stable-diffusion-webui-depthmap-script icon indicating copy to clipboard operation
stable-diffusion-webui-depthmap-script copied to clipboard

ArrayMemoryError

Open rvsoldier opened this issue 2 years ago • 2 comments

Hello! I've tried a bunch of different models/settings/videos with Single Video depth mapping but I keep running into this issue. Is it just that I don't have enough vram for anything bigger than about 20mb?

File "G:\IA\stable-diffusion-webui\extensions\stable-diffusion-webui-depthmap-script\src\common_ui.py", line 451, in run_generate ret = video_mode.gen_video( File "G:\IA\stable-diffusion-webui\extensions\stable-diffusion-webui-depthmap-script\src\video_mode.py", line 135, in gen_video input_depths = process_predicitons(input_depths, smoothening) File "G:\IA\stable-diffusion-webui\extensions\stable-diffusion-webui-depthmap-script\src\video_mode.py", line 111, in process_predicitons a, b = np.percentile(np.stack(processed), [0.5, 99.5]) File "<array_function internals>", line 180, in percentile File "G:\IA\stable-diffusion-webui\venv\lib\site-packages\numpy\lib\function_base.py", line 4166, in percentile return _quantile_unchecked( File "G:\IA\stable-diffusion-webui\venv\lib\site-packages\numpy\lib\function_base.py", line 4424, in _quantile_unchecked r, k = _ureduce(a, File "G:\IA\stable-diffusion-webui\venv\lib\site-packages\numpy\lib\function_base.py", line 3725, in _ureduce r = func(a, **kwargs) File "G:\IA\stable-diffusion-webui\venv\lib\site-packages\numpy\lib\function_base.py", line 4590, in _quantile_ureduce_func arr = a.flatten() numpy.core._exceptions._ArrayMemoryError: Unable to allocate 8.08 GiB for an array with shape (4337838720,) and data type float16

Time taken: 8 min. 26.2 sec.

rvsoldier avatar Sep 13 '23 09:09 rvsoldier

Thank you for reporting! Please try a smaller video, running in standalone mode and closing all other programs (to free RAM). I am busy right now, sadly no proper fix will be done in foreseeable future (it would have required some time)...

semjonsona avatar Sep 13 '23 09:09 semjonsona

That was a RAM issue probably

semjonsona avatar Sep 13 '23 09:09 semjonsona