api_server issue

[nogardvfx]

Running the api_server on a Windows 11 machine. The apir_server loads fine. Was trying to do a text to image process and I noticed the "self.pipeline_t2i" part of the code is commented out. I uncommented it and reran the server and now it crashes with the following message. Tried to find out what to do, but I am not having much luck. Image to model works fine. Haven't tried generating a texture yet. Maybe I have overlooked something.

This is the line in the code that I uncommented:

    self.pipeline_t2i = HunyuanDiTPipeline(
        'Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers-Distilled',
        device=device

This is the error message:

2025-05-25 10:06:10 | INFO | hy3dgen.shapgen | Loading model from C:\Users\nogar.cache\huggingface\hub\models--tencent--Hunyuan3D-2mini\snapshots\d3318f050d91fe232038820bbbabeab95c0de14e\hunyuan3d-vae-v2-mini-turbo\model.fp16.safetensors
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]
Loading pipeline components...: 29%|██████████████▊ | 2/7 [00:02<00:05, 1.00s/it]
Loading pipeline components...: 43%|██████████████████████▎ | 3/7 [00:02<00:02, 1.58it/s]
Loading pipeline components...: 43%|██████████████████████▎ | 3/7 [00:02<00:02, 1.41it/s]
2025-05-25 10:06:17 | ERROR | stderr |
2025-05-25 10:06:17 | ERROR | stderr | Traceback (most recent call last):
2025-05-25 10:06:17 | ERROR | stderr | File "E:\Maya_Hunyuan\Hunyuan3D-2\api_server.py", line 324, in
2025-05-25 10:06:17 | ERROR | stderr | worker = ModelWorker(model_path=args.model_path, device=args.device, enable_tex=args.enable_tex,
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "E:\Maya_Hunyuan\Hunyuan3D-2\api_server.py", line 176, in init
2025-05-25 10:06:17 | ERROR | stderr | self.pipeline_t2i = HunyuanDiTPipeline(
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "E:\Maya_Hunyuan\Hunyuan3D-2\hy3dgen\text2image.py", line 37, in init
2025-05-25 10:06:17 | ERROR | stderr | self.pipe = AutoPipelineForText2Image.from_pretrained(
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
2025-05-25 10:06:17 | ERROR | stderr | return fn(*args, **kwargs)
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\pipelines\auto_pipeline.py", line 443, in from_pretrained
2025-05-25 10:06:17 | ERROR | stderr | return text_2_image_cls.from_pretrained(pretrained_model_or_path, **kwargs)
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
2025-05-25 10:06:17 | ERROR | stderr | return fn(*args, **kwargs)
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 961, in from_pretrained
2025-05-25 10:06:17 | ERROR | stderr | loaded_sub_model = load_sub_model(
2025-05-25 10:06:17 | ERROR | stderr | ^^^^^^^^^^^^^^^
2025-05-25 10:06:17 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 709, in load_sub_model
2025-05-25 10:06:17 | ERROR | stderr | raise ValueError(
2025-05-25 10:06:17 | ERROR | stderr | ValueError: The component <class 'transformers.models.t5.tokenization_t5._LazyModule.getattr..Placeholder'> of <class 'diffusers.pipelines.pag.pipeline_pag_hunyuandit.HunyuanDiTPAGPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_pretrained', 'from_pretrained'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained'], 'ProcessorMixin': ['save_pretrained', 'from_pretrained'], 'ImageProcessingMixin': ['save_pretrained', 'from_pretrained'], 'ORTModule': ['save_pretrained', 'from_pretrained']}.

Thank you in advance.

[nogardvfx]

Also whenever I try to generate a texture from an image, I get this:

2025-05-25 12:49:14 | INFO | stdout | Caught Unknown Error 'ModelWorker' object has no attribute 'pipeline_tex'
2025-05-25 12:49:14 | ERROR | stderr | Traceback (most recent call last):
2025-05-25 12:49:14 | ERROR | stderr | File "E:\Maya_Hunyuan\Hunyuan3D-2\api_server.py", line 260, in generate
2025-05-25 12:49:14 | ERROR | stderr | file_path, uid = worker.generate(uid, params)
2025-05-25 12:49:14 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2025-05-25 12:49:14 | ERROR | stderr | File "C:\Users\nogar\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
2025-05-25 12:49:14 | ERROR | stderr | return func(*args, **kwargs)
2025-05-25 12:49:14 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^
2025-05-25 12:49:14 | ERROR | stderr | File "E:\Maya_Hunyuan\Hunyuan3D-2\api_server.py", line 229, in generate
2025-05-25 12:49:14 | ERROR | stderr | mesh = self.pipeline_tex(mesh, image)
2025-05-25 12:49:14 | ERROR | stderr | ^^^^^^^^^^^^^^^^^
2025-05-25 12:49:14 | ERROR | stderr | AttributeError: 'ModelWorker' object has no attribute 'pipeline_tex'
2025-05-25 12:49:14 | INFO | stdout | INFO: 127.0.0.1:63466 - "POST /generate HTTP/1.1" 404 Not Found