stable-diffusion-webui-depthmap-script Depth map crashing some time after pressing generate

After some time after pressing Generate button I have error:

Saving faces: 100%|███████████████| 5232425/5232425 [00:17<00:00, 307174.04it/s] 0%| | 0/1 [10:34<?, ?it/s] All done. Error completing request Arguments: (0, <PIL.Image.Image image mode=RGB size=512x768 at 0x7F9B024AD5A0>, None, '', '', 0, 2, 512, 512, False, True, False, False, 0, 1, True, 1, True, True, False, False, ['left-right', 'red-cyan-anaglyph'], 2.5, 'polylines_sharp', 0, True, True, False, False, False, 'u2net', False, 0, 2, False, None, True, False, True, False) {} Traceback (most recent call last): File "/workspace/sd/stable-diffusion-webui/modules/call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "/workspace/sd/stable-diffusion-webui/modules/call_queue.py", line 37, in f res = func(*args, **kwargs) File "/workspace/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-depthmap-script/scripts/depthmap.py", line 1184, in run_generate outputs, mesh_fi, meshsimple_fi = run_depthmap( File "/workspace/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-depthmap-script/scripts/depthmap.py", line 779, in run_depthmap mesh_fi = run_3dphoto(device, inpaint_imgs, inpaint_depths, inputnames, outpath, fnExt, vid_ssaa, inpaint_vids) File "/workspace/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-depthmap-script/scripts/depthmap.py", line 944, in run_3dphoto run_3dphoto_videos(mesh_fi, basename, outpath, 300, 40, File "/workspace/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-depthmap-script/scripts/depthmap.py", line 972, in run_3dphoto_videos vispy.use(app='egl') File "/usr/local/lib/python3.10/dist-packages/vispy/util/wrappers.py", line 93, in use use_app(app) File "/usr/local/lib/python3.10/dist-packages/vispy/app/_default_app.py", line 47, in use_app default_app = Application(backend_name) File "/usr/local/lib/python3.10/dist-packages/vispy/app/application.py", line 47, in init self._use(backend_name) File "/usr/local/lib/python3.10/dist-packages/vispy/app/application.py", line 240, in _use raise RuntimeError(msg) RuntimeError: Could not import backend "EGL": Could not initialize

Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/gradio/routes.py", line 408, in run_predict output = await app.get_blocks().process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1318, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1221, in postprocess_data self.validate_outputs(fn_index, predictions) # type: ignore File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1196, in validate_outputs raise ValueError( ValueError: An event handler (f) didn't receive enough output values (needed: 5, received: 3). Wanted outputs: [gallery, textbox, model3d, html, html] Received outputs: [None, "", "

RuntimeError: Could not import backend "EGL": Could not initialize

Time taken: 11m 59.28s

Torch active/reserved: 12381/12588 MiB, Sys VRAM: 13749/16118 MiB (85.3%)

"]

Generate 3D inpainted mesh. (Sloooow, required for generating videos) is on dpt_beit_large_384 (midas 3.1) GPU

on 1 x RTX A4000 8 vCPU 31 GB RAM