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.

Deoldify Vapoursynth filter
Hi NASS,

  Can you provide a small sample and the script used.

Dan

(Yesterday, 14:35)Selur Wrote: updated Hybrid_havc_test, which should update the tool-tips.

Cu Selur

Now, it's Okay.

It is missing only the too-tip for "Retry (threshold/model)" you can add:  
"If Retry (threshold) > 0, this value will be used to detect frames with insufficient permanent-memory coverage and in this case the frame with missing good references will be colorized on the fly, suggested value: 0 (disabled) or 0.20-0.35 . The colorization models can be:  
HAVC (Deoldify + DDColor)  #  fast, but the quality is not good if compared to DiT models 
DiT fp4/int4  (depending on GPU used) # very good quality but can slow-down the inference speed by about 40%-50%".

Thanks,
Dan
Reply
Hi Dan. Thanks so much for your reply. Here's the script in dev version ( Motion Distortion + Color jump ):
# Imports
import sys
import os
import vapoursynth as vs
# getting Vapoursynth core
core = vs.core
# Import scripts folder
scriptPath = 'C:/Program Files/Hybrid/64bit/vsscripts'
sys.path.insert(0, os.path.abspath(scriptPath))
# loading plugins
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/MiscFilter/MiscFilters/MiscFilters.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/SourceFilter/LSmashSource/LSMASHSource.dll")
# Import scripts
import vsdeoldify as havc
import validate
# Source: 'C:\Users\NASS\Desktop\outestny_restoredcolor.mp4'
# clip current meta; color space: YUV420P8, bit depth: 8, resolution: 960x720, fps: 24, color matrix: 709, color primaries: Unspecific, color transfer: BT.709, yuv luminance scale: limited, scanorder: progressive, full height: true (Source)
# Loading 'C:\Users\NASS\Desktop\outestny_restoredcolor.mp4Ä using LWLibavSource
clip = core.lsmas.LWLibavSource(source="C:/Users/NASS/Desktop/outestny_restoredcolor.mp4", format="YUV420P8", stream_index=0, cache=0, prefer_hw=0)
frame = clip.get_frame(0)
# setting color matrix to 709.
clip = core.std.SetFrameProps(clip, _Matrix=vs.MATRIX_BT709)
# setting color transfer (vs.TRANSFER_BT709), if it is not set.
if validate.transferIsInvalid(clip):
clip = core.std.SetFrameProps(clip=clip, _Transfer=vs.TRANSFER_BT709)
# setting color primaries info (to vs.PRIMARIES_BT709), if it is not set.
if validate.primariesIsInvalid(clip):
clip = core.std.SetFrameProps(clip=clip, _Primaries=vs.PRIMARIES_BT709)
# setting color range to TV (limited) range.
prop_name = '_Range' if core.core_version.release_major >= 74 else '_ColorRange'
clip = core.std.SetFrameProps(clip=clip, **{prop_name: vs.RANGE_LIMITED})
# making sure frame rate is set to 24fps
clip = core.std.AssumeFPS(clip=clip, fpsnum=24, fpsden=1)
# making sure the detected scan type is set (detected: progressive)
clip = core.std.SetFrameProps(clip=clip, _FieldBased=vs.FIELD_PROGRESSIVE) # scan type: progressive
# adjusting color space from YUV420P8 to RGB24 for vsColorAdjust
clip = core.resize.Bicubic(clip=clip, format=vs.RGB24, matrix_in_s="709", range_in_s="limited", range_s="full")
# stabilize colors using ColorAdjust (HAVC)
clip = havc.HAVC_ColorAdjust(clip, BlackWhiteTune="light", BlackWhiteMode=6)
# adjusting output color from RGB24 to YUV420P8 for x264Model
clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="709", range_in_s="full", range_s="limited")
# set output frame rate to 24fps (progressive)
clip = core.std.AssumeFPS(clip=clip, fpsnum=24, fpsden=1)
# output
clip.set_output()
# clip current meta; color space: YUV420P8, bit depth: 8, resolution: 960x720, fps: 24, color matrix: 709, color primaries: Unspecific, color transfer: BT.709, yuv luminance scale: limited, scanorder: progressive, full height: true (Meta)
# script was created by Hybrid 2026.05.22.1

It’s a shame because this is a really great feature, but Motion Distortion Issue + Color jump affects the final result. We definitely need to find a solution!

