search

ltdrdata / ComfyUI-Impact-Pack

Custom nodes pack for ComfyUI This custom node helps to conveniently enhance images through Detector, Detailer, Upscaler, Pipe, and more.
GNU General Public License v3.0
1.68k stars 158 forks source link

Error for DetailerForEachDebugPipe #330

Closed Charuru closed 9 months ago

Charuru commented 9 months ago 
Error occurred when executing DetailerForEachDebugPipe:

tuple indices must be integers or slices, not str

File "D:\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\execution.py", line 83, 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 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 1162, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 207, in do_detail
enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 267, in enhance_detail
positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 1619, in apply
image = self.preprocessor.apply(image, mask)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack\inspire\segs_support.py", line 178, in apply
return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^

Please help, just uninstalled and reinstalled impact and inspired pack so I believe both should be the latest. Also the latest build of comfyui after turbo.

Was trying to run this: https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Inspire-Pack/workflow/regional-ipadapter.png

ltdrdata commented 9 months ago

Show me the full startup terminal log of ComfyUI. If you are using ComfyUI-Manager, you should be able to find the comfyui.log file in the ComfyUI execution path.

Charuru commented 9 months ago

Thanks! Here's my logs:


** ComfyUI start up time: 2023-11-28 23:26:07.742996

Prestartup times for custom nodes:
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Using xformers cross attention
Adding extra search path loras C:\Users\aaa\projects\comfyui-files\loras
Adding extra search path checkpoints C:\Users\aaa\projects\comfyui-files\checkpoints
Adding extra search path controlnet C:\Users\aaa\projects\comfyui-files\controlnet
### Loading: ComfyUI-Impact-Pack (V4.36.2)
### Loading: ComfyUI-Impact-Pack (Subpack: V0.3.2)
### Loading: ComfyUI-Inspire-Pack (V0.47.1)
### Loading: ComfyUI-Manager (V1.5)
### ComfyUI Revision: 1754 [777f6b15] | Released on '2023-11-28'
Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Comfyroll Custom Nodes: Loaded
Registered sys.path: ['D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\__init__.py', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_pycocotools', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_oneformer', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_mmpkg', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_midas_repo', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_detectron2', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\controlnet_aux', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\animation_nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\animation_nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Frame-Interpolation', 'C:\\Python311\\Lib\\site-packages\\git\\ext\\gitdb', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Custom-Scripts', 'D:\\ComfyUI\\comfy', 'D:\\ComfyUI', 'C:\\Python311\\python311.zip', 'C:\\Python311\\DLLs', 'C:\\Python311\\Lib', 'C:\\Python311', 'C:\\Users\\aaa\\AppData\\Roaming\\Python\\Python311\\site-packages', 'C:\\Python311\\Lib\\site-packages', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Impact-Pack\\modules', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Impact-Pack\\impact_subpack', '../..']
FizzleDorf Custom Nodes: Loaded
[comfy_mtb] | WARNING -> Web extensions folder at D:\ComfyUI\web\extensions\mtb is not a symlink, if updating please delete it before
[comfy_mtb] | STATUS -> Some nodes failed to load:
    Failed to import module faceenhance because ModuleNotFoundError: No module named 'basicsr'
    Failed to import module faceswap because ModuleNotFoundError: No module named 'onnx.onnx_cpp2py_export.defs'; 'onnx.onnx_cpp2py_export' is not a package
    Failed to import module generate because ModuleNotFoundError: No module named 'qrcode'
    Failed to import module mask because ImportError: Numba needs NumPy 1.24 or less

