Error occurred when executing PipelineLoader: Allocation on device

[Be-coder]

What is the problem? Is there not enough memory? Do you currently have a suitable solution? Please, thank you！！！

[TemryL]

Hi, thanks for your report, can you show the full trace?

[Be-coder]

Here! And weight_dtype: float16. thank you very much.

[TemryL]

Most likely OOM exception as https://github.com/TemryL/ComfyUI-IDM-VTON/issues/4. Can you specify your GPU config?

[Be-coder]

it is RTX 4060，VRAM:8G，RAM:16GB. The memory usage during runtime has reached its highest level, while the graphics memory usage is not high. Can my configuration run your code?

[AfterHAL]

Hi. Same error for me. Running on RX4080 16GB Vram (2GB used by system)

GPU VRAM is filled up in 10 seconds.

[Pythonpa]

+1 GPU 3090 24G VRAM。Below is the error info

Error occurred when executing IDM-VTON:

Allocation on device

File "C:\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\idm_vton.py", line 100, in make_inference images = pipeline( File "C:\ComfyUI\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "C:\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\tryon_pipeline.py", line 1630, in call mask, masked_image_latents = self.prepare_mask_latents( File "C:\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\tryon_pipeline.py", line 961, in prepare_mask_latents masked_image_latents = self._encode_vae_image(masked_image, generator=generator) File "C:\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\tryon_pipeline.py", line 921, in _encode_vae_image image_latents = retrieve_latents(self.vae.encode(image), generator=generator) File "C:\ComfyUI\python\lib\site-packages\diffusers\utils\accelerate_utils.py", line 46, in wrapper return method(self, *args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\diffusers\models\autoencoders\autoencoder_kl.py", line 260, in encode h = self.encoder(x) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\diffusers\models\autoencoders\vae.py", line 172, in forward sample = down_block(sample) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\diffusers\models\unets\unet_2d_blocks.py", line 1465, in forward hidden_states = resnet(hidden_states, temb=None) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\diffusers\models\resnet.py", line 332, in forward hidden_states = self.norm1(hidden_states) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\python\lib\site-packages\torch\nn\modules\normalization.py", line 287, in forward return F.group_norm( File "C:\ComfyUI\python\lib\site-packages\torch\nn\functional.py", line 2588, in group_norm return torch.group_norm(input, num_groups, weight, bias, eps, torch.backends.cudnn.enabled)

[ZombieNeighbor]

Hello,

Same error here The Pipeline Loader is very slow and fail after 2-5mn then fail in Out Of Memory error

---

!!! Exception during processing!!! Allocation on device Traceback (most recent call last): File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py", line 68, in load_pipeline ).requires_grad_(False).eval().to(DEVICE) ^^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1173, in to return self._apply(convert) ^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) [Previous line repeated 5 more times] File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 804, in _apply param_applied = fn(param) ^^^^^^^^^ File "E:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1159, in convert return t.to( ^^^^^ torch.cuda.OutOfMemoryError: Allocation on device