Error, Script evaluation failed

[Odjur]

Tried #54 with no success. Looks like there may have been an update since then, or I'm running into a slightly different version of the problem.

Notably upscaling does work on some videos, but not others, despite both playing back correctly. I'm not sure what the difference is.

Generating TensorRT engine with command: python\VSPipe.exe -c y4m --arg "slot=1" --arg "video_path=E:\Videos\test.mkv" --start 0 --end 1 "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy" -p .
run_animejanai slot 1 chain_1
chain_conf {'min_px': 0.0, 'max_px': inf, 'min_resolution': '0x0', 'max_resolution': '0x0', 'min_fps': 0.0, 'max_fps': inf, 'models': [{'resize_factor_before_upscale': 100.0, 'resize_height_before_upscale': 0.0, 'name': '2xLiveActionV1_SPAN_490000'}], 'rife': False, 'rife_factor_numerator': 2, 'rife_factor_denominator': 1, 'rife_model': 422, 'rife_ensemble': False, 'rife_scene_detect_threshold': 0.15, 'final_resize_height': 0.0, 'final_resize_factor': 100.0, 'tensorrt_engine_settings': ''}
upscale2x: scaling 2x from 720x1280 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is not compatible with this version of TensorRT, expecting library version 10.8.0.43 got 
.	.)
upscale2x: scaling 2x from 720x1280 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is not compatible with this version of TensorRT, expecting library version 10.8.0.43 got 
.	.)
Script evaluation failed:
Python exception: operator (): engine deserialization failed
Traceback (most recent call last):
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 209, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 268, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 171, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): engine deserialization failed
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "src\\cython\\vapoursynth.pyx", line 3387, in vapoursynth._vpy_evaluate
  File "src\\cython\\vapoursynth.pyx", line 3388, in vapoursynth._vpy_evaluate
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy", line 20, in <module>
    animejanai_core.run_animejanai_with_keybinding(clip, clip.fps, slot)
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 301, in run_animejanai_with_keybinding
    run_animejanai(clip, container_fps, chain_conf, config['global']['backend'])
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 219, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 268, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 171, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): engine deserialization failed
Upscaling with command: python\VSPipe.exe -c y4m --arg "slot=1" --arg "video_path=E:\Videos\test.mkv" "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy" - | "C:\Users\Odjur\AppData\Roaming\VideoJaNai\ffmpeg\ffmpeg.exe" -y -i pipe: -i "E:\Videos\test.mkv" -map 0:v -c:v hevc_nvenc -preset p7 -profile:v main10 -b:v 50M -max_interleave_delta 0 -max_interleave_delta 0 -map 1:t? -map 1:a?  -map 1:s? -c:t copy -c:a copy -c:s copy "E:\Output\test.mkv"
ffmpeg version 2026-01-19-git-43dbc011fa-essentials_build-www.gyan.dev Copyright (c) 2000-2026 the FFmpeg developers
  built with gcc 15.2.0 (Rev8, Built by MSYS2 project)
  configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-cairo --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-zlib --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-sdl2 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxvid --enable-libaom --enable-libopenjpeg --enable-libvpx --enable-mediafoundation --enable-libass --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-openal --enable-libgme --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libtheora --enable-libvo-amrwbenc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-librubberband
  libavutil      60. 23.100 / 60. 23.100
  libavcodec     62. 23.102 / 62. 23.102
  libavformat    62.  8.102 / 62.  8.102
  libavdevice    62.  2.100 / 62.  2.100
  libavfilter    11. 11.101 / 11. 11.101
  libswscale      9.  3.100 /  9.  3.100
  libswresample   6.  2.100 /  6.  2.100
run_animejanai slot 1 chain_1
chain_conf {'min_px': 0.0, 'max_px': inf, 'min_resolution': '0x0', 'max_resolution': '0x0', 'min_fps': 0.0, 'max_fps': inf, 'models': [{'resize_factor_before_upscale': 100.0, 'resize_height_before_upscale': 0.0, 'name': '2xLiveActionV1_SPAN_490000'}], 'rife': False, 'rife_factor_numerator': 2, 'rife_factor_denominator': 1, 'rife_model': 422, 'rife_ensemble': False, 'rife_scene_detect_threshold': 0.15, 'final_resize_height': 0.0, 'final_resize_factor': 100.0, 'tensorrt_engine_settings': ''}
upscale2x: scaling 2x from 720x1280 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is not compatible with this version of TensorRT, expecting library version 10.8.0.43 got 
.	.)
upscale2x: scaling 2x from 720x1280 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
IRuntime::deserializeCudaEngine: Error Code 6: API Usage Error (The engine plan file is not compatible with this version of TensorRT, expecting library version 10.8.0.43 got 
.	.)
Script evaluation failed:
Python exception: operator (): engine deserialization failed
Traceback (most recent call last):
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 209, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 268, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 171, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): engine deserialization failed
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "src\\cython\\vapoursynth.pyx", line 3387, in vapoursynth._vpy_evaluate
  File "src\\cython\\vapoursynth.pyx", line 3388, in vapoursynth._vpy_evaluate
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy", line 20, in <module>
    animejanai_core.run_animejanai_with_keybinding(clip, clip.fps, slot)
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 301, in run_animejanai_with_keybinding
    run_animejanai(clip, container_fps, chain_conf, config['global']['backend'])
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 219, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 268, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 171, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): engine deserialization failed
[in#0 @ 000001fb44257400] Error opening input: Invalid data found when processing input
Error opening input file pipe:.
Error opening input files: Invalid data found when processing input

