no working #362

Describe the bug

img to mesh

Steps to reproduce

img to mesh

Modly version

0.4.2

Operating system

win11

Screenshots & logs

Error: Traceback (most recent call last):
File "X:\3dModel\Modly\resources\api\routers\generation.py", line 199, in _run_generation
gen = await loop.run_in_executor(None, generator_registry.get_active)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\3dModel\Modly\resources\python-embed\Lib\concurrent\futures\thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\3dModel\Modly\resources\api\services\generator_registry.py", line 711, in get_active
gen.load()
File "X:\3dModel\Modly\resources\api\services\extension_process.py", line 274, in load
raise RuntimeError(msg.get("traceback") or msg.get("message"))
RuntimeError: Traceback (most recent call last):
File "X:\3dModel\Modly\resources\api\runner.py", line 159, in main
gen.load()
File "X:\3dModel\Modly\extensions\hunyuan3d-mini-fast\generator.py", line 59, in load
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\3dModel\Modly\models\hunyuan3d-mini-fast\generate_hy3dgen\hy3dgen\shapegen\pipelines.py", line 225, in from_pretrained
return cls.from_single_file(
^^^^^^^^^^^^^^^^^^^^^
File "X:\3dModel\Modly\models\hunyuan3d-mini-fast\generate_hy3dgen\hy3dgen\shapegen\utils.py", line 83, in wrapper
result = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "X:\3dModel\Modly\models\hunyuan3d-mini-fast\generate_hy3dgen\hy3dgen\shapegen\pipelines.py", line 181, in from_single_file
conditioner.load_state_dict(ckpt['conditioner'])
File "X:\3dModel\Modly\extensions\hunyuan3d-mini-fast\venv\Lib\site-packages\torch\nn\modules\module.py", line 2581, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for SingleImageEncoder:
Missing key(s) in state_dict: "main_image_encoder.model.encoder.layer.0.attention.q_proj.weight", "main_image_encoder.model.encoder.layer.0.attention.q_proj.bias", "main_image_encoder.model.encoder.layer.0.attention.k_proj.weight", "main_image_encoder.model.encoder.layer.0.attention.k_proj.bias",

Confirmation

• I have searched existing issues and this has not been reported yet.
• I can reproduce this on the latest version of Modly.