GitLab

They are loaded as CONTROL_NET objects because they are similar.

This decodes the image with the VAE in tiles which should be faster and
use less vram.

It's in the _for_testing section so I might change/remove it or even
add the functionality to the regular VAEDecode node depending on how
well it performs which means don't depend too much on it.

Moved socket output updates to all node executions
Made image rendering on nodes more generic

Might be useful for controlnets.

Reworked sockets to use socketio
Added progress to nodes
Added highlight to active node
Added preview to saveimage node

It can be used to apply multiple control nets at the same time.

There only needs to be one example in the folder.

LATENT is now a dict that can contain properties.

Put them in models/clip

It's pretty much the same as the LatentUpscale node for now but for images
in pixel space.

The models are modified in place before being used and unpatched after.
I think this is better than monkeypatching since it might make it easier
to use faster non pytorch unet inference in the future.

This can be used to "paste" one latent image on top of the other.

This node exposes more sampling options and makes it possible for example
to sample the first few steps on the latent image, do some operations on it
 and then do the rest of the sampling steps. This can be achieved using the
start_at_step and end_at_step options.