Using Stable Diffision models for Colorization

[Selur]

using:

# Imports import sys import os from pathlib import Path import vapoursynth as vs # Ensure local module is found script_dir = Path(__file__).parent.resolve() if str(script_dir) not in sys.path: sys.path.insert(0, str(script_dir)) # getting Vapoursynth core core = vs.core # loading plugins core.std.LoadPlugin(path="F:/Hybrid/64bit/Vapoursynth/Lib/site-packages/vapoursynth/plugins2/akarin/libakarin.dll") core.std.LoadPlugin(path="F:/Hybrid/64bit/Vapoursynth/Lib/site-packages/vapoursynth/plugins2/libbestsource.dll") # Import scripts import vshavc_test as havc clip = core.bs.VideoSource(source="sample.mp4") # colorize using CMNet with external DiT (HAVC) clip = havc.HAVC_cmnet2dit(clip, max_memory_frames=10) # output clip.set_output()

(copied tcanny into the Support folder)
with:

F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vapoursynth>vspipe.exe c:\Users\Selur\Desktop\CMNET2DIT_test.vpy -c y4m --info Warning: Start detecting referenence frames Warning: Plugin F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vshavc_test\vsfilters\ColorFilter\Retinex\Retinex.dll is using API3 which is deprecated and will be removed shortly. Warning: Detection completed

it seems to be stuck no cpu or gpu usage,..