Rtx 4080 16 GB Vram on Win 11 here. Your demo workflow is eating all my 16 Gb Vram and is at about 30 s/it very slow.
Saying you need min 16 Gb Vram is very optimistic. Yes it's doing something but at that speed it's unusable.
Please for the love of god, what can be done?

Thank you for the node, first of all!

However, after installing the node from Manager I faced the problem:

Error occurred when executing PipelineLoader:

yisol/IDM-VTON does not appear to have a file named diffusion_pytorch_model.bin.

File "/workspace/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/workspace/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 "/workspace/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/workspace/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/src/nodes/pipeline_loader.py", line 64, in load_pipeline
unet_encoder = UNet2DConditionModel_ref.from_pretrained(
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/models/modeling_utils.py", line 632, in from_pretrained
model_file = _get_model_file(
File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/diffusers/utils/hub_utils.py", line 371, in _get_model_file
raise EnvironmentError(

Can anybody help please?

Everything seem working fine, but got stuck in “Load IDM-VTON Pipeline - float16” ?

OSError: float16 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with token or log in with huggingface-cli login.

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

Come on, man, you deserve to be respected. o(￣▽￣)ｄ
I will test for the first time.

From the examples I've ran, it seems although the masking and clothing creation is phenomenal. It isn't properly creating the fabrics, colours, and length of referenced. Thank you for your continued work, this node has promise to be amazing. Reference image (drawings included)

Error occurred when executing PipelineLoader:

yisol/IDM-VTON does not appear to have a file named scheduler_config.json.

File "D:\AI\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\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 "D:\AI\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py", line 41, in load_pipeline
noise_scheduler = DDPMScheduler.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 119, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\python_embeded\Lib\site-packages\diffusers\schedulers\scheduling_utils.py", line 143, in from_pretrained
config, kwargs, commit_hash = cls.load_config(
^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 119, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "D:\AI\ComfyUI\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 406, in load_config
raise EnvironmentError(

Hi, thank you for this custom_nodes. But I got a problem when loading it. Please see below.

/home/silver/.local/lib/python3.10/site-packages/diffusers/models/dual_transformer_2d.py:20: FutureWarning: `DualTransformer2DModel` is deprecated and will be removed in version 0.29. Importing `DualTransformer2DModel` from `diffusers.models.dual_transformer_2d` is deprecated and this will be removed in a future version. Please use `from diffusers.models.transformers.dual_transformer_2d import DualTransformer2DModel`, instead.
  deprecate("DualTransformer2DModel", "0.29", deprecation_message)
/home/silver/.local/lib/python3.10/site-packages/diffusers/models/transformer_2d.py:20: FutureWarning: `Transformer2DModelOutput` is deprecated and will be removed in version 0.29. Importing `Transformer2DModelOutput` from `diffusers.models.transformer_2d` is deprecated and this will be removed in a future version. Please use `from diffusers.models.transformers.transformer_2d import Transformer2DModelOutput`, instead.
  deprecate("Transformer2DModelOutput", "0.29", deprecation_message)
/home/silver/.local/lib/python3.10/site-packages/diffusers/models/transformer_2d.py:25: FutureWarning: `Transformer2DModel` is deprecated and will be removed in version 0.29. Importing `Transformer2DModel` from `diffusers.models.transformer_2d` is deprecated and this will be removed in a future version. Please use `from diffusers.models.transformers.transformer_2d import Transformer2DModel`, instead.
  deprecate("Transformer2DModel", "0.29", deprecation_message)

The nodes seem working though. Any ideas? BTW, I'm currently using Python 3.10.2 on linux.

