如题，这个工作流是否能将图片中的单个物体提取出来，并另存为图片供下一个节点使用？

报了以下的错

Error occurred when executing ESAM_ModelLoader_Zho:

The provided filename /ssd2/ws/ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM/efficient_sam_s_gpu.jit does not exist

File "/ssd2/ws/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/ssd2/ws/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 "/ssd2/ws/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/ssd2/ws/ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM/YOLO_WORLD_EfficientSAM.py", line 98, in load_esam_model
EFFICIENT_SAM_MODEL = torch.jit.load(model_path)
File "/home/nc/miniconda3/envs/comfyui/lib/python3.10/site-packages/torch/jit/_serialization.py", line 152, in load
raise ValueError("The provided filename {} does not exist".format(f)) # type: ignore[str-bytes-safe]

How to solve the following problem when loading：

The provided filename D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\efficient_sam_s_gpu.jit does not exist

Error occurred when executing Yoloworld_ESAM_Zho:

'WorldModel' object has no attribute 'clip_model'

File "E:\new_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:\new_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:\new_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:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 139, in yoloworld_esam_image
YOLO_WORLD_MODEL.set_classes(categories)
File "E:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\inference\models\yolo_world\yolo_world.py", line 133, in set_classes
self.model.set_classes(text)
File "E:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\models\yolo\model.py", line 96, in set_classes
self.model.set_classes(classes)
File "E:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\nn\tasks.py", line 575, in set_classes
if not self.clip_model:
^^^^^^^^^^^^^^^
File "E:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1695, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

Judging by the issues in this repo, the Yoloworld ESAM node should probably allow loading of yolo models from disk rather than via roboflow. There's really no reason to use a third party service when the relevant models are freely available on hugginface.co.

Should probably also add a warning on the readme to stop peeps from installing both onnxruntime and onnxruntime-gpu (which somehow isn't blocked while installing inference).

我下载了导入还是1.0版本的

I encountered a compatibility issue when trying to install onnxruntime-gpu on a macOS 14.3 environment using an M2 chip with

• Python 3.9.18
• Python 3.10.13

The installation fails due to the unavailability of a suitable onnxruntime-gpu version for this setup.

pip install -r requirements.txt

ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu<=1.15.1 (from inference-gpu) (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu<=1.15.1

onnxruntime-gpu should be the CUDA version which makes sense that it doesn't work on mac but shouldn't it still work with CPU only version?

Could we consider integrating an alternative like onnxruntime-silicon for better compatibility with macOS M2 chip environments?

How to do inference?

I just want to do inference on an image with both segmentation and detection by giving needed classes. There is no inference code in the repo. Can anyone provide it or give me hints to write it myself?

File "D:\Data\Packages\ComfyUI\nodes.py", line 1887, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM_init.py", line 1, in
from .YOLO_WORLD_EfficientSAM import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "D:\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 6, in
import supervision as sv
ModuleNotFoundError: No module named 'supervision'

Cannot import D:\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM module for custom nodes: No module named 'supervision'

看管理器的提示是和新版本的comfyui不兼容？能不能辛苦作者更新下节点去兼容COMFYUI新的版本呢？
When installing or updating this custom node, many installation packages may be downgraded due to the installation of requirements.
在安装或更新此自定义节点时，许多安装包可能会因安装要求而降级。

!! python3.12 is incompatible.
!! python3.12不兼容。

Traceback (most recent call last):
File "H:\ComfyUI-qiuye\ComfyUI\nodes.py", line 1888, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "H:\ComfyUI-qiuye\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM_init.py", line 1, in
from . import YOLO_WORLD_EfficientSAM
File "H:\ComfyUI-qiuye\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 6, in
import supervision as sv
ModuleNotFoundError: No module named 'supervision'

Cannot import H:\ComfyUI-qiuye\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM module for custom nodes: No module named 'supervision'

小白如何解决这个问题，求回答

This is awesome. Thank you.

Roboflow Inference was updated to version 0.9.16. This breaks the mask detection in the node.

It cannot detect say "person".

But when trying to detect "person, car" it works.

