This website requires JavaScript.
Explore
Help
Register
Sign In
github
/
InvokeAI
Watch
1
Star
1
Fork
0
You've already forked InvokeAI
mirror of
https://github.com/invoke-ai/InvokeAI.git
synced
2026-02-01 23:35:10 -05:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
b44415415a241a0d81157f66b0b5dededb171706
InvokeAI
/
invokeai
History
Ryan Dick
b44415415a
Use a default tile size of 1024 for VAE encode/decode operations in upscaling workflows. Previously, the model default was used (512 for SD1, 1024 for SDXL). Larger tile sizes help to prevent tiling artifacts.
2025-02-14 14:23:42 +11:00
..
app
Make ruff gods happy
2025-02-13 19:24:01 +11:00
assets
feat(api): chore: pydantic & fastapi upgrade
2023-10-17 14:59:25 +11:00
backend
Add endpoint for emptying the model cache. Also, adds a threading lock to the ModelCache to make it thread-safe.
2025-01-30 09:18:28 -05:00
configs
Remove dependency on flux config files
2024-08-26 20:17:50 -04:00
frontend
Use a default tile size of 1024 for VAE encode/decode operations in upscaling workflows. Previously, the model default was used (512 for SD1, 1024 for SDXL). Larger tile sizes help to prevent tiling artifacts.
2025-02-14 14:23:42 +11:00
invocation_api
Added support for bounding boxes in the Invocation API
2024-08-26 08:03:30 +10:00
version
chore: bump version to v5.6.2
2025-02-14 13:13:33 +11:00
__init__.py
…