Error accurred as follow:

The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Some weights of the model checkpoint were not used when initializing UNet2DConditionModel:
['add_embedding.linear_1.bias, add_embedding.linear_1.weight, add_embedding.linear_2.bias, add_embedding.linear_2.weight']

How to solve it, please TT

Hi, I think it would be wise to move the download of the weights from the default Huggingface path to the models folder in ComfyUI

Error occurred when executing IDM-VTON:

Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 18.33 GiB
Requested : 3.43 GiB
Device limit : 22.02 GiB
Free (according to CUDA): 31.62 MiB
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB

should fix:
RuntimeError: MPS backend out of memory (MPS allocated: 16.56 GB, other allocations: 128.70 MB, max allowed: 18.13 GB). Tried to allocate 3.00 GB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure).

same issue on cuda with small gpu

Guys, is not possible use it in my RTX 4070 with 12GB VRAM?
I am in linux with 4070 dedicated only for AI and my IGPU renders my desktop, I have 48gb of ram

I would like use it, I've tried bfloat and float but nothings works

Hi, anyone encounted this error too?

2024-05-08 13:24:55,102- root:179- ERROR- !!! Exception during processing!!! Attention.set_processor() got an unexpected keyword argument '_remove_lora'
2024-05-08 13:24:55,108- root:180- ERROR- Traceback (most recent call last):
File "F:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\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 "F:\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 "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py", line 53, in load_pipeline
unet = UNet2DConditionModel.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 119, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\models\modeling_utils.py", line 650, in from_pretrained
model = cls.from_config(config, **unused_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 259, in from_config
model = cls(**init_dict)
^^^^^^^^^^^^^^^^
File "F:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 653, in inner_init
init(self, *args, **init_kwargs)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 791, in init
self.set_attn_processor(attn_procs)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 852, in set_attn_processor
fn_recursive_attn_processor(name, module, processor, _remove_lora=_remove_lora)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 849, in fn_recursive_attn_processor
fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor, _remove_lora=_remove_lora)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 849, in fn_recursive_attn_processor
fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor, _remove_lora=_remove_lora)
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 849, in fn_recursive_attn_processor
fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor, _remove_lora=_remove_lora)
[Previous line repeated 3 more times]
File "F:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\idm_vton\unet_hacked_tryon.py", line 846, in fn_recursive_attn_processor
module.set_processor(processor.pop(f"{name}.processor"), _remove_lora=_remove_lora)
TypeError: Attention.set_processor() got an unexpected keyword argument '_remove_lora'

After pulling the latest commit, error ocurred:

"LayerNormKernelImpl" not implemented for 'Half'

Thank you for the author's efforts, but the testing was slow and the size did not match well. It must be a multiple of 8, and the most crucial thing is that the color did not match after changing into clothes

Is this model work on real time input
if it works just please explain how it works

I can save or preview the Run IDM-VTON Inference.
But if I try to connect anything in between - I get different errors.

For example, connecting Get Resolution node to the Run IDM-VTON Inference image output, I get this error.

Error occurred when executing Get resolution [Crystools]:

'list' object has no attribute 'movedim'

File "S:\ComfyUI1\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "S:\ComfyUI1\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 "S:\ComfyUI1\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "S:\ComfyUI1\ComfyUI\custom_nodes\ComfyUI-Crystools\nodes\image.py", line 221, in execute
res = getResolutionByTensor(image)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "S:\ComfyUI1\ComfyUI\custom_nodes\ComfyUI-Crystools\core\common.py", line 89, in getResolutionByTensor
img = image.movedim(-1, 1)
^^^^^^^^^^^^^

Allocation on device 0 would exceed allowed memory. (out of memory)

why? help me.. plz..

I updated node today and found that I had to re-download the model automatically. It seems that the folder structure has changed. This is not very friendly for those who have already installed it. ：（

Error occurred when executing PipelineLoader:

float16 does not appear to have a file named scheduler_config.json.