Check that you properly installed the dependencies.
If you think this is a bug, please report it on the github page (https://github.com/melMass/comfy_mtb/issues)
[comfy_mtb] | STATUS -> Loaded the following nodes:
    Animation Builder (mtb): Convenient way to manage basic animation maths at the core of many of my workflows
    Batch Float (mtb): Generates a batch of float values with interpolation
    Batch Transform (mtb): Transform a batch of images using a batch of keyframes
    Batch Shape (mtb): Generates a batch of 2D shapes with optional shading (experimental)
    Batch Make (mtb): Simply duplicates the input frame as a batch
    Batch Float Assemble (mtb): Assembles mutiple batches of floats into a single stream (batch)
    Batch Float Fill (mtb): Fills a batch float with a single value until it reaches the target length
    Smart Step (mtb): Utils to control the steps start/stop of the KAdvancedSampler in percentage
    Styles Loader (mtb): Load csv files and populate a dropdown from the rows (à la A111)
    Interpolate Clip Sequential (mtb): -
    Bbox From Mask (mtb): From a mask extract the bounding box
    Bbox (mtb): The bounding box (BBOX) custom type used by other nodes
    Crop (mtb): Crops an image and an optional mask to a given bounding box
    Uncrop (mtb): Uncrops an image to a given bounding box
    Debug (mtb): Experimental node to debug any Comfy values, support for more types and widgets is planned
    Save Tensors (mtb): Save torch tensors (image, mask or latent) to disk, useful to debug things outside comfy
    Deep Bump (mtb): Normal & height maps generation from single pictures
    String Replace (mtb): Basic string replacement
    Fit Number (mtb): Fit the input float using a source and target range
    Get Batch From History (mtb): Very experimental node to load images from the history of the server.
    Any To String (mtb): Tries to take any input and convert it to a string
    Load Film Model (mtb): Loads a FILM model
    Film Interpolation (mtb): Google Research FILM frame interpolation for large motion
    Concat Images (mtb): Add images to batch
    Color Correct (mtb): Various color correction methods
    Image Compare (mtb): Compare two images and return a difference image
    Image Tile Offset (mtb): Mimics an old photoshop technique to check for seamless textures
    Blur (mtb): Blur an image using a Gaussian filter.
    Mask To Image (mtb): Converts a mask (alpha) to an RGB image with a color and background
    Colored Image (mtb): Constant color image of given size
    Image Premultiply (mtb): Premultiply image with mask
    Image Resize Factor (mtb): Extracted mostly from WAS Node Suite, with a few edits (most notably multiple image support) and less features.
    Save Image Grid (mtb): Save all the images in the input batch as a grid of images.
    Load Image From Url (mtb): Load an image from the given URL
    Stack Images (mtb): Stack the input images horizontally or vertically
    Save Gif (mtb): Save the images from the batch as a GIF
    Export With Ffmpeg (mtb): Export with FFmpeg (Experimental)
    Latent Lerp (mtb): Linear interpolation (blend) between two latent vectors
    Model Patch Seamless (mtb): Uses the stable diffusion 'hack' to infer seamless images by setting the model layers padding mode to circular (experimental)
    Vae Decode (mtb): Wrapper for the 2 core decoders but also adding the sd seamless hack, taken from: FlyingFireCo/tiled_ksampler
    Float To Number (mtb): Node addon for the WAS Suite. Converts a "comfy" FLOAT to a NUMBER.
    Int To Bool (mtb): Basic int to bool conversion
    Int To Number (mtb): Node addon for the WAS Suite. Converts a "comfy" INT to a NUMBER.
    Transform Image (mtb): Save torch tensors (image, mask or latent) to disk, useful to debug things outside comfy
    Load Image Sequence (mtb): Load an image sequence from a folder. The current frame is used to determine which image to load.
    Save Image Sequence (mtb): Save an image sequence to a folder. The current frame is used to determine which image to save.

Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Failed!
Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Searge-SDXL v4.3.1 in D:\ComfyUI\custom_nodes\SeargeSDXL
Traceback (most recent call last):
  File "D:\ComfyUI\nodes.py", line 1800, in load_custom_node
    module_spec.loader.exec_module(module)
  File "<frozen importlib._bootstrap_external>", line 940, in exec_module
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  File "D:\ComfyUI\custom_nodes\was-node-suite-comfyui\__init__.py", line 1, in <module>
    from .WAS_Node_Suite import NODE_CLASS_MAPPINGS
  File "D:\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 36, in <module>
    from numba import jit
  File "C:\Python311\Lib\site-packages\numba\__init__.py", line 55, in <module>
    _ensure_critical_deps()
  File "C:\Python311\Lib\site-packages\numba\__init__.py", line 42, in _ensure_critical_deps
    raise ImportError("Numba needs NumPy 1.24 or less")
ImportError: Numba needs NumPy 1.24 or less

Cannot import D:\ComfyUI\custom_nodes\was-node-suite-comfyui module for custom nodes: Numba needs NumPy 1.24 or less

