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.

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

Now everything in transformer_options gets put in extra_options.

Control loras are controlnets where some of the weights are stored in
"lora" format: an up and a down low rank matrice that when multiplied
together and added to the unet weight give the controlnet weight.

This allows a much smaller memory footprint depending on the rank of the
matrices.

These controlnets are used just like regular ones.

Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.

Large refactor of the model detection and loading code.

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.