This forum uses cookies
This forum makes use of cookies to store your login information if you are registered, and your last visit if you are not. Cookies are small text documents stored on your computer; the cookies set by this forum can only be used on this website and pose no security risk. Cookies on this forum also track the specific topics you have read and when you last read them. Please confirm whether you accept or reject these cookies being set.

A cookie will be stored in your browser regardless of choice to prevent you being asked this question again. You will be able to change your cookie settings at any time using the link in the footer.

Using Stable Diffision models for Colorization
Just downloaded https://github.com/vapoursynth/vapoursyn...#artifacts ->
vapoursynth-win_amd64 which contains vapoursynth-77-cp312-abi3-win_amd64.whl Smile
(running a test encode with BasicVSR++ atm.)
=> 5000 frame test encode ran without freezing.

Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Offline between (including) 29th of June and 5th of July => RochHarz Festival
Reply
I installed R77 over R76
And now I get the following error

2026-06-12 19:44:24.970 Failed to evaluate the script: Python exception: No module named 'cv2' Traceback (most recent call last): File "vapoursynth.pyx", line 3623, in vapoursynth._vpy_evaluate File "vapoursynth.pyx", line 3624, in vapoursynth._vpy_evaluate File "D:\PProjects\vs-havc_dev\vs_test_debug_no-gpu\CMNET2DIT_test.vpy", line 15, in import vshavc_test as havc File "D:\PProjects\vs-havc_dev\vs_test_debug_no-gpu\vshavc_test\__init__.py", line 34, in from vshavc_test.havc_utils import _get_tune_id, convert_format_RGB24, restore_format, HAVC_read_video, rgb_denoise File "D:\PProjects\vs-havc_dev\vs_test_debug_no-gpu\vshavc_test\havc_utils.py", line 18, in import cv2 ModuleNotFoundError: No module named 'cv2'

Previously this script was working and cv2 is installed on my side (I just updated R76 with R77).

I will wait your release before confirm that the bug is fixed.

Dan
Reply
'pip list' does list cv2 ? (at least I don't install cv/cv2 normally)
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Offline between (including) 29th of June and 5th of July => RochHarz Festival
Reply
cv2 is in the "opencv-python" package, and of course is installed (I also tried to reinstall)

Dan
Reply
Strange.
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Offline between (including) 29th of June and 5th of July => RochHarz Festival
Reply
I tested vs_cmnet2dit() with the last dev version with R77 released by you today, and it works with no issues.
I think that the thread deadlock bug has been fixed.

Dan
Reply
you can enable again (without core.num_threads=1) the filter CMNet2DiT which is currently disabled.

Dan
Reply
Will do. (probably tomorrow)
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Offline between (including) 29th of June and 5th of July => RochHarz Festival
Reply
Uploaded a new dev version which enabled CMNet2DiT and removes the thread=1 limitation.
(uploading a new torch-add-on,.. upload will be done in ~ 1/2 hours)

Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Offline between (including) 29th of June and 5th of July => RochHarz Festival
Reply
As a natural extension of the "Fix Image" tab, I've added the new "Fix Video" tab.

Suppose you've already colorized a clip with CMNET2 and DitServerRPC. There will be a folder called "ref_qwen" containing the colored frames.
Suppose you've viewed the clip and want to change the color of some frames. Let's say these frames range from #34 to #525. After fixing them with the "Fix Image" tab, you can recolor the video only in the identified frame range (in this case, from #34 to #525). As shown in the image below.

[Image: attachment.php?aid=3646]

I hope this helps; in some cases, it was necessary for me (which is why I added the implementation).

Since for technical reasons, I still need to re-encode the entire clip, it's mandatory to use as input the clip already colorized and to have NVEnC installed as explained in the README.

Dan


Attached Files Thumbnail(s)
   
Reply


Forum Jump:


Users browsing this thread: 4 Guest(s)