Thanks so much Dan

NASS

In the original version (Hybrid_2026.03.21.1_SETUP) and VapoursynthR73_torch_2026.02.26 with the old colormnet, there is no color-jumping issue, but the major distortion problem remains.

# Imports
import vapoursynth as vs
# getting Vapoursynth core
import sys
import os
core = vs.core
# Import scripts folder
scriptPath = 'C:/Program Files/Hybrid2/64bit/vsscripts'
sys.path.insert(0, os.path.abspath(scriptPath))
# loading plugins
core.std.LoadPlugin(path="C:/Program Files/Hybrid2/64bit/vsfilters/MiscFilter/MiscFilters/MiscFilters.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid2/64bit/vsfilters/SourceFilter/LSmashSource/LSMASHSource.dll")
# Import scripts
import vsdeoldify as havc
import validate
# Source: 'C:\Users\NASS\Desktop\LA\restoredcolor.mp4'
# Current color space: YUV420P8, bit depth: 8, resolution: 938x698, frame rate: 24fps, scanorder: progressive, yuv luminance scale: limited, matrix: 709, transfer: bt.709, primaries: bt.709, format: AVC
# Loading ' C:\Users\NASS\Desktop\LA\restoredcolor.mp4Ä using LWLibavSource
clip = core.lsmas.LWLibavSource(source="C:\Users\NASS\Desktop\LA\restoredcolor.mp4 ", format="YUV420P8", stream_index=0, cache=0, prefer_hw=0)
frame = clip.get_frame(0)
# setting color matrix to 709.
clip = core.std.SetFrameProps(clip, _Matrix=vs.MATRIX_BT709)
# setting color transfer (vs.TRANSFER_BT709), if it is not set.
if validate.transferIsInvalid(clip):
clip = core.std.SetFrameProps(clip=clip, _Transfer=vs.TRANSFER_BT709)
# setting color primaries info (to vs.PRIMARIES_BT709), if it is not set.
if validate.primariesIsInvalid(clip):
clip = core.std.SetFrameProps(clip=clip, _Primaries=vs.PRIMARIES_BT709)
# setting color range to TV (limited) range.
clip = core.std.SetFrameProps(clip=clip, _ColorRange=vs.RANGE_LIMITED)
# making sure frame rate is set to 24fps
clip = core.std.AssumeFPS(clip=clip, fpsnum=24, fpsden=1)
# making sure the detected scan type is set (detected: progressive)
clip = core.std.SetFrameProps(clip=clip, _FieldBased=vs.FIELD_PROGRESSIVE) # scan type: progressive
# adjusting color space from YUV420P8 to RGB24 for vsColorAdjust
clip = core.resize.Bicubic(clip=clip, format=vs.RGB24, matrix_in_s="709", range_in_s="limited", range_s="full")
# stabilize colors using ColorAdjust (HAVC)
clip = havc.HAVC_ColorAdjust(clip, BlackWhiteTune="strong", BlackWhiteMode=6, Strength=1)
# adjusting output color from RGB24 to YUV420P8 for x264Model
clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P8, matrix_s="709", range_in_s="full", range_s="limited") # additional resize to match target color sampling
# set output frame rate to 24fps (progressive)
clip = core.std.AssumeFPS(clip=clip, fpsnum=24, fpsden=1)
# output
clip.set_output()
# script was created by Hybrid 2026.03.21.1

Here are a few photos of the result with the distortion problem

https://drive.google.com/drive/folders/1...KwSv1D5ifD


Best

NASS
Reply
(Yesterday, 15:16)Dan64 Wrote: Hi NASS,

  Can you provide a small sample and the script used.

