The question about python examples/ctsd_generation_example.py -c examples/ctsd_21_6views_image_generation.json -o output/ctsd_21_6views_image_generation.

[WangzcBruce]

I have changed the configuration of the json file about the path of SD-2.1, as follows.(ctsd_21_6views_image_generation.json)
But it incured the errors below.
`(base) root@wzc-test1-0:/workspace/OpenDWM#

ctsd_21_6views_image_generation.json

PYTHONPATH=src python examples/ctsd_generation_example.py -c examples/ctsd_21_6views_image_generation.json -o output/ctsd_21_6views_image_generation
Traceback (most recent call last):
File "/workspace/[email protected]/OpenDWM/examples/ctsd_generation_example.py", line 42, in
pipeline = dwm.common.create_instance_from_config(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/[email protected]/OpenDWM/src/dwm/common.py", line 164, in create_instance_from_config
return create_instance(_config["_class_name"], **args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/[email protected]/OpenDWM/src/dwm/common.py", line 151, in create_instance
return class_type(**kwargs)
^^^^^^^^^^^^^^^^^^^^
File "/workspace/[email protected]/OpenDWM/src/dwm/pipelines/ctsd.py", line 899, in init
missing_keys, unexpected_keys = self.model.load_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 2584, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for UNetCrossviewTemporalConditionModel:
Unexpected key(s) in state_dict: "condition_image_adapter.body.0.in_conv.weight", "condition_image_adapter.body.0.in_conv.bias", "condition_image_adapter.body.0.resnets.0.block1.weight", "condition_image_adapter.body.0.resnets.0.block1.bias", "condition_image_adapter.body.0.resnets.0.block2.weight", "condition_image_adapter.body.0.resnets.0.block2.bias", "condition_image_adapter.body.0.resnets.1.block1.weight", "condition_image_adapter.body.0.resnets.1.block1.bias", "condition_image_adapter.body.0.resnets.1.block2.weight", "condition_image_adapter.body.0.resnets.1.block2.bias", "condition_image_adapter.body.1.resnets.0.block1.weight", "condition_image_adapter.body.1.resnets.0.block1.bias", "condition_image_adapter.body.1.resnets.0.block2.weight", "condition_image_adapter.body.1.resnets.0.block2.bias", "condition_image_adapter.body.1.resnets.1.block1.weight", "condition_image_adapter.body.1.resnets.1.block1.bias", "condition_image_adapter.body.1.resnets.1.block2.weight", "condition_image_adapter.body.1.resnets.1.block2.bias", "condition_image_adapter.body.2.in_conv.weight", "condition_image_adapter.body.2.in_conv.bias", "condition_image_adapter.body.2.resnets.0.block1.weight", "condition_image_adapter.body.2.resnets.0.block1.bias", "condition_image_adapter.body.2.resnets.0.block2.weight", "condition_image_adapter.body.2.resnets.0.block2.bias", "condition_image_adapter.body.2.resnets.1.block1.weight", "condition_image_adapter.body.2.resnets.1.block1.bias", "condition_image_adapter.body.2.resnets.1.block2.weight", "condition_image_adapter.body.2.resnets.1.block2.bias", "condition_image_adapter.body.3.in_conv.weight", "condition_image_adapter.body.3.in_conv.bias", "condition_image_adapter.body.3.resnets.0.block1.weight", "condition_image_adapter.body.3.resnets.0.block1.bias", "condition_image_adapter.body.3.resnets.0.block2.weight", "condition_image_adapter.body.3.resnets.0.block2.bias", "condition_image_adapter.body.3.resnets.1.block1.weight", "condition_image_adapter.body.3.resnets.1.block1.bias", "condition_image_adapter.body.3.resnets.1.block2.weight", "condition_image_adapter.body.3.resnets.1.block2.bias", "condition_image_adapter.body.4.resnets.0.block1.weight", "condition_image_adapter.body.4.resnets.0.block1.bias", "condition_image_adapter.body.4.resnets.0.block2.weight", "condition_image_adapter.body.4.resnets.0.block2.bias", "condition_image_adapter.body.4.resnets.1.block1.weight", "condition_image_adapter.body.4.resnets.1.block1.bias", "condition_image_adapter.body.4.resnets.1.block2.weight", "condition_image_adapter.body.4.resnets.1.block2.bias", "condition_image_adapter.zero_convs.0.weight", "condition_image_adapter.zero_convs.0.bias", "condition_image_adapter.zero_convs.1.weight", "condition_image_adapter.zero_convs.1.bias", "condition_image_adapter.zero_convs.2.weight", "condition_image_adapter.zero_convs.2.bias", "condition_image_adapter.zero_convs.3.weight", "condition_image_adapter.zero_convs.3.bias", "condition_image_adapter.zero_convs.4.weight", "condition_image_adapter.zero_convs.4.bias".
`

[wzhgba]

It seems that you tried the config of model without layout control but loaded a checkpoint with layout control, please check the download link.