Error

[dillfrescott]

Traceback (most recent call last):
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
    exec(code, module.__dict__)
  File "/workspace/generative-models/scripts/demo/sampling.py", line 304, in <module>
    state2 = init_st(version_dict2, load_filter=False)
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 212, in wrapper
    return cached_func(*args, **kwargs)
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 241, in __call__
    return self._get_or_create_cached_value(args, kwargs)
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 267, in _get_or_create_cached_value
    return self._handle_cache_miss(cache, value_key, func_args, func_kwargs)
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 321, in _handle_cache_miss
    computed_value = self._info.func(*func_args, **func_kwargs)
  File "/workspace/generative-models/scripts/demo/streamlit_helpers.py", line 46, in init_st
    model, msg = load_model_from_config(config, ckpt if load_ckpt else None)
  File "/workspace/generative-models/scripts/demo/streamlit_helpers.py", line 86, in load_model_from_config
    model = instantiate_from_config(config.model)
  File "/workspace/generative-models/sgm/util.py", line 175, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "/workspace/generative-models/sgm/models/diffusion.py", line 48, in __init__
    model = instantiate_from_config(network_config)
  File "/workspace/generative-models/sgm/util.py", line 175, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "/workspace/generative-models/sgm/modules/diffusionmodules/openaimodel.py", line 665, in __init__
    SpatialTransformer(
  File "/workspace/generative-models/sgm/modules/attention.py", line 678, in __init__
    [
  File "/workspace/generative-models/sgm/modules/attention.py", line 679, in <listcomp>
    BasicTransformerBlock(
  File "/workspace/generative-models/sgm/modules/attention.py", line 512, in __init__
    self.attn2 = attn_cls(
  File "/workspace/generative-models/sgm/modules/attention.py", line 365, in __init__
    self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
  File "/workspace/generative-models/.pt2/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 96, in __init__
    self.weight = Parameter(torch.empty((out_features, in_features), **factory_kwargs))
TypeError: empty(): argument 'size' must be tuple of ints, but found element of type ListConfig at pos 2

[jangofett890]

I also get this error. No idea why, was difficult enough to even get it to attempt to do something because the versions of torch installed via requirements dont even install with cuda.

[perryrighthere]

Get the same error too. Stuck here for a while :(

[tekntrash]

same

[gllhjy]

same

[chenbinghui1]

The followings help me solve this problem: [1] In sd_xl_refiner.yaml, replace the following code: [2] In streamlit_helpers, add the following code:

[youngwoo-dev]

You only need to fix sgd/modules/attention.py file.

1. Add the following line to the top of the sgd/modules/attention.py file:

from omegaconf import ListConfig

2. Insert this line in the middle of the sgd/modules/attention.py file, around line 655:

if exists(context_dim) and isinstance(context_dim, ListConfig):
    context_dim = list(context_dim)

[shoaib42]

sgd/modules/attention.py

Shouldn't this be in sgm/modules/attention.py