Dan


Hi! Can you provide a step-by-step workflow for using DITserver-based colorization? Also, can DITserver colorize new characters that appear in the same shot without altering the colors of the already colorized areas?
Reply
Hi Dan, thanks so much—with RC3, the colors are stable! Thanks.
Reply
Hi Selur,

  I attached the new RC4, it fix a bug introduced in RC3.
  This should be the last RC before the official release.

Dan


Attached Files
.zip   vsdeoldify-5.8.5_RC4.zip (Size: 641,38 KB / Downloads: 3)
Reply
Will test later and report back.
Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Reply
I performed a test by colorizing a full film (960x720, fps: 23.976) on my RTX5070 Ti.

I obtained the following results:

encoded 125236 frames in 22145.44s (5.66 fps), 2572.90 kb/s, Avg QP:24.47
finished after 06:12:32.007

 Using my previous pipeline:

1) Extraction of 3062 reference images (about 1 ref. every 41 frames): 7 min.
2) Colorization DiT:  (3062*4)/60 = 204 min.
3) Encoding with CMNET2 at a speed of 12.8 fps: (125236/12.8)/60 = 163 min.

Total Time: 374 min. (5.58 fps)

So with direct encoding, the colorization speed improves by about 1.5% (mainly due to the skipped frame extraction phase and filesystem image access).

The only problem is that in this way is not possible to see the colorized frames and eventually remove the ones with inconsistent colors.

CMNET2 is already doing a good job in keeping the color consistency, but to obtain a perfect results it is necessary to manually analyze the colored reference frames and eventually remove the ones with inconsistent colors. But in my opinion the film colorized with the direct encoding is already very good, much, much better than using HAVC (DeOldify + DDColor).