[nwoltman]

It might be because of using an engine that was built with a previous driver or a different version of TensorRT. Try going to C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx and deleting any file that ends in .engine and try upscaling again. The main file to delete would look something like: 2xLiveActionV1_SPAN_490000.3678297938.engine

[the-database]

@nwoltman solution should work but I'd also consider this a bug as the software should handle this scenario for you.

[Odjur]

Unfortunately it did not work. Also tested with one of the default upscalers and had the same result. Here is the full output after the first time running it again if that is helpful:

Generating TensorRT engine with command: python\VSPipe.exe -c y4m --arg "slot=1" --arg "video_path=E:\Output\test.mkv" --start 0 --end 1 "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy" -p .
run_animejanai slot 1 chain_1
chain_conf {'min_px': 0.0, 'max_px': inf, 'min_resolution': '0x0', 'max_resolution': '0x0', 'min_fps': 0.0, 'max_fps': inf, 'models': [{'resize_factor_before_upscale': 100.0, 'resize_height_before_upscale': 0.0, 'name': '2xLiveActionV1_SPAN_490000'}], 'rife': False, 'rife_factor_numerator': 2, 'rife_factor_denominator': 1, 'rife_model': 422, 'rife_ensemble': False, 'rife_scene_detect_threshold': 0.15, 'final_resize_height': 0.0, 'final_resize_factor': 100.0, 'tensorrt_engine_settings': ''}
upscale2x: scaling 2x from 1080x1920 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
C:\Users\Odjur\AppData\Roaming\VideoJaNai\python/vs-plugins/vsmlrt-cuda\trtexec --onnx=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.onnx --saveEngine=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.1853643832.engine --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
&&&& RUNNING TensorRT.trtexec [TensorRT v100800] [b43] # C:\Users\Odjur\AppData\Roaming\VideoJaNai\python/vs-plugins/vsmlrt-cuda\trtexec --onnx=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.onnx --saveEngine=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.1853643832.engine --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
[01/27/2026-02:22:09] [I] === Model Options ===
[01/27/2026-02:22:09] [I] Format: ONNX
[01/27/2026-02:22:09] [I] Model: C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.onnx
[01/27/2026-02:22:09] [I] Output:
[01/27/2026-02:22:09] [I] === Build Options ===
[01/27/2026-02:22:09] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default, tacticSharedMem: default
[01/27/2026-02:22:09] [I] avgTiming: 8
[01/27/2026-02:22:09] [I] Precision: FP32+BF16
[01/27/2026-02:22:09] [I] LayerPrecisions: 
[01/27/2026-02:22:09] [I] Layer Device Types: 
[01/27/2026-02:22:09] [I] Calibration: 
[01/27/2026-02:22:09] [I] Refit: Disabled
[01/27/2026-02:22:09] [I] Strip weights: Disabled
[01/27/2026-02:22:09] [I] Version Compatible: Disabled
[01/27/2026-02:22:09] [I] ONNX Plugin InstanceNorm: Disabled
[01/27/2026-02:22:09] [I] TensorRT runtime: full
[01/27/2026-02:22:09] [I] Lean DLL Path: 
[01/27/2026-02:22:09] [I] Tempfile Controls: { in_memory: allow, temporary: allow }
[01/27/2026-02:22:09] [I] Exclude Lean Runtime: Disabled
[01/27/2026-02:22:09] [I] Sparsity: Disabled
[01/27/2026-02:22:09] [I] Safe mode: Disabled
[01/27/2026-02:22:09] [I] Build DLA standalone loadable: Disabled
[01/27/2026-02:22:09] [I] Allow GPU fallback for DLA: Disabled
[01/27/2026-02:22:09] [I] DirectIO mode: Disabled
[01/27/2026-02:22:09] [I] Restricted mode: Disabled
