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

add support for "balanced" attention slice size

Browse Source
This commit is contained in:
Lincoln Stein
2023-08-17 16:11:09 -04:00
parent 23b4e1cea0
commit b69f26c85c
7 changed files with 38 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/features/CONFIGURATION.md
View File

@ -184,7 +184,7 @@ These options tune InvokeAI's memory and performance characteristics.
|-----------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `sequential_guidance` | `false` | Calculate guidance in serial rather than in parallel, lowering memory requirements at the cost of some performance loss |
| `attention_type` | `auto` | Select the type of attention to use. One of `auto`,`normal`,`xformers`,`sliced`, or `torch-sdp` |
| `attention_slice_size` | `auto` | When "sliced" attention is selected, set the slice size. One of `auto`, `max` or the integers 1-8|
| `attention_slice_size` | `auto` | When "sliced" attention is selected, set the slice size. One of `auto`, `balanced`, `max` or the integers 1-8|
| `force_tiled_decode` | `false` | Force the VAE step to decode in tiles, reducing memory consumption at the cost of performance |
### Device