GitLab

This was broken because of recent changes so I fixed it and moved it from
the experiments repo.

Use the "lcm" sampler to sample them, you also have to use the
ModelSamplingDiscrete node to set them as lcm models to use them properly.

Converting Nan to zero is a bad idea because it makes it hard to tell when
something went wrong.

This should make things that use sampler_cfg_function behave like before.

Added an input argument for those that want the denoised output.

This means you can calculate the x0 prediction of the model by doing:
(input - cond) for example.

DDIM is the same as euler with a small difference in the inpaint code.
DDIM uses randn_like but I set a fixed seed instead.

I'm keeping it in because I'm sure if I remove it people are going to
complain.

apply_model in model_base now returns the denoised output.

This means that sampling_function now computes things on the denoised
output instead of the model output. This should make things more consistent
across current and future models.

cond and what is uncond.

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.

Try to keep models on the vram when possible.

Better lowvram mode for controlnets.

The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.

but faster.