Downgrading to inference 0.9.15 works.

Can you please check so the node works with the latest version of inference?

According to #4, I manually pip install inference and succeded to import this custom node suite. However, when I runt the workflow, the node fails to auto-download yolo_world models and return this error:

File "/ComfyUI/execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM/YOLO_WORLD_EfficientSAM.py", line 70, in load_yolo_world_model
YOLO_WORLD_MODEL = YOLOWorld(model_id=yolo_world_model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/inference/models/yolo_world/yolo_world.py", line 36, in init
self.model = YOLO(self.cache_file("yolo-world.pt"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/ultralytics/engine/model.py", line 94, in init
self._load(model, task)
File "/ComfyUI/venv/lib/python3.11/site-packages/ultralytics/engine/model.py", line 146, in _load
self.model, self.ckpt = attempt_load_one_weight(weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/ultralytics/nn/tasks.py", line 628, in attempt_load_one_weight
ckpt, weight = torch_safe_load(weight) # load ckpt
^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/ultralytics/nn/tasks.py", line 567, in torch_safe_load
return torch.load(file, map_location='cpu'), file # load
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/torch/serialization.py", line 1025, in load
return _load(opened_zipfile,
^^^^^^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/torch/serialization.py", line 1437, in _load
result = unpickler.load()
^^^^^^^^^^^^^^^^
File "/ComfyUI/venv/lib/python3.11/site-packages/torch/serialization.py", line 1430, in find_class
return super().find_class(mod_name, name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: Can't get attribute 'WorldModel' on <module 'ultralytics.nn.tasks' from '/ComfyUI/venv/lib/python3.11/site-packages/ultralytics/nn/tasks.py'>

Also, how do yolo_world/l, yolo_world/m, yolo_world/m map to the model files in this directory?

If there's a chance to download and use the extra-large model, I'd love to do that.

Our devs are getting conflicts integrating your node pack because it requires onnxruntime-gpu to be so old.

This is a request to update that.

I got this error message when running your workflow. I installed everything correctly as described in your instruction.

Error occurred when executing Yoloworld_ESAM_Zho:

Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [CPU, QuantizedCPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher].

CPU: registered at C:\actions-runner_work\vision\vision\pytorch\vision\torchvision\csrc\ops\cpu\nms_kernel.cpp:112 [kernel]
QuantizedCPU: registered at C:\actions-runner_work\vision\vision\pytorch\vision\torchvision\csrc\ops\quantized\cpu\qnms_kernel.cpp:124 [kernel]
BackendSelect: fallthrough registered at ..\aten\src\ATen\core\BackendSelectFallbackKernel.cpp:3 [backend fallback]
Python: registered at ..\aten\src\ATen\core\PythonFallbackKernel.cpp:153 [backend fallback]
FuncTorchDynamicLayerBackMode: registered at ..\aten\src\ATen\functorch\DynamicLayer.cpp:498 [backend fallback]
Functionalize: registered at ..\aten\src\ATen\FunctionalizeFallbackKernel.cpp:290 [backend fallback]
Named: registered at ..\aten\src\ATen\core\NamedRegistrations.cpp:7 [backend fallback]
Conjugate: registered at ..\aten\src\ATen\ConjugateFallback.cpp:17 [backend fallback]
Negative: registered at ..\aten\src\ATen\native\NegateFallback.cpp:19 [backend fallback]
ZeroTensor: registered at ..\aten\src\ATen\ZeroTensorFallback.cpp:86 [backend fallback]
ADInplaceOrView: fallthrough registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:86 [backend fallback]
AutogradOther: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:53 [backend fallback]
AutogradCPU: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:57 [backend fallback]
AutogradCUDA: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:65 [backend fallback]
AutogradXLA: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:69 [backend fallback]
AutogradMPS: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:77 [backend fallback]
AutogradXPU: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:61 [backend fallback]
AutogradHPU: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:90 [backend fallback]
AutogradLazy: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:73 [backend fallback]
AutogradMeta: registered at ..\aten\src\ATen\core\VariableFallbackKernel.cpp:81 [backend fallback]
Tracer: registered at ..\torch\csrc\autograd\TraceTypeManual.cpp:296 [backend fallback]
AutocastCPU: fallthrough registered at ..\aten\src\ATen\autocast_mode.cpp:382 [backend fallback]
AutocastCUDA: fallthrough registered at ..\aten\src\ATen\autocast_mode.cpp:249 [backend fallback]
FuncTorchBatched: registered at ..\aten\src\ATen\functorch\LegacyBatchingRegistrations.cpp:710 [backend fallback]
FuncTorchVmapMode: fallthrough registered at ..\aten\src\ATen\functorch\VmapModeRegistrations.cpp:28 [backend fallback]
Batched: registered at ..\aten\src\ATen\LegacyBatchingRegistrations.cpp:1075 [backend fallback]
VmapMode: fallthrough registered at ..\aten\src\ATen\VmapModeRegistrations.cpp:33 [backend fallback]
FuncTorchGradWrapper: registered at ..\aten\src\ATen\functorch\TensorWrapper.cpp:203 [backend fallback]
PythonTLSSnapshot: registered at ..\aten\src\ATen\core\PythonFallbackKernel.cpp:161 [backend fallback]
FuncTorchDynamicLayerFrontMode: registered at ..\aten\src\ATen\functorch\DynamicLayer.cpp:494 [backend fallback]
PreDispatch: registered at ..\aten\src\ATen\core\PythonFallbackKernel.cpp:165 [backend fallback]
PythonDispatcher: registered at ..\aten\src\ATen\core\PythonFallbackKernel.cpp:157 [backend fallback]

