ZHO-ZHO-ZHO / ComfyUI-YoloWorld-EfficientSAM

Unofficial implementation of YOLO-World + EfficientSAM for ComfyUI
GNU General Public License v3.0
588 stars 52 forks source link

Exception during processing!!! Required inputs (['attention_mask']) are missing from input feed (['input_ids']). #88

Open yyoouu opened 1 month ago

yyoouu commented 1 month ago

with the 2 sample workflow,1.0 and 2.0,i get the error msg like these:

Exception during processing!!! Required inputs (['attention_mask']) are missing from input feed (['input_ids']). Traceback (most recent call last): File "D:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\StabilityMatrix\Data\Packages\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:\StabilityMatrix\Data\Packages\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "D:\StabilityMatrix\Data\Packages\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 139, in yoloworld_esam_image YOLO_WORLD_MODEL.set_classes(categories) File "D:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\inference\models\yolo_world\yolo_world.py", line 197, in set_classes cache_miss_embeddings = self.clip_model.embed_text( File "D:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\inference\models\clip\clip_model.py", line 275, in embed_text embeddings = self.textual_onnx_session.run(None, onnx_input_text)[0] File "D:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 213, in run self._validate_input(list(input_feed.keys())) File "D:\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 195, in _validate_input raise ValueError( ValueError: Required inputs (['attention_mask']) are missing from input feed (['input_ids']).

the config look like this: image

thks