GitLab

comfy.ops -> comfy.ops.disable_weight_init

This should make it more clear what they actually do.

Some unused code has also been removed.

* Prevent cleaning graph state on undo/redo

* Remove pause rendering due to LG bug

Use fp16 text encoder weights for CPU inference to lower memory usage.

- Addressing the issue where an unnecessary hidden panel disrupts the drawing.

Use a simple CLIP model implementation instead of the one from
transformers.

This will allow some interesting things that would too hackish to implement
using the transformers implementation.

# Conflicts:
#	web/extensions/core/widgetInputs.js

* renewal mask editor

* fix: ignoring keydown when 2nd open

--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.