low gpu-util about rerender_a_video HOT 10 CLOSED

I suppose that's the ebsynth part (not fully GPU-based, mostly CPU-based). Ebsynth is not implemented by us. If you are interested, you can improve the Ebsynth part to make a high gpu-util.

Our diffusion part does not have low gpu-util.

from rerender_a_video.

I am sorry. But (60~80 second / frame) infers to the ddim phase speed.

from rerender_a_video.

But in my case, on V100 32G, the speed is much faster than your case. (512x512 videos, take about 14.23s per frame)
Did you use very large video resolution?

from rerender_a_video.

I also fixed the 512 x 512 resolution. And varm cost about 10g.
In my case, we spend about 200s to load the model and inference per frame cost 60s. I first though it work in the CPU, but i check it work in CUDA:4 (I set it through torch.set.cuda).
And it is difficulty to set gpu id in weiui.py. CUDA_VISIA... and os cmd are not working. It only work when i set it in front of the per process_x.

from rerender_a_video.

I remember that I can set the GPU by CUDA_VISIBLE_DEVICES=0 python webUI.py.
The slow speed might also caused by WebUI? You can try to use rerender.py instead to test the speed.
If rerender.py is also slow, then I think there may be something wrong with your hardware or software.

from rerender_a_video.

rerender.py also performs bad. I test another rep (fresco)

from rerender_a_video.

https://github.com/williamyang1991/Rerender_A_Video/blob/main/inference_playground.ipynb
You can see the recorded speed in my inference_playground.ipynb

from rerender_a_video.

thanks for your patient resp

from rerender_a_video.

this image shows the speed

from rerender_a_video.

I cannot help you with it. I think it is not the problem of my code.
Your hardware or software or setting or environment may have some problem that slow down the code.

from rerender_a_video.