GitLab

support masked attention.

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 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.

Now everything in transformer_options gets put in extra_options.

There's no reason for the whole CrossAttention object to be repeated when
only the operation in the middle changes.