File "K:\ComfyUI\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 140, in yoloworld_esam_image
results = YOLO_WORLD_MODEL.infer(img, confidence=confidence_threshold)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\inference\models\yolo_world\yolo_world.py", line 88, in infer
results = self.model.predict(
^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\ultralytics\engine\model.py", line 429, in predict
return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\ultralytics\engine\predictor.py", line 204, in call
return list(self.stream_inference(source, model, *args, **kwargs)) # merge list of Result into one
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context
response = gen.send(None)
^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\ultralytics\engine\predictor.py", line 290, in stream_inference
self.results = self.postprocess(preds, im, im0s)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\ultralytics\models\yolo\detect\predict.py", line 25, in postprocess
preds = ops.non_max_suppression(
^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\ultralytics\utils\ops.py", line 282, in non_max_suppression
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\torchvision\ops\boxes.py", line 41, in nms
return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\ComfyUI\ComfyUI\venv\Lib\site-packages\torch_ops.py", line 692, in call
return self._op(*args, **kwargs or {})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

There is a facial crop and paste function in WAS node suit, which can extract the facial area, redraw it and paste it back to the original image. But it only works on faces, and it doesn't work in many cases, such as this picture of a toy.

It would be very practical if the powerful recognition ability of ComfyUI-YoloWorld-EfficientSAM could be used to create a general crop and paste function.

Thanks a lot.

大佬，安装后各种报错用不了啊

When the mask is empty, the workflow generates the following error:

Error occurred when executing MaskToImage:

cannot reshape tensor of 0 elements into shape [-1, 1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous
in mask_to_image
result = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)

3 种官方模型无法自动下载，怎么手动安装？
错误提示：inference.core.exceptions.RoboflowAPIConnectionError: Could not connect to Roboflow API.

!!! Exception during processing !!!
Traceback (most recent call last):
File "C:\Users\moloc\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\moloc\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:\Users\moloc\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Users\moloc\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 141, in yoloworld_esam_image
detections = sv.Detections.from_inference(results)
AttributeError: type object 'Detections' has no attribute 'from_inference'

first time running and i encountered this. some package issus? how should i fix the code?