Dan
Reply
What I did with the latest version
cd F:\Hybrid\64bit\Vapoursynth
git clone https://github.com/dan64/DiTServerRPC.git DiTServerRPC-main
cd DiTServerRPC-main
..\python -m pip install virtualenv
..\python -m virtualenv .venv
.venv\Scripts\activate
pip install torch==2.9.1+cu128 torchvision==0.24.1+cu128 torchaudio==2.9.1+cu128 --index-url https://download.pytorch.org/whl/cu128
pip install https://github.com/nunchaku-ai/nunchaku/releases/download/v1.2.1/nunchaku-1.2.1+cu12.8torch2.9-cp312-cp312-win_amd64.whl
pip show nunchaku
python patch_nunchaku.py
python patch_nunchaku.py --check
pip install packages\diffusers-0.37.0.dev0-py3-none-any.whl
python -c "import diffusers; print(diffusers.__version__)"
pip install transformers==4.57.6 accelerate==1.12.0 huggingface_hub>=0.26.0 Pillow>=10.0.0
python dit_rpc_server.py --load-pipeline --pipeline-config qwen_config_int4.json
then I used:
clip = havc.HAVC_cmnet2dit(clip, encode_mode=1, dit_engine_params={"host": "127.0.0.1", "port": 8765, "model_precision": "int4"})
in Hybrid, but that crashed while using:
"F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vapoursynth\vspipe.exe" "J:\tmp\2026-05-24@18_25_46_1110\encodingTempSynthSkript_2026-05-24@18_25_46_1110_0.vpy" - --outputindex 0 -c y4m |"F:\Hybrid\64bit\NVEncC.exe" --y4m -i - --fps 25.000 --codec av1 --sar 1:1 --lookahead 32 --output-depth 10 --vbr 0 --vbr-quality 23.00 --aq --aq-strength 5 --aq-temporal --gop-len 0 --ref 6 --multiref-l0 3 --multiref-l1 3 --bframes 3 --direct auto --bref-mode auto --no-b-adapt --mv-precision Q-pel --preset quality --colorrange limited --colormatrix smpte170m --colorrange limited --cuda-schedule sync --output "J:\tmp\2026-05-24@18_25_46_1110\test_1_2026-05-24@18_25_46_1110_02.av1"
Server showed:
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.86s/it]
2026-05-24 18:26:35,387 [INFO] colorize_frame_pair_shm: 10.26s (5.13s/frame)
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.69s/it]
2026-05-24 18:26:48,751 [INFO] colorize_frame_pair_shm: 9.41s (4.70s/frame)
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.69s/it]
2026-05-24 18:26:56,753 [INFO] colorize_frame_pair_shm: 7.83s (3.91s/frame)
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.69s/it]
2026-05-24 18:27:04,797 [INFO] colorize_frame_pair_shm: 7.87s (3.93s/frame)
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.76s/it]
2026-05-24 18:27:12,892 [INFO] colorize_frame_pair_shm: 7.92s (3.96s/frame)
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.69s/it]
2026-05-24 18:27:20,794 [INFO] colorize_frame_pair_shm: 7.74s (3.87s/frame)
----------------------------------------
----------------------------------------
Exception occurred during processing of request from ('127.0.0.1', 10668)
Exception occurred during processing of request from ('127.0.0.1', 10669)
Traceback (most recent call last):
Traceback (most recent call last):
  File "socketserver.py", line 697, in process_request_thread
  File "socketserver.py", line 697, in process_request_thread
  File "socketserver.py", line 362, in finish_request
  File "socketserver.py", line 766, in __init__
  File "socketserver.py", line 362, in finish_request
  File "http\server.py", line 438, in handle
  File "socketserver.py", line 766, in __init__
  File "http\server.py", line 404, in handle_one_request
  File "http\server.py", line 438, in handle
  File "socket.py", line 720, in readinto
  File "http\server.py", line 404, in handle_one_request
  File "socket.py", line 720, in readinto
ConnectionResetError: [WinError 10054] Eine vorhandene Verbindung wurde vom Remotehost geschlossen

So I tried it manually with the above call and got:
C:\Users\Selur>"F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vapoursynth\vspipe.exe" "J:\tmp\2026-05-24@18_25_46_1110\encodingTempSynthSkript_2026-05-24@18_25_46_1110_0.vpy" - --outputindex 0 -c y4m |"F:\Hybrid\64bit\NVEncC.exe" --y4m -i - --fps 25.000 --codec av1 --sar 1:1 --lookahead 32 --output-depth 10 --vbr 0 --vbr-quality 23.00 --aq --aq-strength 5 --aq-temporal --gop-len 0 --ref 6 --multiref-l0 3 --multiref-l1 3 --bframes 3 --direct auto --bref-mode auto --no-b-adapt --mv-precision Q-pel --preset quality --colorrange limited --colormatrix smpte170m --colorrange limited --cuda-schedule sync --output "J:\tmp\2026-05-24@18_25_46_1110\test_1_2026-05-24@18_25_46_1110_02.av1"
--------------------------------------------------------------------------------
J:\tmp\2026-05-24@18_25_46_1110\test_1_2026-05-24@18_25_46_1110_02.av1
--------------------------------------------------------------------------------
Warning: Plugin F:\Hybrid\64bit\vsfilters\ColorFilter\Retinex\Retinex.dll is using API3 which is deprecated and will be removed shortly.
Warning: Plugin F:\Hybrid\64bit\vsfilters\Support\akarin.dll is using API3 which is deprecated and will be removed shortly.
Error: Failed to retrieve frame 0 with error:
Traceback (most recent call last):
  File "vapoursynth.pyx", line 3353, in vapoursynth.publicFunction
  File "vapoursynth.pyx", line 3355, in vapoursynth.publicFunction
  File "vapoursynth.pyx", line 818, in vapoursynth.FuncData.__call__
TypeError: _colormnet2dit_async.<locals>.colormnet_dit_color() got an unexpected keyword argument 'reader'

