controlnet issues in 4.0

[whmc76]

i have test with Searge-SDXL-Reborn-v4_0.json

revision not working, it could preprocess the image but nothing happend to the image generated,

canny and recolor is good,

depth and sketch not

depth Error occurred when executing SeargeControlnetAdapterV2:

stat: path should be string, bytes, os.PathLike or integer, not NoneType

File "E:\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\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\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\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 149, in get_value (stack_entry, image) = self.create_dict( File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 110, in create_dict cn_image = self.process_image(cn_image, controlnet_mode, low_threshold, high_threshold) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 84, in process_image image = leres(image, low_threshold, high_threshold, self.leres_annotator_full_path) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet__init.py", line 23, in leres annotator = LeresDetector.from_pretrained(annotator_model).to(model_management.get_torch_device()) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet\leres\init__.py", line 23, in from_pretrained if os.path.isdir(pretrained_model_or_path): File "genericpath.py", line 42, in isdir

sketch Error occurred when executing SeargeControlnetAdapterV2:

stat: path should be string, bytes, os.PathLike or integer, not NoneType

File "E:\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\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\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\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 149, in get_value (stack_entry, image) = self.create_dict( File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 110, in create_dict cn_image = self.process_image(cn_image, controlnet_mode, low_threshold, high_threshold) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet_adapter.py", line 87, in process_image image = hed(image, self.hed_annotator_full_path) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet__init.py", line 39, in hed annotator = HEDdetector.from_pretrained(annotator_model).to(model_management.get_torch_device()) File "E:\ComfyUI_windows_portable\ComfyUI\custom_nodes\SeargeSDXL\modules\controlnet\hed\init__.py", line 65, in from_pretrained if os.path.isdir(pretrained_model_or_path): File "genericpath.py", line 42, in isdir

[SeargeDP]

You have to download and copy the required model files as described in the readme file. Or use the new installer script.

[viebrix]

I have the same problem. models are installed in

/media/software/ComfyUI/models/controlnet$ ls
control-lora-canny-rank256.safetensors
control-lora-depth-rank128.safetensors
control-lora-depth-rank256.safetensors
control-lora-openposeXL2-rank256.safetensors
control-lora-recolor-rank256.safetensors
control-lora-sketch-rank256.safetensors
depth-zoe-xl-v1.0-controlnet.safetensors
diffusers_xl_canny_mid.safetensors
diffusers_xl_depth_mid.safetensors
OpenPoseXL2.safetensors
put_controlnets_and_t2i_here
sai_xl_canny_128lora.safetensors
sai_xl_canny_256lora.safetensors
sai_xl_depth_128lora.safetensors
sai_xl_depth_256lora.safetensors
sai_xl_recolor_128lora.safetensors
sai_xl_recolor_256lora.safetensors
sai_xl_sketch_128lora.safetensors
sai_xl_sketch_256lora.safetensors
t2i-adapter_xl_canny.safetensors
t2i-adapter_xl_openpose.safetensors

ControlNetHED.pth and res101.pth is also in the annotators directory clip_vision_g.safetensors is in the clip_vision directory...

what have i missed? I'm using comfyui in linux...

in the workflow I have set in the "Controlnet and Revision Adapter" the controlnet_mode: depth controlnet_preprocessor: true in Controlsnet Model Selector: depth_checkpoint there I tried every depth model from directory which i have shown at the beginning of this post.

Thanks for any help

[viebrix]

Updating ComfyUI with the ComfyUI Manager Menu did the trick. The Console wrote a lot of: Requirement already satisfied And I was sure I should have the least version, because I installed ComfyUI last week, but something seems to have changed.