2024-05-08 19:40:57,132- root:1894- WARNING- Traceback (most recent call last):
File "F:\ComfyUI\ComfyUI\nodes.py", line 1876, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM_init.py", line 1, in
from . import YOLO_WORLD_EfficientSAM
File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 9, in
from inference.models import YOLOWorld
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference_init_.py", line 1, in
from inference.core.interfaces.stream.stream import Stream # isort:skip
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\interfaces\stream\stream.py", line 13, in
from inference.core.active_learning.middlewares import (
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\active_learning\middlewares.py", line 7, in
from inference.core.active_learning.accounting import image_can_be_submitted_to_batch
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\active_learning\accounting.py", line 4, in
from inference.core.roboflow_api import (
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\roboflow_api.py", line 11, in
from inference.core.cache import cache
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\cache_init_.py", line 5, in
from inference.core.cache.redis import RedisCache
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\cache\redis.py", line 15, in
from inference.core.entities.responses.inference import InferenceResponseImage
File "F:\ComfyUI\python_embeded\Lib\site-packages\inference\core\entities\responses\inference.py", line 5, in
from pydantic import BaseModel, ConfigDict, Field, ValidationError, field_serializer
ImportError: cannot import name 'field_serializer' from 'pydantic' (F:\ComfyUI\python_embeded\Lib\site-packages\pydantic_init_.cp311-win_amd64.pyd)

就不能换成新版本的环境版本？？？

Error occurred when executing MaskToImage:

cannot reshape tensor of 0 elements into shape [-1, 1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous

File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy_extras\nodes_mask.py", line 109, in mask_to_image
result = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Error occurred when executing Yoloworld_ModelLoader_Zho:

[ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from /tmp/cache\clip/ViT-B-32\visual.onnx failed:Protobuf parsing failed.

File "D:\comfyui\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\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 "D:\comfyui\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\comfyui\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 70, in load_yolo_world_model
YOLO_WORLD_MODEL = YOLOWorld(model_id=yolo_world_model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\comfyui\Lib\site-packages\inference\models\yolo_world\yolo_world.py", line 54, in init
) -> ObjectDetectionInferenceResponse:
^^^^^^^^^^^^^^^^^^^^^^
File "C:\ProgramData\anaconda3\envs\comfyui\Lib\site-packages\inference\models\clip\clip_model.py", line 65, in init
self.cache_file("visual.onnx"),
^^^^^^^^
File "C:\ProgramData\anaconda3\envs\comfyui\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 383, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "C:\ProgramData\anaconda3\envs\comfyui\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 424, in _create_inference_session
sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

When you use the settings at 0.00, it detects the prompt, but it also detects unnecessary places.

It doesn't detect when you set it to 0.01 or higher. What is the problem?

and 0.1

当模型选择yolo_world/l时，报错（其它模型没有问题）：
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

Start installing ComfyUI YoloWorld-EfficientSAMStart
git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-YoloWorld-EfficientSAM to install正克隆到 'ComfyUI-YoloWorld-EfficientSAM'...
正克隆到 'ComfyUI-YoloWorld-EfficientSAM'...Install: pip packagesCollecting inference-gpu==0.9.13 (from inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached inference_gpu-0.9.13-py3-none-any.whl.metadata (18 kB)
Collecting APScheduler<=3.10.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached APScheduler-3.10.1-py3-none-any.whl.metadata (5.7 kB)
Collecting cython<=3.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached Cython-3.0.0-cp310-cp310-macosx_10_9_x86_64.whl.metadata (3.1 kB)
Collecting python-dotenv<=2.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached python_dotenv-1.0.1-py3-none-any.whl.metadata (23 kB)
Collecting fastapi<1.0,>=0.100 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached fastapi-0.110.0-py3-none-any.whl.metadata (25 kB)
Requirement already satisfied: numpy<=1.25.2 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (1.24.4)
Collecting opencv-python<=4.8.0.76 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached opencv_python-4.8.0.76-cp37-abi3-macosx_10_16_x86_64.whl.metadata (19 kB)
Requirement already satisfied: piexif<=1.1.3 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (1.1.3)
Requirement already satisfied: pillow<11.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (9.5.0)
Collecting prometheus-fastapi-instrumentator<=6.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached prometheus_fastapi_instrumentator-6.0.0-py3-none-any.whl.metadata (13 kB)
Collecting redis<6.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached redis-5.0.3-py3-none-any.whl.metadata (9.3 kB)
Requirement already satisfied: requests>=2.26.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (2.31.0)
Collecting rich<=13.5.2 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached rich-13.5.2-py3-none-any.whl.metadata (18 kB)
Collecting shapely<=2.0.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached shapely-2.0.1-cp310-cp310-macosx_10_9_x86_64.whl.metadata (7.0 kB)
Collecting supervision<1.0.0,>0.16.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached supervision-0.19.0-py3-none-any.whl.metadata (13 kB)
Collecting pybase64<2.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached pybase64-1.3.2-cp310-cp310-macosx_10_9_x86_64.whl.metadata (7.9 kB)
Requirement already satisfied: scikit-image>=0.19.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (0.22.0)
Collecting requests-toolbelt>=1.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached requests_toolbelt-1.0.0-py2.py3-none-any.whl.metadata (14 kB)
Requirement already satisfied: wheel>=0.38.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (0.41.2)
Requirement already satisfied: setuptools>=65.5.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (68.0.0)
Collecting pytest-asyncio<=0.21.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached pytest_asyncio-0.21.1-py3-none-any.whl.metadata (4.0 kB)
Requirement already satisfied: networkx>=3.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (3.2.1)
Requirement already satisfied: pydantic>=2.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (2.6.3)
INFO: pip is looking at multiple versions of inference-gpu to determine which version is compatible with other requirements. This could take a while.