Output 32 frames in 0.09 seconds (338.41 fps)
NVEncC (x64) 9.16 (r3587) by rigaya, May  1 2026 01:35:16 (VC 1944/Win)
OS Version     Windows 11 x64 (26200) [UTF-8]
CPU            AMD Ryzen 9 7950X 16-Core Processor [5.51GHz] (16C/32T)
GPU            #0: NVIDIA GeForce RTX 4080 (9728 cores, 2505 MHz)[PCIe4x16][596.36]
NVENC / CUDA   NVENC API 13.0, CUDA 13.2, schedule mode: sync
Input Buffers  CUDA, 44 frames
Input Info     y4m(yv12(10bit))->p010 [AVX2], 640x352, 25/1 fps
Vpp Filters    copyDtoD
Output Info    AV1 main 10bit @ Level auto
               640x352p 1:1 25.000fps (25/1fps)
Encoder Preset quality
Rate Control   VBR
Multipass      none
Bitrate        0 kbps (Max: 2000 kbps)
Target Quality 23.00
QP range       I:0-255  P:0-255  B:0-255
QP Offset      cb:0  cr:0
VBV buf size   auto
Split Enc Mode auto
Tuning Info    hq
Lookahead      on, 32 frames, Adaptive I Insert
GOP length     250 frames
B frames       3 frames [ref mode: middle]
Ref frames     6 frames, MultiRef L0:auto L1:auto
AQ             on (spatial, temporal, strength 5)
Part size      max auto / min auto
Tile num       columns auto / rows auto
TemporalLayers max 1
Refs           forward auto, backward auto
VUI            matrix:smpte170m,range:limited
Others         mv:Q-pel

encoded 0 frames, 0.00 fps, 0.00 kbps, 0.00 MB
encode time 0:00:00, CPULoad: 1.9%
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Reply
The memory requirements for running local version of CMNET2 are very high, try to pass max_memory_frames=2.
I left the local version mainly to debug the code, the current limitation regarding the memory do not make it useful for an effective coloring.

