GitLab

Update LoadClip to load clip models for SDXL refiner.

Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.

Large refactor of the model detection and loading code.

Clean up a few things.

It's like bilinear but with slerp.

* wip

* latent dir

* fix

* fix

* now working

* mark todo

* remove server.py changes to separate PRt

---------
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>

Switch time.time to time.perf_counter for custom node import times.

Change the slow import message.

* allow nodes to map over lists

* make work with IS_CHANGED and VALIDATE_INPUTS

* give list outputs distinct socket shape

* add rebatch node

* add batch index logic

* add repeat latent batch

* deal with noise mask edge cases in latentfrombatch