👇
ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu<=1.15.1 (from inference-gpu) (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu<=1.15.1
Install extension ComfyUI YoloWorld-EfficientSAM failed: Install(git-clone) error: https://github.com/ZHO-ZHO-ZHO/ComfyUI-YoloWorld-EfficientSAM / Error: Command failed with exit code 1: ~/miniconda3/envs/comflowy/bin/pip install -r requirements.txt
ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu<=1.15.1 (from inference-gpu) (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu<=1.15.1
👆

Collecting inference-gpu==0.9.13 (from inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached inference_gpu-0.9.13-py3-none-any.whl.metadata (18 kB)
Collecting APScheduler<=3.10.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached APScheduler-3.10.1-py3-none-any.whl.metadata (5.7 kB)
Collecting cython<=3.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached Cython-3.0.0-cp310-cp310-macosx_10_9_x86_64.whl.metadata (3.1 kB)
Collecting python-dotenv<=2.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached python_dotenv-1.0.1-py3-none-any.whl.metadata (23 kB)
Collecting fastapi<1.0,>=0.100 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached fastapi-0.110.0-py3-none-any.whl.metadata (25 kB)
Requirement already satisfied: numpy<=1.25.2 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (1.24.4)
Collecting opencv-python<=4.8.0.76 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached opencv_python-4.8.0.76-cp37-abi3-macosx_10_16_x86_64.whl.metadata (19 kB)
Requirement already satisfied: piexif<=1.1.3 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (1.1.3)
Requirement already satisfied: pillow<11.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (9.5.0)
Collecting prometheus-fastapi-instrumentator<=6.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached prometheus_fastapi_instrumentator-6.0.0-py3-none-any.whl.metadata (13 kB)
Collecting redis<6.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached redis-5.0.3-py3-none-any.whl.metadata (9.3 kB)
Requirement already satisfied: requests>=2.26.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (2.31.0)
Collecting rich<=13.5.2 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached rich-13.5.2-py3-none-any.whl.metadata (18 kB)
Collecting shapely<=2.0.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached shapely-2.0.1-cp310-cp310-macosx_10_9_x86_64.whl.metadata (7.0 kB)
Collecting supervision<1.0.0,>0.16.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached supervision-0.19.0-py3-none-any.whl.metadata (13 kB)
Collecting pybase64<2.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached pybase64-1.3.2-cp310-cp310-macosx_10_9_x86_64.whl.metadata (7.9 kB)
Requirement already satisfied: scikit-image>=0.19.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (0.22.0)
Collecting requests-toolbelt>=1.0.0 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached requests_toolbelt-1.0.0-py2.py3-none-any.whl.metadata (14 kB)
Requirement already satisfied: wheel>=0.38.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (0.41.2)
Requirement already satisfied: setuptools>=65.5.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (68.0.0)
Collecting pytest-asyncio<=0.21.1 (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1))
Using cached pytest_asyncio-0.21.1-py3-none-any.whl.metadata (4.0 kB)
Requirement already satisfied: networkx>=3.1 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (3.2.1)
Requirement already satisfied: pydantic>=2.0 in ~/miniconda3/envs/comflowy/lib/python3.10/site-packages (from inference-gpu==0.9.13->inference-gpu[yolo-world]==0.9.13->-r requirements.txt (line 1)) (2.6.3)
INFO: pip is looking at multiple versions of inference-gpu to determine which version is compatible with other requirements. This could take a while.^C
Stopped server

