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

Allow bfloat16 to be configurable in invoke.yaml (#5469)

Browse Source 
* feat: allow bfloat16 to be configurable in invoke.yaml

* fix: `torch_dtype()` util

- Use `choose_precision` to get the precision string
- Do not reference deprecated `config.full_precision` flat (why does this still exist?), if a user had this enabled it would override their actual precision setting and potentially cause a lot of confusion.

---------

Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
This commit is contained in:
Millun Atluri
2024-01-12 13:40:37 -05:00
committed by GitHub
parent d4c36da3ee
commit 74e644c4ba
2 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/app/services/config/config_default.py
View File

@ -263,7 +263,7 @@ class InvokeAIAppConfig(InvokeAISettings):
# DEVICE
device : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", json_schema_extra=Categories.Device)
precision : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
precision : Literal["auto", "float16", "bfloat16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
# GENERATION
sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", json_schema_extra=Categories.Generation)