GitLab

To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.

Make it use the same dtype as the text encoder.

Moved all the sag related code to comfy_extras/nodes_sag.py

* First SAG test

* need to put extra options on the model instead of patcher

* no errors and results seem not-broken

* Use @ashen-uncensored formula, which works better!!!

* Fix a crash when using weird resolutions. Remove an unnecessary UNet call

* Improve comments, optimize memory in blur routine

* SAG works with sampler_cfg_function

comfy.ops -> comfy.ops.disable_weight_init

This should make it more clear what they actually do.

Some unused code has also been removed.

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

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.

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