olegchomp
Cannot deserialize with an empty memory buffer.
Hello i have this issue when trying to running the python sd_ndi :
C:\Users\User\AppData\Roaming\Python\Python310\site-packages\diffusers\utils\outputs.py:63: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree.register_pytree_node(
{'sd_model': 'darkstorm2150/Protogen_v2.2_Official_Release', 't_index_list': [25, 45], 'engine': '../engines/darkstorm2150/Protogen_v2.2_Official_Release--lcm_lora-True--tiny_vae-True--max_batch-2--min_batch-2--mode-img2img', 'min_batch_size': 1, 'max_batch_size': 2, 'ndi_name': 'DESKTOP-KKKKKKK (TouchDesigner)', 'osc_out_adress': '127.0.0.1', 'osc_out_port': 12345, 'osc_in_adress': '127.0.0.1', 'osc_in_port': 12346}
C:\Users\User\AppData\Roaming\Python\Python310\site-packages\huggingface_hub\file_download.py:1142: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True.
warnings.warn(
safety_checker\model.safetensors not found
Loading pipeline components...: 14%|███████▍ | 1/7 [00:00<00:01, 5.35it/s]C:\Users\User\AppData\Roaming\Python\Python310\site-packages\diffusers\models\modeling_utils.py:109: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
return torch.load(checkpoint_file, map_location="cpu")
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:02<00:00, 3.48it/s]
C:\Users\User\AppData\Roaming\Python\Python310\site-packages\diffusers\loaders\lora.py:952: FutureWarning: fuse_text_encoder_lora is deprecated and will be removed in version 0.25. You are using an old version of LoRA backend. This will be deprecated in the next releases in favor of PEFT make sure to install the latest PEFT and transformers packages in the future.
deprecate("fuse_text_encoder_lora", "0.25", LORA_DEPRECATION_MESSAGE)
Loading TensorRT engine: ../engines/darkstorm2150/Protogen_v2.2_Official_Release--lcm_lora-True--tiny_vae-True--max_batch-2--min_batch-2--mode-img2img/unet.engine
[I] Loading bytes from ../engines/darkstorm2150/Protogen_v2.2_Official_Release--lcm_lora-True--tiny_vae-True--max_batch-2--min_batch-2--mode-img2img/unet.engine
[E] IRuntime::deserializeCudaEngine: Error Code 3: API Usage Error (Cannot deserialize with an empty memory buffer.)
[!] Could not deserialize engine. See log for details.
Traceback (most recent call last):
File "C:\Users\User\StreamDiffusion-NDI\sd_ndi.py", line 86, in
