camenduru / videocomposer-colab Goto Github PK

What do I do.

Hi, I'm running this in google colab with A100 GPU, getting the following issue.

[2023-09-19 00:30:12,741] INFO: GPU Memory used 12.70 GB
Traceback (most recent call last):
File "/content/videocomposer/run_net.py", line 36, in
main()
File "/content/videocomposer/run_net.py", line 31, in main
inference_single(cfg.cfg_dict)
File "/content/videocomposer/tools/videocomposer/inference_single.py", line 351, in inference_single
worker(0, cfg)
File "/content/videocomposer/tools/videocomposer/inference_single.py", line 695, in worker
video_output = diffusion.ddim_sample_loop(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/videocomposer/artist/ops/diffusion.py", line 236, in ddim_sample_loop
xt, _ = self.ddim_sample(xt, t, model, model_kwargs, clamp, percentile, condition_fn, guide_scale, ddim_timesteps, eta)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/content/videocomposer/artist/ops/diffusion.py", line 200, in ddim_sample
_, _, _, x0 = self.p_mean_variance(xt, t, model, model_kwargs, clamp, percentile, guide_scale)
File "/content/videocomposer/artist/ops/diffusion.py", line 166, in p_mean_variance
var = _i(self.posterior_variance, t, xt)
File "/content/videocomposer/artist/ops/diffusion.py", line 13, in _i
return tensor[t].view(shape).to(x)
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

I suspect its an error in t he run_net.py (probably some tensors not on gpu), but still pose here in case anyone came across it before.