[01/27/2026-02:22:09] [I] Skip inference: Enabled
[01/27/2026-02:22:09] [I] Save engine: C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.1853643832.engine
[01/27/2026-02:22:09] [I] Load engine: 
[01/27/2026-02:22:09] [I] Profiling verbosity: 0
[01/27/2026-02:22:09] [I] Tactic sources: cublas [OFF], cublasLt [OFF], cudnn [ON], 
[01/27/2026-02:22:09] [I] timingCacheMode: local
[01/27/2026-02:22:09] [I] timingCacheFile: 
[01/27/2026-02:22:09] [I] Enable Compilation Cache: Enabled
[01/27/2026-02:22:09] [I] Enable Monitor Memory: Disabled
[01/27/2026-02:22:09] [I] errorOnTimingCacheMiss: Disabled
[01/27/2026-02:22:09] [I] Preview Features: Use default preview flags.
[01/27/2026-02:22:09] [I] MaxAuxStreams: -1
[01/27/2026-02:22:09] [I] BuilderOptimizationLevel: -1
[01/27/2026-02:22:09] [I] MaxTactics: -1
[01/27/2026-02:22:09] [I] Calibration Profile Index: 0
[01/27/2026-02:22:09] [I] Weight Streaming: Disabled
[01/27/2026-02:22:09] [I] Runtime Platform: Same As Build
[01/27/2026-02:22:09] [I] Debug Tensors: 
[01/27/2026-02:22:09] [I] Input(s): fp32:chw
[01/27/2026-02:22:09] [I] Output(s): fp32:chw
[01/27/2026-02:22:09] [I] Input build shape (profile 0): input=1x3x8x8+1x3x1080x1920+1x3x1080x1920
[01/27/2026-02:22:09] [I] Input calibration shapes: model
[01/27/2026-02:22:09] [I] === System Options ===
[01/27/2026-02:22:09] [I] Device: 0
[01/27/2026-02:22:09] [I] DLACore: 
[01/27/2026-02:22:09] [I] Plugins:
[01/27/2026-02:22:09] [I] setPluginsToSerialize:
[01/27/2026-02:22:09] [I] dynamicPlugins:
[01/27/2026-02:22:09] [I] ignoreParsedPluginLibs: 0
[01/27/2026-02:22:09] [I] 
[01/27/2026-02:22:09] [I] === Inference Options ===
[01/27/2026-02:22:09] [I] Batch: Explicit
[01/27/2026-02:22:09] [I] Input inference shape : input=1x3x1080x1920
[01/27/2026-02:22:09] [I] Iterations: 10
[01/27/2026-02:22:09] [I] Duration: 3s (+ 200ms warm up)
[01/27/2026-02:22:09] [I] Sleep time: 0ms
[01/27/2026-02:22:09] [I] Idle time: 0ms
[01/27/2026-02:22:09] [I] Inference Streams: 1
[01/27/2026-02:22:09] [I] ExposeDMA: Disabled
[01/27/2026-02:22:09] [I] Data transfers: Enabled
[01/27/2026-02:22:09] [I] Spin-wait: Disabled
[01/27/2026-02:22:09] [I] Multithreading: Disabled
[01/27/2026-02:22:09] [I] CUDA Graph: Disabled
[01/27/2026-02:22:09] [I] Separate profiling: Disabled
[01/27/2026-02:22:09] [I] Time Deserialize: Disabled
[01/27/2026-02:22:09] [I] Time Refit: Disabled
[01/27/2026-02:22:09] [I] NVTX verbosity: 0
[01/27/2026-02:22:09] [I] Persistent Cache Ratio: 0
[01/27/2026-02:22:09] [I] Optimization Profile Index: 0
[01/27/2026-02:22:09] [I] Weight Streaming Budget: 100.000000%
[01/27/2026-02:22:09] [I] Inputs:
[01/27/2026-02:22:09] [I] Debug Tensor Save Destinations:
[01/27/2026-02:22:09] [I] === Reporting Options ===
[01/27/2026-02:22:09] [I] Verbose: Disabled
[01/27/2026-02:22:09] [I] Averages: 10 inferences
[01/27/2026-02:22:09] [I] Percentiles: 90,95,99
[01/27/2026-02:22:09] [I] Dump refittable layers:Disabled
[01/27/2026-02:22:09] [I] Dump output: Disabled
[01/27/2026-02:22:09] [I] Profile: Disabled
[01/27/2026-02:22:09] [I] Export timing to JSON file: 
[01/27/2026-02:22:09] [I] Export output to JSON file: 
[01/27/2026-02:22:09] [I] Export profile to JSON file: 
[01/27/2026-02:22:09] [I] 
[01/27/2026-02:22:09] [I] === Device Information ===
[01/27/2026-02:22:09] [I] Available Devices: 
[01/27/2026-02:22:09] [I]   Device 0: "NVIDIA GeForce RTX 4080 SUPER" UUID: GPU-b9cd3fa8-80b9-f8cc-b622-b6094a4e06e6
