vitacon

Thank you for your replay. Yes, the optimization was enabled. Meanwhile I checked FPNG-test that compresses and decompresses PNGs using different libraries and the results are different too: ``` SSE...

My home CPU is AMD Ryzen 5 3600 (6 cores, 12 threads). I believe Intel would produce different ratios of measured times because I already noticed that while measuring my...

Weeell, I think I pasted by mistake a log from debug version of FPNG-test. It was just an illustration of ratios so I did not notice the absolute values are...

I took me a while to notice it is already solved by a custom node. https://github.com/Stability-AI/stability-ComfyUI-nodes And it is handled using cv2. ``` def color_blend(bw_layer,color_layer): # Convert the color layer...

Nothing too fancy. Just variations of this: `main -t 10 -l cs -m models\ggml-model-whisper-large.bin --output-srt -f temp.wav` I think it happens with smaller models too but it's just less apparent...

Some additional information: I suspected the amount of locked memory depends on the number of threads and it really does. The previous test with Medium model and 11 threads raised...

Thanks for your investigation. I used the latest build [whisper : avoid some memory allocations](https://github.com/ggerganov/whisper.cpp/actions/runs/3806607201). Last time I used a 7:30 long video, 11 threads, Medium model and the locked...

Damn, I think I previously mixed up data from two different computers so they were a bit misleading. After a few more tests on just one computer (Ryzen with 16...

> I don't have Windows machine so I cannot investigate in details. I understand that it is a big obstacle. I suppose it would be necessary to add some debug...

I'd like to improve the temporal consistency too. https://youtu.be/z6fK-kdMZNQ I guess the depth maps can be "normalized" by some post processing and the same thing applies for your request of...