Import times for custom nodes:
   0.0 seconds: D:\ComfyUI\custom_nodes\sampler_rescalecfg.py
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Logic
   0.0 seconds: D:\ComfyUI\custom_nodes\ControlNet-LLLite-ComfyUI
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui_lora_tag_loader
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui-tooling-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_ADV_CLIP_emb
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Noise
   0.0 seconds: D:\ComfyUI\custom_nodes\sd-dynamic-thresholding
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui-previewlatent
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
   0.0 seconds: D:\ComfyUI\custom_nodes\masquerade-nodes-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_JPS-Nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_NestedNodeBuilder
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Cutoff
   0.0 seconds: D:\ComfyUI\custom_nodes\stability-ComfyUI-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-post-processing-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_FizzNodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Custom-Scripts
   0.0 seconds (IMPORT FAILED): D:\ComfyUI\custom_nodes\was-node-suite-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
   0.0 seconds: D:\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes
   0.0 seconds: D:\ComfyUI\custom_nodes\efficiency-nodes-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui_controlnet_aux
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
   0.0 seconds: D:\ComfyUI\custom_nodes\facerestore_cf
   0.1 seconds: D:\ComfyUI\custom_nodes\comfy_mtb
   0.1 seconds: D:\ComfyUI\custom_nodes\ComfyI2I
   0.2 seconds: D:\ComfyUI\custom_nodes\comfyui-PromptAttention
   0.2 seconds: D:\ComfyUI\custom_nodes\clipseg.py
   0.2 seconds: D:\ComfyUI\custom_nodes\comfyui_segment_anything
   0.3 seconds: D:\ComfyUI\custom_nodes\comfyui-reactor-node
   0.4 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Manager
   0.6 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
   0.6 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
   0.6 seconds: D:\ComfyUI\custom_nodes\SeargeSDXL

Starting server

To see the GUI go to: http://0.0.0.0:8193
FETCH DATA from: D:\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json
got prompt
model_type EPS
adm 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
missing {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
Requested to load SD1ClipModel
Loading 1 new model

100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.93it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 11.41it/s]
Requested to load AutoencoderKL
Loading 1 new model

0: 640x448 2 hands, 79.8ms
Speed: 3.0ms preprocess, 79.8ms inference, 43.0ms postprocess per image at shape (1, 3, 640, 448)
[] []
model_type EPS
adm 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
missing {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
Requested to load SD1ClipModel
Loading 1 new model
warning, embedding:bhands-neg, does not exist, ignoring
Detailer: segment upscale for ((47.739136, 42.66028)) | crop region (238, 213) x 3.2273739808994995 -> (768, 687)
Requested to load AutoencoderKL
Loading 1 new model
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "D:\ComfyUI\execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\execution.py", line 83, 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 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 1162, in doit
    DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 207, in do_detail
    enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 267, in enhance_detail
    positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 1619, in apply
    image = self.preprocessor.apply(image, mask)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack\inspire\segs_support.py", line 178, in apply
    return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^
TypeError: tuple indices must be integers or slices, not str

Prompt executed in 10.35 seconds
gc collect
ltdrdata commented 9 months ago

segs_support.py.zip

Please replace the file at D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack\inspire\segs_support.py with the attached file, and resend the log of the execution results.

Charuru commented 9 months ago 
** ComfyUI start up time: 2023-11-29 06:15:35.838447

Prestartup times for custom nodes:
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Using xformers cross attention
Adding extra search path loras C:\Users\mirap\projects\comfyui-files\loras
Adding extra search path checkpoints C:\Users\mirap\projects\comfyui-files\checkpoints
Adding extra search path controlnet C:\Users\mirap\projects\comfyui-files\controlnet
### Loading: ComfyUI-Impact-Pack (V4.36.2)
### Loading: ComfyUI-Impact-Pack (Subpack: V0.3.2)
### Loading: ComfyUI-Inspire-Pack (V0.47.1)
### Loading: ComfyUI-Manager (V1.5)
### ComfyUI Revision: 1754 [777f6b15] | Released on '2023-11-28'
Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Comfyroll Custom Nodes: Loaded
Registered sys.path: ['D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\__init__.py', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_pycocotools', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_oneformer', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_mmpkg', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_midas_repo', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\custom_detectron2', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src\\controlnet_aux', 'D:\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\src', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\animation_nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\animation_nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI_Comfyroll_CustomNodes\\nodes\\comfy', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Frame-Interpolation', 'C:\\Python311\\Lib\\site-packages\\git\\ext\\gitdb', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Custom-Scripts', 'D:\\ComfyUI\\comfy', 'D:\\ComfyUI', 'C:\\Python311\\python311.zip', 'C:\\Python311\\DLLs', 'C:\\Python311\\Lib', 'C:\\Python311', 'C:\\Users\\mirap\\AppData\\Roaming\\Python\\Python311\\site-packages', 'C:\\Python311\\Lib\\site-packages', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Impact-Pack\\modules', 'D:\\ComfyUI\\custom_nodes\\ComfyUI-Impact-Pack\\impact_subpack', '../..']
FizzleDorf Custom Nodes: Loaded
[comfy_mtb] | WARNING -> Web extensions folder at D:\ComfyUI\web\extensions\mtb is not a symlink, if updating please delete it before
[comfy_mtb] | STATUS -> Some nodes failed to load:
    Failed to import module faceenhance because ModuleNotFoundError: No module named 'basicsr'
    Failed to import module faceswap because ModuleNotFoundError: No module named 'onnx.onnx_cpp2py_export.defs'; 'onnx.onnx_cpp2py_export' is not a package
    Failed to import module generate because ModuleNotFoundError: No module named 'qrcode'
    Failed to import module mask because ImportError: Numba needs NumPy 1.24 or less