[01/27/2026-02:22:09] [I] Selected Device: NVIDIA GeForce RTX 4080 SUPER
[01/27/2026-02:22:09] [I] Selected Device ID: 0
[01/27/2026-02:22:09] [I] Selected Device UUID: GPU-b9cd3fa8-80b9-f8cc-b622-b6094a4e06e6
[01/27/2026-02:22:09] [I] Compute Capability: 8.9
[01/27/2026-02:22:09] [I] SMs: 80
[01/27/2026-02:22:09] [I] Device Global Memory: 16375 MiB
[01/27/2026-02:22:09] [I] Shared Memory per SM: 100 KiB
[01/27/2026-02:22:09] [I] Memory Bus Width: 256 bits (ECC disabled)
[01/27/2026-02:22:09] [I] Application Compute Clock Rate: 2.55 GHz
[01/27/2026-02:22:09] [I] Application Memory Clock Rate: 11.501 GHz
[01/27/2026-02:22:09] [I] 
[01/27/2026-02:22:09] [I] Note: The application clock rates do not reflect the actual clock rates that the GPU is currently running at.
[01/27/2026-02:22:09] [I] 
[01/27/2026-02:22:09] [I] TensorRT version: 10.8.0
[01/27/2026-02:22:09] [I] Loading standard plugins
[01/27/2026-02:22:09] [I] [TRT] [MemUsageChange] Init CUDA: CPU +1, GPU +0, now: CPU 33434, GPU 1344 (MiB)
[01/27/2026-02:22:28] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +4222, GPU +446, now: CPU 37987, GPU 1790 (MiB)
[01/27/2026-02:22:28] [I] Start parsing network model.
[01/27/2026-02:22:28] [I] [TRT] ----------------------------------------------------------------
[01/27/2026-02:22:28] [I] [TRT] Input filename:   C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.onnx
[01/27/2026-02:22:28] [I] [TRT] ONNX IR version:  0.0.7
[01/27/2026-02:22:28] [I] [TRT] Opset version:    14
[01/27/2026-02:22:28] [I] [TRT] Producer name:    pytorch
[01/27/2026-02:22:28] [I] [TRT] Producer version: 2.1.2
[01/27/2026-02:22:28] [I] [TRT] Domain:           
[01/27/2026-02:22:28] [I] [TRT] Model version:    0
[01/27/2026-02:22:28] [I] [TRT] Doc string:       
[01/27/2026-02:22:28] [I] [TRT] ----------------------------------------------------------------
[01/27/2026-02:22:28] [I] Finished parsing network model. Parse time: 0.0236351
[01/27/2026-02:22:28] [I] Set shape of input tensor input for optimization profile 0 to: MIN=1x3x8x8 OPT=1x3x1080x1920 MAX=1x3x1080x1920
[01/27/2026-02:22:28] [I] [TRT] Local timing cache in use. Profiling results in this builder pass will not be stored.
[01/27/2026-02:23:49] [I] [TRT] Detected 1 inputs and 1 output network tensors.
[01/27/2026-02:23:50] [I] [TRT] Total Host Persistent Memory: 130832 bytes
[01/27/2026-02:23:50] [I] [TRT] Total Device Persistent Memory: 0 bytes
[01/27/2026-02:23:50] [I] [TRT] Max Scratch Memory: 0 bytes
[01/27/2026-02:23:50] [I] [TRT] [BlockAssignment] Started assigning block shifts. This will take 46 steps to complete.
[01/27/2026-02:23:50] [I] [TRT] [BlockAssignment] Algorithm ShiftNTopDown took 0.2698ms to assign 7 blocks to 46 nodes requiring 3185050624 bytes.
[01/27/2026-02:23:50] [I] [TRT] Total Activation Memory: 3185049600 bytes
[01/27/2026-02:23:50] [I] [TRT] Total Weights Memory: 1652784 bytes
[01/27/2026-02:23:50] [I] [TRT] Engine generation completed in 81.3906 seconds.
[01/27/2026-02:23:50] [I] [TRT] [MemUsageStats] Peak memory usage of TRT CPU/GPU memory allocators: CPU 0 MiB, GPU 9124 MiB
[01/27/2026-02:23:50] [I] Engine built in 81.4159 sec.
[01/27/2026-02:23:50] [I] Created engine with size: 2.04259 MiB
[01/27/2026-02:23:50] [I] [TRT] Loaded engine size: 2 MiB
[01/27/2026-02:23:50] [I] Engine deserialized in 0.0085827 sec.
[01/27/2026-02:23:50] [I] Skipped inference phase since --skipInference is added.
