RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

[8600862]

there is a error when i click 'run video editing' button in the gradio_demo, and i just choose a example at the end of the page. how to fix it?

Using seed: 65485
Loading pipeline components...:   0%|                                                                                                                                                            | 0/7 [00:00<?, ?it/s]The config attributes {'attention_head_dim': 64} were passed to I2VGenXLUNet, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading pipeline components...: 100%|####################################################################################################################################################| 7/7 [00:00<00:00,  7.82it/s]
  1%|#7                                                                                                                                                                              | 1/100.0 [00:01<01:42,  1.03s/it]
Traceback (most recent call last):
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/gradio/routes.py", line 516, in predict
    output = await route_utils.call_process_api(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/gradio/route_utils.py", line 219, in call_process_api
    output = await app.get_blocks().process_api(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/gradio/blocks.py", line 1437, in process_api
    result = await self.call_function(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/gradio/blocks.py", line 1109, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/gradio/utils.py", line 650, in wrapper
    response = f(*args, **kwargs)
  File "/server/stablediffusion/text2video/AnyV2V/gradio_demo.py", line 303, in btn_infer_fn
    result_video_path = AnyV2V_Editor.perform_anyv2v(video_path=video_path,
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/server/stablediffusion/text2video/AnyV2V/gradio_demo.py", line 142, in perform_anyv2v
    _ddim_latents = ddim_inversion(
  File "/server/stablediffusion/text2video/AnyV2V/i2vgen-xl/run_group_ddim_inversion.py", line 37, in ddim_inversion
    ddim_latents = pipe.invert(
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/server/stablediffusion/text2video/AnyV2V/i2vgen-xl/pipelines/pipeline_i2vgen_xl.py", line 1418, in invert
    latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
  File "/server/anaconda3/envs/anyv2v/lib/python3.10/site-packages/diffusers/schedulers/scheduling_ddim_inverse.py", line 337, in step
    alpha_prod_t = self.alphas_cumprod[timestep] if timestep >= 0 else self.initial_alpha_cumprod
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

[vinesmsuic]

Hi, can you provide more information about your hardware and software environment?

[8600862]

Hi, can you provide more information about your hardware and software environment?

3090 python3.10-torch2.1.0, I can run it using run_group_ddim_inversion.py and run_group_pnp_edit.py as redme

[vinesmsuic]

This is weird, me and my collaborators was able to run all the scripts with the provided requirement.txt. Let's see if there are other people ran into same issue