InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00

Files

Lincoln Stein d34655fd58 Fix(model manager): Improve calculation of Z-Image VAE working memory needs (#8740 )

* Fix Z-Image VAE encode/decode to request working memory

Co-authored-by: lstein <111189+lstein@users.noreply.github.com>

* fix: remove check for non-flux vae

* fix: remove check for non-flux vae: latents_to_image

* Remove conditional estimation tests

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: lstein <111189+lstein@users.noreply.github.com>

2026-01-08 17:48:09 +00:00

invocations

Fix(model manager): Improve calculation of Z-Image VAE working memory needs (#8740 )

2026-01-08 17:48:09 +00:00

routers

add debugging statements and a timeout to download test

2024-03-01 10:42:33 +11:00

services

refactor: model manager v3 (#8607 )

2025-10-15 10:18:53 +11:00

util

tests: use dangerously_run_function_in_subprocess to fix configure_torch_cuda_allocator tests