&&&& PASSED TensorRT.trtexec [TensorRT v100800] [b43] # C:\Users\Odjur\AppData\Roaming\VideoJaNai\python/vs-plugins/vsmlrt-cuda\trtexec --onnx=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.onnx --saveEngine=C:\Users\Odjur\AppData\Roaming\VideoJaNai\onnx\2xLiveActionV1_SPAN_490000.1853643832.engine --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
upscale2x: scaling 2x from 1080x1920 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
Script evaluation failed:
Python exception: operator (): no valid optimization profile found
Traceback (most recent call last):
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 203, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 256, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 165, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): no valid optimization profile found
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "src\\cython\\vapoursynth.pyx", line 3387, in vapoursynth._vpy_evaluate
  File "src\\cython\\vapoursynth.pyx", line 3388, in vapoursynth._vpy_evaluate
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy", line 20, in <module>
    animejanai_core.run_animejanai_with_keybinding(clip, clip.fps, slot)
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 289, in run_animejanai_with_keybinding
    run_animejanai(clip, container_fps, chain_conf, config['global']['backend'])
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 213, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 256, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 165, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): no valid optimization profile found
Upscaling with command: python\VSPipe.exe -c y4m --arg "slot=1" --arg "video_path=E:\Output\test.mkv" "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy" - | "C:\Users\Odjur\AppData\Roaming\VideoJaNai\ffmpeg\ffmpeg.exe" -y -i pipe: -i "E:\Output\test.mkv" -map 0:v -c:v hevc_nvenc -preset p7 -profile:v main10 -b:v 50M -max_interleave_delta 0 -max_interleave_delta 0 -map 1:t? -map 1:a?  -map 1:s? -c:t copy -c:a copy -c:s copy "E:\Output\Upscaled Videos\test-animejanai.mkv"
ffmpeg version 2026-01-19-git-43dbc011fa-essentials_build-www.gyan.dev Copyright (c) 2000-2026 the FFmpeg developers
  built with gcc 15.2.0 (Rev8, Built by MSYS2 project)
  configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-cairo --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-zlib --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-sdl2 --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxvid --enable-libaom --enable-libopenjpeg --enable-libvpx --enable-mediafoundation --enable-libass --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-openal --enable-libgme --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libtheora --enable-libvo-amrwbenc --enable-libgsm --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-librubberband
  libavutil      60. 23.100 / 60. 23.100
  libavcodec     62. 23.102 / 62. 23.102
  libavformat    62.  8.102 / 62.  8.102
  libavdevice    62.  2.100 / 62.  2.100
  libavfilter    11. 11.101 / 11. 11.101
  libswscale      9.  3.100 /  9.  3.100
  libswresample   6.  2.100 /  6.  2.100
run_animejanai slot 1 chain_1
chain_conf {'min_px': 0.0, 'max_px': inf, 'min_resolution': '0x0', 'max_resolution': '0x0', 'min_fps': 0.0, 'max_fps': inf, 'models': [{'resize_factor_before_upscale': 100.0, 'resize_height_before_upscale': 0.0, 'name': '2xLiveActionV1_SPAN_490000'}], 'rife': False, 'rife_factor_numerator': 2, 'rife_factor_denominator': 1, 'rife_model': 422, 'rife_ensemble': False, 'rife_scene_detect_threshold': 0.15, 'final_resize_height': 0.0, 'final_resize_factor': 100.0, 'tensorrt_engine_settings': ''}