File "/root/autodl-tmp/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/root/autodl-tmp/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 "/root/autodl-tmp/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/root/autodl-tmp/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/src/nodes/pipeline_loader.py", line 41, in load_pipeline
noise_scheduler = DDPMScheduler.from_pretrained(
File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/diffusers/schedulers/scheduling_utils.py", line 143, in from_pretrained
config, kwargs, commit_hash = cls.load_config(
File "/root/miniconda3/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 406, in load_config
raise EnvironmentError(

在下面函数(ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py)，
def load_pipeline(self, weight_dtype):

修改两点：
修改1> 把所有的 .to(DEVICE) ，全部注释掉，所有的。

修改2> 函数结尾处
修改前:
pipe.unet_encoder = unet_encoder
pipe = pipe.to(DEVICE)
pipe.weight_dtype = weight_dtype
修改为:

在显卡12G测试，完全无压力。查看显存占用大概6G多点，估计在8G下也能跑。

model and mask image should be resized to size (width, height)

preprocess_images function should expect input images as tensor of size (n_batch, H, W, n_channel)

Hi, where can I find and download workflow as showed on the image?

Should not let hugging face download weights in default cache memory

float16 is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with token or log in with huggingface-cli login.

I just drag workflow.png into the comfyui, after downloading the models, an error was reported. I am already used command huggingface-cli login, but it does not work

Here is the model address:
https://huggingface.co/xiaozaa/IDM-VTON-unofficial/

I cloned the new branch, move_weights.

In custom_nodes/ComfyUI-IDM-VTON/models/idm_vton, I have the idm_vton folder which is exactly the same as the one in the updated README.md, with the relevant files having model.safetensors, etc etc, as i downloaded it from hugging face and deleted the relevant files (based on the new README).

However, I get the following error when running the workflow:

The file mentioned in the README has been downloaded, but the PiplineLoader execution time is too long (more than half an hour). What should I do?

My device: RTX 3090 24G

【Some tips from the console】
Prompt executed in 0.02 seconds
got prompt
[rgthree] Using rgthree's optimized recursive execution.
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.

When I try to output the mask from Run IDM-VTON Inference, I get error:

Error occurred when executing MaskPreview+:

list index out of range

File "/workspace/ComfyUI/execution.py", line 141, in recursive_execute
input_data_all = get_input_data(inputs, class_def, unique_id, outputs, prompt, extra_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/execution.py", line 26, in get_input_data
obj = outputs[input_unique_id][output_index]

Hello, you set license of this project to GPL which allows commercial use but original license is non-commercial see yisol/IDM-VTON#13
so both are not compatible in my opinion (I am not an expert).

I recommend to change license of this repo to same - CC BY-NC-SA 4.0 so that would be a good solution.

The following error is happening on the Load IDM-VTON Pipeline node.

Error occurred when executing PipelineLoader:

Error no file named config.json found in directory /home/ec2-user/repos/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/models.

File "/home/ec2-user/repos/ComfyUI/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/repos/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 "/home/ec2-user/repos/ComfyUI/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/repos/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/src/nodes/pipeline_loader.py", line 46, in load_pipeline
vae = AutoencoderKL.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/.pyenv/versions/3.11.9/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/models/modeling_utils.py", line 567, in from_pretrained
config, unused_kwargs, commit_hash = cls.load_config(
^^^^^^^^^^^^^^^^
File "/home/ec2-user/.pyenv/versions/3.11.9/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/ec2-user/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/configuration_utils.py", line 374, in load_config
raise EnvironmentError(

why

I'm trying to run the model on MacBook Pro M1 Max

Getting this error:

The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to AutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.
!!! Exception during processing!!! cross_attention_dim must be specified for CrossAttnDownBlock2D
Traceback (most recent call last):
  File "/Users/enuriru/ComfyUI/execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enuriru/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 "/Users/enuriru/ComfyUI/execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/src/nodes/pipeline_loader.py", line 46, in load_pipeline
    vae = AutoencoderKL.from_pretrained(
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/models/modeling_utils.py", line 650, in from_pretrained
    model = cls.from_config(config, **unused_kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/configuration_utils.py", line 259, in from_config
    model = cls(**init_dict)
            ^^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/configuration_utils.py", line 653, in inner_init
    init(self, *args, **init_kwargs)
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/models/autoencoders/autoencoder_kl.py", line 90, in __init__
    self.encoder = Encoder(
                   ^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/models/autoencoders/vae.py", line 103, in __init__
    down_block = get_down_block(
                 ^^^^^^^^^^^^^^^
  File "/Users/enuriru/ComfyUI/myenv/lib/python3.11/site-packages/diffusers/models/unets/unet_2d_blocks.py", line 128, in get_down_block
    raise ValueError("cross_attention_dim must be specified for CrossAttnDownBlock2D")
ValueError: cross_attention_dim must be specified for CrossAttnDownBlock2D