i stuck at apply instantID node.

terminal:

got prompt

Failed to validate prompt for output 391:

• ApplyInstantID 336:

• Required input is missing: image_features

Output will be ignored

Failed to validate prompt for output 378:

Output will be ignored

[rgthree] Using rgthree's optimized recursive execution.

Prompt executed in 0.01 seconds

Issue 1

If there is no comma at the end of the word entered in the input box, it may fail to detect, especially with local detection.

Issue 2

In the Linux system, the yolo-world.pt file will be automatically downloaded to /tmp/cache/yolo_world instead of ComfyUI/models/yolo_world. It is unknown if this issue will occur under Windows system.

Issue 3

Will there be an addition of YOLO-World-Seg detection function in the future? This should improve detection efficiency.

I did two ways of installation, manual install and manager install:

1. during manual install, I see this error but I chose to ignore it and I don't know if it is related to the problem.
   ===
   ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
   mediapipe 0.10.9 requires protobuf<4,>=3.11, but you have protobuf 4.25.2 which is incompatible.
   ===

2. I then run the sample workflow provide for image, and the node "Convert mask to image" throws the following error (see also attached screenshot):

===
Error occurred when executing MaskToImage:

cannot reshape tensor of 0 elements into shape [-1, 1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous

File "C:\Apps\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Apps\ComfyUI\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:\Apps\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Apps\ComfyUI\ComfyUI\comfy_extras\nodes_mask.py", line 109, in mask_to_image
result = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

3. I then removed the "Convert mask to image" node, and nothing ( of detection) seems to happen, see screen shot below:
   

4. btw, any idea which directory is yolo-world/l model auto-downloaded to ?

5. I then manually deleted the above installation and installed again via manager this time. I don't notice any error (such as the above mentioned incompatible protobuf error), but the exception thrown by "Convert mask to image" node persists and the detection of yolo-world still doesn't happen.

Pls help and thanks a bunch in advance (so eager to try out the excellent YOLO-WORLD + ESAM!!!)

Sean

confidence threshold 0.05

confidence threshold 0.10

!!! Exception during processing!!! Can't get attribute 'WorldModel' on <module 'ultralytics.nn.tasks' from 'E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\nn\tasks.py'>
Traceback (most recent call last):
File "E:\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "E:\ComfyUI-aki-v1.3\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-aki-v1.3\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "E:\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 70, in load_yolo_world_model
YOLO_WORLD_MODEL = YOLOWorld(model_id=yolo_world_model)
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\inference\models\yolo_world\yolo_world.py", line 36, in init
self.model = YOLO(self.cache_file("yolo-world.pt"))
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\engine\model.py", line 95, in init
self._load(model, task)
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\engine\model.py", line 161, in _load
self.model, self.ckpt = attempt_load_one_weight(weights)
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\nn\tasks.py", line 700, in attempt_load_one_weight
ckpt, weight = torch_safe_load(weight) # load ckpt
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\nn\tasks.py", line 634, in torch_safe_load
return torch.load(file, map_location="cpu"), file # load
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\serialization.py", line 1014, in load
return _load(opened_zipfile,
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\serialization.py", line 1422, in _load
result = unpickler.load()
File "E:\ComfyUI-aki-v1.3\python\lib\site-packages\torch\serialization.py", line 1415, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'WorldModel' on <module 'ultralytics.nn.tasks' from 'E:\ComfyUI-aki-v1.3\python\lib\site-packages\ultralytics\nn\tasks.py'>