Check that you properly installed the dependencies.
If you think this is a bug, please report it on the github page (https://github.com/melMass/comfy_mtb/issues)
[comfy_mtb] | STATUS -> Loaded the following nodes:
    Animation Builder (mtb): Convenient way to manage basic animation maths at the core of many of my workflows
    Batch Float (mtb): Generates a batch of float values with interpolation
    Batch Transform (mtb): Transform a batch of images using a batch of keyframes
    Batch Shape (mtb): Generates a batch of 2D shapes with optional shading (experimental)
    Batch Make (mtb): Simply duplicates the input frame as a batch
    Batch Float Assemble (mtb): Assembles mutiple batches of floats into a single stream (batch)
    Batch Float Fill (mtb): Fills a batch float with a single value until it reaches the target length
    Smart Step (mtb): Utils to control the steps start/stop of the KAdvancedSampler in percentage
    Styles Loader (mtb): Load csv files and populate a dropdown from the rows (à la A111)
    Interpolate Clip Sequential (mtb): -
    Bbox From Mask (mtb): From a mask extract the bounding box
    Bbox (mtb): The bounding box (BBOX) custom type used by other nodes
    Crop (mtb): Crops an image and an optional mask to a given bounding box
    Uncrop (mtb): Uncrops an image to a given bounding box
    Debug (mtb): Experimental node to debug any Comfy values, support for more types and widgets is planned
    Save Tensors (mtb): Save torch tensors (image, mask or latent) to disk, useful to debug things outside comfy
    Deep Bump (mtb): Normal & height maps generation from single pictures
    String Replace (mtb): Basic string replacement
    Fit Number (mtb): Fit the input float using a source and target range
    Get Batch From History (mtb): Very experimental node to load images from the history of the server.
    Any To String (mtb): Tries to take any input and convert it to a string
    Load Film Model (mtb): Loads a FILM model
    Film Interpolation (mtb): Google Research FILM frame interpolation for large motion
    Concat Images (mtb): Add images to batch
    Color Correct (mtb): Various color correction methods
    Image Compare (mtb): Compare two images and return a difference image
    Image Tile Offset (mtb): Mimics an old photoshop technique to check for seamless textures
    Blur (mtb): Blur an image using a Gaussian filter.
    Mask To Image (mtb): Converts a mask (alpha) to an RGB image with a color and background
    Colored Image (mtb): Constant color image of given size
    Image Premultiply (mtb): Premultiply image with mask
    Image Resize Factor (mtb): Extracted mostly from WAS Node Suite, with a few edits (most notably multiple image support) and less features.
    Save Image Grid (mtb): Save all the images in the input batch as a grid of images.
    Load Image From Url (mtb): Load an image from the given URL
    Stack Images (mtb): Stack the input images horizontally or vertically
    Save Gif (mtb): Save the images from the batch as a GIF
    Export With Ffmpeg (mtb): Export with FFmpeg (Experimental)
    Latent Lerp (mtb): Linear interpolation (blend) between two latent vectors
    Model Patch Seamless (mtb): Uses the stable diffusion 'hack' to infer seamless images by setting the model layers padding mode to circular (experimental)
    Vae Decode (mtb): Wrapper for the 2 core decoders but also adding the sd seamless hack, taken from: FlyingFireCo/tiled_ksampler
    Float To Number (mtb): Node addon for the WAS Suite. Converts a "comfy" FLOAT to a NUMBER.
    Int To Bool (mtb): Basic int to bool conversion
    Int To Number (mtb): Node addon for the WAS Suite. Converts a "comfy" INT to a NUMBER.
    Transform Image (mtb): Save torch tensors (image, mask or latent) to disk, useful to debug things outside comfy
    Load Image Sequence (mtb): Load an image sequence from a folder. The current frame is used to determine which image to load.
    Save Image Sequence (mtb): Save an image sequence to a folder. The current frame is used to determine which image to save.

Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Failed!
Total VRAM 24564 MB, total RAM 32538 MB
xformers version: 0.0.21
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Searge-SDXL v4.3.1 in D:\ComfyUI\custom_nodes\SeargeSDXL
Traceback (most recent call last):
  File "D:\ComfyUI\nodes.py", line 1800, in load_custom_node
    module_spec.loader.exec_module(module)
  File "<frozen importlib._bootstrap_external>", line 940, in exec_module
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  File "D:\ComfyUI\custom_nodes\was-node-suite-comfyui\__init__.py", line 1, in <module>
    from .WAS_Node_Suite import NODE_CLASS_MAPPINGS
  File "D:\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 36, in <module>
    from numba import jit
  File "C:\Python311\Lib\site-packages\numba\__init__.py", line 55, in <module>
    _ensure_critical_deps()
  File "C:\Python311\Lib\site-packages\numba\__init__.py", line 42, in _ensure_critical_deps
    raise ImportError("Numba needs NumPy 1.24 or less")
ImportError: Numba needs NumPy 1.24 or less

Cannot import D:\ComfyUI\custom_nodes\was-node-suite-comfyui module for custom nodes: Numba needs NumPy 1.24 or less

Import times for custom nodes:
   0.0 seconds: D:\ComfyUI\custom_nodes\sampler_rescalecfg.py
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui-tooling-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Logic
   0.0 seconds: D:\ComfyUI\custom_nodes\ControlNet-LLLite-ComfyUI
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui_lora_tag_loader
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Noise
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_ADV_CLIP_emb
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_JPS-Nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui-previewlatent
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Cutoff
   0.0 seconds: D:\ComfyUI\custom_nodes\sd-dynamic-thresholding
   0.0 seconds: D:\ComfyUI\custom_nodes\masquerade-nodes-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-post-processing-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\stability-ComfyUI-nodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_NestedNodeBuilder
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_FizzNodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Custom-Scripts
   0.0 seconds: D:\ComfyUI\custom_nodes\efficiency-nodes-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\comfyui_controlnet_aux
   0.0 seconds: D:\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes
   0.0 seconds (IMPORT FAILED): D:\ComfyUI\custom_nodes\was-node-suite-comfyui
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
   0.0 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
   0.1 seconds: D:\ComfyUI\custom_nodes\facerestore_cf
   0.1 seconds: D:\ComfyUI\custom_nodes\ComfyI2I
   0.1 seconds: D:\ComfyUI\custom_nodes\comfy_mtb
   0.2 seconds: D:\ComfyUI\custom_nodes\comfyui-PromptAttention
   0.4 seconds: D:\ComfyUI\custom_nodes\clipseg.py
   0.4 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Manager
   0.5 seconds: D:\ComfyUI\custom_nodes\comfyui-reactor-node
   0.7 seconds: D:\ComfyUI\custom_nodes\SeargeSDXL
   1.1 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
   1.2 seconds: D:\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
  11.0 seconds: D:\ComfyUI\custom_nodes\comfyui_segment_anything

Starting server

To see the GUI go to: http://0.0.0.0:8193
FETCH DATA from: D:\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json
got prompt
model_type EPS
adm 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
missing {'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
Requested to load SD1ClipModel
Loading 1 new model

100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:00<00:00, 25.17it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:00<00:00, 21.33it/s]
Requested to load AutoencoderKL
Loading 1 new model

0: 640x448 2 hands, 67.0ms
Speed: 2.0ms preprocess, 67.0ms inference, 18.8ms postprocess per image at shape (1, 3, 640, 448)
[] []
model_type EPS
adm 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
missing {'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
loaded straight to GPU
Requested to load BaseModel
Loading 1 new model
Requested to load SD1ClipModel
Loading 1 new model
warning, embedding:bhands-neg, does not exist, ignoring
Detailer: segment upscale for ((47.739136, 42.66028)) | crop region (238, 213) x 3.2273739808994995 -> (768, 687)
Requested to load AutoencoderKL
Loading 1 new model
[DBG1-DWPreprocessor_wrapper] class_name=DWPose_Preprocessor / module_name=comfyui_controlnet_aux.node_wrappers.dwpose
[DBG2-DWPreprocessor_wrapper] res=(tensor([[[[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]],

