://github.com/kulinseth/pytorch/pull/222 but no idea when it will get merged to pytorch mainline.
pass
else:
self.enable_attention_slicing(slice_size='auto')
self.enable_attention_slicing(slice_size='max')
def image_from_embeddings(self, latents: torch.Tensor, num_inference_steps: int,
conditioning_data: ConditioningData,