ComfyUI-YoloWorld-EfficientSAM node vision is 0416，when run yolo world model loader occur this error，anyone knows how fix it？thx so much！

At first was getting an error saying it couldnt find efficientsam_s_gpu.jit but then I downloaded the model and adjusted the naming to match what was being searched for and now getting the following error:

PytorchStreamReader failed reading zip archive: failed finding central directory

File "C:\Users\trist\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\trist\Downloads\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 "C:\Users\trist\Downloads\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 "C:\Users\trist\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 98, in load_esam_model
EFFICIENT_SAM_MODEL = torch.jit.load(model_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\trist\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\jit_serialization.py", line 159, in load
cpp_module = torch._C.import_ir_module(cu, str(f), map_location, _extra_files, _restore_shapes) # type: ignore[call-arg]

一直卡在这个节点：Yoloworld_ModelLoader_Zho，不报错，也没法取消进程，只能关掉comfyui重启。

raise RoboflowAPIConnectionError(

inference.core.exceptions.RoboflowAPIConnectionError: Could not connect to Roboflow API.

I have followed the install proceadure on every point and downloaded the models form huggingface, but it present the error:

**When loading the graph, the following node types were not found:

• Yoloworld_ESAM_Zho
• ESAM_ModelLoader_Zho
• Yoloworld_ModelLoader_Zho

Nodes that have failed to load will show as red on the graph.**

I looked at the YOLO_WORLD_EfficientSAM.py and it does seem to have these nodes.
Thanks for your work and your help.

Hi. Thanks for this new great custom node!

The node suite, installed it via ComfyUI Manager, fails to import due to the following error:

File "/ComfyUI/nodes.py", line 1887, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "/ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM/init.py", line 1, in
from . import YOLO_WORLD_EfficientSAM
File "/ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM/YOLO_WORLD_EfficientSAM.py", line 9, in
from inference.models import YOLOWorld
ModuleNotFoundError: No module named 'inference'

Cannot import /ComfyUI/custom_nodes/ComfyUI-YoloWorld-EfficientSAM module for custom nodes: No module named 'inference'

I believe this is because I am on Apple M2 and the requirement.txt is looking for an inference-gpu package that is not available for macOS.

As I read on PyPI, perhaps the requirement can be modified to also install the inference package?

Thank you

Hi, ZHO-ZHO-SHO:

This is a very good tool. But I met a lot of error:

Mixlab Nodes: Loaded

LaMaInpainting.available True
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json

clip_interrogator_model not found: D:\AI\ComfyUI_windows_portable\ComfyUI\models\clip_interrogator/Salesforce/blip-image-captioning-base, pls download from https://huggingface.co/Salesforce/blip-image-captioning-base

ClipInterrogator.available True

text_generator_model not found: D:\AI\ComfyUI_windows_portable\ComfyUI\models\prompt_generator/text2image-prompt-generator, pls download from https://huggingface.co/succinctly/text2image-prompt-generator/tree/main

zh_en_model not found: D:\AI\ComfyUI_windows_portable\ComfyUI\models\prompt_generator/opus-mt-zh-en, pls download from https://huggingface.co/Helsinki-NLP/opus-mt-zh-en/tree/main

PromptGenerate.available True
ChinesePrompt.available True
RembgNode_.available True

Traceback (most recent call last):
File "D:\AI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1887, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM_init.py", line 1, in
from . import YOLO_WORLD_EfficientSAM
File "D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 6, in
import supervision as sv
ModuleNotFoundError: No module named 'supervision'

Cannot import D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM module for custom nodes: No module named 'supervision'
[comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[comfyui_controlnet_aux] | INFO -> Using symlinks: False
[comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly
warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly")

[START] ComfyUI AlekPet Nodes

Node -> ArgosTranslateNode [Loading]
Node -> ExtrasNode [Loading]
Node -> PainterNode [Loading]
Node -> PoseNode [Loading]
Node -> TranslateNode [Loading]

[END] ComfyUI AlekPet Nodes

Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: ffmpeg_bin_path is not set in D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 211 nodes successfully.