there is "cross_attention_dim": 2048, in models/config.json, but it seems it's not passed down.

Any ideas?

Thanks in advance!

Is it possible to add a node for auto-masking (just like the one on the HF Hub demo)?

just pulled the newest code and try to run it. got this erro:
!!! Exception during processing!!! Error no file named config.json found in directory /root/ComfyUI/custom_nodes/ComfyUI-IDM-VTON/models.

1. Don't you have a batch image function?

2. How to make batch images?
   no latent pipe line..

Anyone help me plz. ^^

I tried to install IDM- VTON node in comfyui but I have been facing (import failed) every time and I've tried to install it manually also with manager but it just gives me the same error (import failed). PLZ HELP

Issue:
Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,

Config:
python 3.10
torch 2.3.0

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.116.04 Driver Version: 525.116.04 CUDA Version: 12.0 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA A40 On | 00000000:E3:00.0 Off | 0 |
| 0% 24C P8 18W / 300W | 0MiB / 46068MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+

When I use other clouthes than the default one, the output color always be dark, like below:

need to reconcile output of the inference node with expected input of image preview and image saving nodes

Hey in the workflow the node is red when installing the node - and I'm getting ímport failed'- please help!!

implement workflow to extract mask and densepose directly from model image. see here

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.
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Some weights of the model checkpoint were not used when initializing UNet2DConditionModel:
['add_embedding.linear_1.bias, add_embedding.linear_1.weight, add_embedding.linear_2.bias, add_embedding.linear_2.weight']
Loading pipeline components...: 0%| | 0/8 [00:00<?, ?it/s]False

===================================BUG REPORT===================================
E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\cuda_setup\main.py:167: UserWarning: Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

warn(msg)

CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=121, Highest Compute Capability: 8.9.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\libbitsandbytes_cuda121.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
Loading pipeline components...: 0%| | 0/8 [00:00<?, ?it/s]
!!! Exception during processing!!!
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

Traceback (most recent call last):
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\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:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py", line 96, in load_pipeline
pipe = TryonPipeline.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 812, in from_pretrained
maybe_raise_or_warn(
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 254, in maybe_raise_or_warn
unwrapped_sub_model = unwrap_model(sub_model)
^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 229, in unwrap_model
from peft import PeftModel
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft_init.py", line 22, in
from .auto import (
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\auto.py", line 31, in
from .config import PeftConfig
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\config.py", line 23, in
from .utils import CONFIG_NAME, PeftType, TaskType
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\utils_init.py", line 21, in
from .loftq_utils import replace_lora_weights_loftq
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\utils\loftq_utils.py", line 35, in
import bitsandbytes as bnb
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes_init.py", line 6, in
from . import cuda_setup, utils, research
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research_init_.py", line 1, in
from . import nn
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research\nn_init_.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\optim_init_.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\cextension.py", line 20, in
raise RuntimeError('''
RuntimeError:
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

[profiler] #11 PipelineLoader: 23.8465 seconds, total 23.8465 seconds
[profiler] #10 IDM-VTON: 0.001 seconds, total 23.8474 seconds(#11 #14 #13 #16 #17)
[profiler] #18 SaveImage: 0.0006 seconds, total 23.848 seconds(#10)
Prompt executed in 23.85 seconds

When loading the graph, the following node types were not found:
IDM-VTON
PipelineLoader
Nodes that have failed to load will show as red on the graph.