GitLab

Do inference in fp32 to make sure quality stays the exact same.

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.

For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13

Try to keep models on the vram when possible.

Better lowvram mode for controlnets.