you should not get problems using encode_mode=0

Dan

P.S.
[WinError 10054] means that the client broken the connection probably crashed
Reply
Ah, I missed that I use dencode_mode=1.
Okay, the server python instance already eats ~22GB RAM. (got 64, no real problem)
using
clip = havc.HAVC_cmnet2dit(clip, dit_engine_params={"host": "127.0.0.1", "port": 8765, "model_precision": "int4"})
Preview in vsViewer works fine.
But encoding is stuck:
100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.98s/it]
2026-05-24 19:09:06,304 [INFO] colorize_frame_pair_shm: 10.65s (5.33s/frame)
restarted the job and it seems to be stuck again,... gpu jumps to 50% at the beginning and then nothing happens.
Stopped the job, restarted the server
(.venv) F:\Hybrid\64bit\Vapoursynth\DiTServerRPC-main>python dit_rpc_server.py --load-pipeline --pipeline-config qwen_config_int4.json
2026-05-24 19:39:48,815 [INFO] module_dir             : F:\Hybrid\64bit\Vapoursynth\DiTServerRPC-main
2026-05-24 19:39:48,815 [INFO] dit_colorize_main.py   : found
2026-05-24 19:39:48,815 [INFO] Loading pipeline from config: qwen_config_int4.json
2026-05-24 19:39:48,815 [INFO] Loading pipeline: nunchaku-qwen int4 r32 steps=4
Loading SVDQuant INT4 transformer from: nunchaku-ai/nunchaku-qwen-image-edit-2509/lightning-251115/svdq-int4_r32-qwen-image-edit-2509-lightning-4steps-251115.safetensors
The config attributes {'pooled_projection_dim': 768} were passed to NunchakuQwenImageTransformer2DModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 44.73it/s]
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:01<00:00,  5.52it/s]
Optimizing VRAM ...
F:\Hybrid\64bit\Vapoursynth\DiTServerRPC-main\.venv\Lib\site-packages\nunchaku\models\transformers\transformer_qwenimage.py:620: UserWarning: Skipping moving the model to GPU as offload is enabled
  warn("Skipping moving the model to GPU as offload is enabled", UserWarning)
2026-05-24 19:40:48,634 [INFO] Pipeline loaded successfully.
2026-05-24 19:40:48,635 [INFO] HAVC Colorize RPC Server listening on 127.0.0.1:8765
2026-05-24 19:40:48,635 [INFO] Press Ctrl+C to stop.
Restarted the job, cpu usage jumps to 74% cpu remains low (3-5%), then after a while it seems to start
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.75s/it]
2026-05-24 19:41:56,819 [INFO] colorize_frame_pair_shm: 42.41s (21.21s/frame)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.96s/it]
2026-05-24 19:42:30,197 [INFO] colorize_frame_pair_shm: 10.39s (5.20s/frame)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.64s/it]
2026-05-24 19:42:38,191 [INFO] colorize_frame_pair_shm: 7.81s (3.91s/frame)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.67s/it]
2026-05-24 19:42:46,226 [INFO] colorize_frame_pair_shm: 7.85s (3.93s/frame)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.68s/it]
2026-05-24 19:42:54,308 [INFO] colorize_frame_pair_shm: 7.90s (3.95s/frame)
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:03<00:00,  1.68s/it]
2026-05-24 19:43:02,450 [INFO] colorize_frame_pair_shm: 7.96s (3.98s/frame)
and then fails, like before reporting that the connection was closed by remote,...
tried it again (server restart, job restart)
This time it worked.
Restarted the job and it worked again.
But at the end of the encoding I always get:
Exception occurred during processing of request from ('127.0.0.1', 5402)
Exception occurred during processing of request from ('127.0.0.1', 5403)
Traceback (most recent call last):
Traceback (most recent call last):
  File "socketserver.py", line 697, in process_request_thread
  File "socketserver.py", line 362, in finish_request
  File "socketserver.py", line 697, in process_request_thread
  File "socketserver.py", line 362, in finish_request
  File "socketserver.py", line 766, in __init__
  File "socketserver.py", line 766, in __init__
  File "http\server.py", line 438, in handle
  File "http\server.py", line 438, in handle
  File "http\server.py", line 404, in handle_one_request
  File "socket.py", line 720, in readinto
  File "http\server.py", line 404, in handle_one_request
ConnectionResetError: [WinError 10054] Eine vorhandene Verbindung wurde vom Remotehost geschlossen
  File "socket.py", line 720, in readinto
----------------------------------------
ConnectionResetError: [WinError 10054] Eine vorhandene Verbindung wurde vom Remotehost geschlossen
This should be captured, since otherwise folks might think this is a crash.

Hmm,.. I added AutoWhite after the coloring and now the encoding stopped after half of the frames,... (the ref frame coloring seemed to be finished,...)
=> restarted the server and the job, this time it looks like the client didn't connect to the server, restarting the job, still nothing happens. gpu: 0%)
# colorize using CMNet with external DiT (HAVC)
clip = havc.HAVC_cmnet2dit(clip, dit_engine_params={"host": "127.0.0.1", "port": 8765, "model_precision": "int4"})
# adjusting color space from YUV420P8 to RGB24 for vsAutoWhite
clip = core.resize.Bicubic(clip=clip, format=vs.RGB24, matrix_in_s="470bg", range_in_s="limited", range_s="full")
# adjusting colors using AutoWhite
clip = color.AutoWhite(clip)
restarting server and then the job now the client connected, frames got created, encoding started and ran without an issue.


Cu Selur
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Reply


Forum Jump:


Users browsing this thread: 4 Guest(s)