ryan/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support for Control Loras.

Browse Source 
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.
This commit is contained in:
comfyanonymous
2023-08-18 02:46:11 -04:00
parent 39ac856a33
commit d6e4b342e6
6 changed files with 216 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/samplers.py
View File

@@ -478,7 +478,7 @@ def pre_run_control(model, conds):
timestep_end = None
percent_to_timestep_function = lambda a: model.sigma_to_t(model.t_to_sigma(torch.tensor(a) * 999.0))
if 'control' in x[1]:
x[1]['control'].pre_run(model.inner_model, percent_to_timestep_function)
x[1]['control'].pre_run(model.inner_model.inner_model, percent_to_timestep_function)
def apply_empty_x_to_equal_area(conds, uncond, name, uncond_fill_func):
cond_cnets = []