GitLab

Large refactor of the model detection and loading code.

This means arguments can be added without issues.

exponential scheduler is the one recommended with this sampler.

Try batching when cond sizes don't match with smart padding.

By default, when applying a mask to a condition, the entire image will
still be used for sampling. The new "set_area_to_bounds" option on the
node will allow the user to automatically limit conditioning to the
bounds of the mask.

I've also removed the dependency on torchvision for calculating bounding
boxes. I've taken the opportunity to fix some frustrating details in the
other version:
1. An all-0 mask will no longer cause an error
2. Indices are returned as integers instead of floats so they can be
   used to index into tensors.

This PR adds support for a Condition by Mask node. This node allows
conditioning to be limited to a non-rectangle area.

Callback format is: callback(step, x0, x)

Add a HypernetworkLoader node to use hypernetworks.

See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.

Tome increases sampling speed at the expense of quality.

Old workflows will still work.

On the KSamplers denoise of 1.0 is the same as txt2img but there was a
small difference on UniPC.