         [[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]],

         [[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]],

         ...,

         [[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]],

         [[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]],

         [[0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.],
          ...,
          [0., 0., 0.],
          [0., 0., 0.],
          [0., 0., 0.]]]]),)
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "D:\ComfyUI\execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\execution.py", line 83, 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 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 1162, in doit
    DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\impact_pack.py", line 207, in do_detail
    enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 267, in enhance_detail
    positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack\modules\impact\core.py", line 1619, in apply
    image = self.preprocessor.apply(image, mask)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack\inspire\segs_support.py", line 184, in apply
    res = res['result']
          ~~~^^^^^^^^^^
TypeError: tuple indices must be integers or slices, not str

Prompt executed in 7.18 seconds
gc collect

Thanks here we go.

ltdrdata commented 9 months ago

It seems your controlnet aux node is outdated. Try reinstall it.

Charuru commented 9 months ago

Thanks that fixed it.

driuqzy commented 8 months ago

I'm facing this same error, in RunDiffusion hosted version of ComfyUI.

Error occurred when executing DetailerForEachDebugPipe:

tuple indices must be integers or slices, not str

File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 1197, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 228, in do_detail
enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 267, in enhance_detail
positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 1624, in apply
image = self.preprocessor.apply(image, mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack/inspire/segs_support.py", line 178, in apply
return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]

And here's the server logs:

got prompt
Detailer: segment upscale for ((97.12479, 60.789703)) | crop region (485, 303) x 1.5838550126001647 -> (768, 479)
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 1197, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 228, in do_detail
enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 267, in enhance_detail
positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 1624, in apply
image = self.preprocessor.apply(image, mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack/inspire/segs_support.py", line 178, in apply
return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]
TypeError: tuple indices must be integers or slices, not str
Prompt executed in 3.34 seconds

In Comfy Manager I've tried clicking Update All but that did not resolve.

Do you think it's the same issue as the above, specifically that controlnet aux node is outdated?

Steps to reproduce:

  1. Use this workflow: https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/workflow/dwpose-segs-handfix.png
  2. Install the 1 missing model: Click the C icon on the far left menu, search for swizz8 and choose Swizz8-XREAL-BakedVAE, click Download. Once it's downloaded, refresh the browser.
  3. Update the model paths to the corresponding model paths that RunDiffusion uses.
  4. Click Queue Prompt
ltdrdata commented 8 months ago

I'm facing this same error, in RunDiffusion hosted version of ComfyUI.

Error occurred when executing DetailerForEachDebugPipe:

tuple indices must be integers or slices, not str

File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 1197, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 228, in do_detail
enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 267, in enhance_detail
positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 1624, in apply
image = self.preprocessor.apply(image, mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack/inspire/segs_support.py", line 178, in apply
return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]

And here's the server logs:

got prompt
Detailer: segment upscale for ((97.12479, 60.789703)) | crop region (485, 303) x 1.5838550126001647 -> (768, 479)
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "/opt/rd/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/opt/rd/ComfyUI/execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/opt/rd/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 1197, in doit
DetailerForEach.do_detail(image, segs, model, clip, vae, guide_size, guide_size_for, max_size, seed, steps, cfg,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/impact_pack.py", line 228, in do_detail
enhanced_pil, cnet_pil = core.enhance_detail(cropped_image, model, clip, vae, guide_size, guide_size_for_bbox, max_size,
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 267, in enhance_detail
positive, cnet_pil = control_net_wrapper.apply(positive, upscaled_image, upscaled_mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/modules/impact/core.py", line 1624, in apply
image = self.preprocessor.apply(image, mask)
File "/opt/rd/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack/inspire/segs_support.py", line 178, in apply
return obj.estimate_pose(image, detect_hand, detect_body, detect_face, resolution=resolution)['result'][0]
TypeError: tuple indices must be integers or slices, not str
Prompt executed in 3.34 seconds

In Comfy Manager I've tried clicking Update All but that did not resolve.

Do you think it's the same issue as the above, specifically that controlnet aux node is outdated?

Steps to reproduce:

  1. Use this workflow: https://github.com/ltdrdata/ComfyUI-extension-tutorials/blob/Main/ComfyUI-Impact-Pack/workflow/dwpose-segs-handfix.png
  2. Install the 1 missing model: Click the C icon on the far left menu, search for swizz8 and choose Swizz8-XREAL-BakedVAE, click Download. Once it's downloaded, refresh the browser.
  3. Update the model paths to the corresponding model paths that RunDiffusion uses.
  4. Click Queue Prompt

Yup. Update cnet aux to latest version.