Cannot import C:\Users\65283\comflowy\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Yolo�[0KW

安装后乱码

Error occurred when executing Yoloworld_ESAM_Zho:

'WorldModel' object has no attribute 'clip_model'

File "C:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\AI\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 "C:\AI\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 "C:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 139, in yoloworld_esam_image
YOLO_WORLD_MODEL.set_classes(categories)
File "C:\anaconda3\envs\ComfyUI\Lib\site-packages\inference\models\yolo_world\yolo_world.py", line 133, in set_classes
self.model.set_classes(text)
File "C:\anaconda3\envs\ComfyUI\Lib\site-packages\ultralytics\models\yolo\model.py", line 96, in set_classes
self.model.set_classes(classes)
File "C:\anaconda3\envs\ComfyUI\Lib\site-packages\ultralytics\nn\tasks.py", line 575, in set_classes
if not self.clip_model:
^^^^^^^^^^^^^^^
File "C:\anaconda3\envs\ComfyUI\Lib\site-packages\torch\nn\modules\module.py", line 1695, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

Yolo performance bad for open-volcabulary, which means a specific style cannot be recoginzed for yolo(well it just trained for human and other realworld object detection, so of course)
Any plan for dino? It's quick enough I guess.

inference-gpu必须使用0.9.13版本吗？可以更新他吗？ 不能和onnxruntime-gpu 1.17.1版本兼容。

环境：Python 3.10.9 Windows 11 23H2 22631.3447

When loading the graph, the following node types were not found:
ESAM_ModelLoader_Zho
Yoloworld_ESAM_Zho
Yoloworld_ModelLoader_Zho

查看启动器的log，有：
Torch version: 2.0.1+cu118
Traceback (most recent call last):
File "D:\ComfyUI_Full\ComfyUI\nodes.py", line 1864, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "D:\ComfyUI_Full\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM_init.py", line 1, in
from . import YOLO_WORLD_EfficientSAM
File "D:\ComfyUI_Full\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 6, in
import supervision as sv
ModuleNotFoundError: No module named 'supervision'

Cannot import D:\ComfyUI_Full\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM module for custom nodes: No module named 'supervision'

'supervision' 模块，我使用pip list查看已经安装上了：
supervision 0.19.0

文件目录：
D:.
│ .gitignore
│ efficient_sam_s_cpu.jit
│ efficient_sam_s_gpu.jit
│ LICENSE
│ README.md
│ requirements.txt
│ YOLO_WORLD_EfficientSAM.py
│ YOLO_WORLD_SEGS.py
│ init.py
│
├─utils
│ efficient_sam.py
│ video.py
│ init.py
│
├─YOLO_World_EfficientSAM_WORKFLOWS
│ YoloWorld-EfficientSAM V1.0 IMG 【Zho】.json
│ YoloWorld-EfficientSAM V1.0 VIDEO 【Zho】.json
│ YoloWorld-EfficientSAM V2.0 IMG 【Zho】.json
│ YoloWorld-EfficientSAM V2.0 VIDEO 【Zho】.json
│
└─__pycache__
YOLO_WORLD_EfficientSAM.cpython-310.pyc
init.cpython-310.pyc

got prompt
[rgthree] Using rgthree's optimized recursive execution.
[rgthree] First run patching recursive_output_delete_if_changed and recursive_will_execute.
[rgthree] Note: If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI.
C:\Users\zg261.conda\envs\ootd\lib\site-packages\torch\nn\functional.py:5476: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.)
attn_output = scaled_dot_product_attention(q, k, v, attn_mask, dropout_p, is_causal)
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\ComfyUI\comfy_extras\nodes_mask.py", line 109, in mask_to_image
result = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)
RuntimeError: cannot reshape tensor of 0 elements into shape [-1, 1, 1, 0] because the unspecified dimension size -1 can be any value and is ambiguous

What is the issue here, and how can it be resolved?