upscale2x: scaling 2x from 1080x1920 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
upscale2x: scaling 2x from 1080x1920 with engine=2xLiveActionV1_SPAN_490000; num_streams=4
trt_settings --bf16 --minShapes=input:1x3x8x8 --optShapes=input:1x3x1080x1920 --maxShapes=input:1x3x1080x1920 --inputIOFormats=fp32:chw --outputIOFormats=fp32:chw --tacticSources=+CUDNN,-CUBLAS,-CUBLAS_LT --skipInference
Script evaluation failed:
Python exception: operator (): no valid optimization profile found
Traceback (most recent call last):
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 203, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 256, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 165, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): no valid optimization profile found
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "src\\cython\\vapoursynth.pyx", line 3387, in vapoursynth._vpy_evaluate
  File "src\\cython\\vapoursynth.pyx", line 3388, in vapoursynth._vpy_evaluate
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_encode.vpy", line 20, in <module>
    animejanai_core.run_animejanai_with_keybinding(clip, clip.fps, slot)
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 289, in run_animejanai_with_keybinding
    run_animejanai(clip, container_fps, chain_conf, config['global']['backend'])
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 213, in run_animejanai
    clip = run_animejanai_upscale(clip, backend, model_conf, trt_settings, num_streams)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 256, in run_animejanai_upscale
    return upscale2x(clip, backend, model_conf['name'], num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 153, in upscale2x
    return upscale2x_trt(clip, engine_name, num_streams, trt_settings)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "E:\Programs\VideoJaNai\current\backend\animejanai\core\animejanai_core.py", line 165, in upscale2x_trt
    return core.trt.Model(
           ^^^^^^^^^^^^^^^
  File "src\\cython\\vapoursynth.pyx", line 3123, in vapoursynth.Function.__call__
vapoursynth.Error: operator (): no valid optimization profile found
[in#0 @ 000001c05aa07300] Error opening input: Invalid data found when processing input
Error opening input file pipe:.
Error opening input files: Invalid data found when processing input

[bnewsond]

This log shows two separate TRT issues:

1. Initially: engine plan incompatibility (“expecting TensorRT 10.8.0.43…”) which usually means a stale *.engine built under a different TRT/runtime/driver. Deleting only one engine may not be enough.

2. After trtexec rebuild: “operator (): no valid optimization profile found” which points to the runtime input shape not matching any profile in the generated engine (or the app loading a different engine than the one just built).

Suggested cleanup:

• Close VideoJaNai
• Delete ALL *.engine in %AppData%\Roaming\VideoJaNai\onnx\ (and any timing cache files if present)
• Also delete any plugin/cache dirs under %AppData%\Roaming\VideoJaNai\python\vs-plugins\ (if they cache TRT)
• Relaunch and let it rebuild

As a potential mitigation: rebuild the engine with a larger maxShapes (e.g., 1x3x2160x3840) and set optShapes to the clip’s actual processed resolution, in case the internal clip handed to TRT differs from the container resolution.