zho-zho-zho/comfyui-instantid

Unofficial implementation of InstantID for ComfyUI

👋 Hi，我是 Zho ！

中文 | English

🏛️ 职业：

• 职业建筑师 | 公共建筑
• 罗杰斯✅福斯特❌ | 盖里✅扎哈❌ | 贝聿铭✅路易斯康❌

❣️ 兴趣：

• AIGC
• 建筑设计&理论 | Archigram ✅ 结构主义✅
• 艺术 | 蔡国强✅
• 工业设计、交互设计

🤖 焦点：

• 目前独立从事 AIGC 研究与实践 | 图像✅ 视频✅ 3D✅ LLM✅
• 论文解读 | 发展梳理 | 视频制作

🏗️重心：

• Stable Diffusion 生态 + ComfyUI：
  • ComfyPark 社区筹备中 | 安装与部署 | 系统教程 | 模块+模组 | 工作流设计 | 定制化UI
  • 编写、汉化或优化自定义节点
  • 设计工作流
  • 完成2000+节点测试
  • 未来推出ComfyUI的一个优化版本
• AIGC 理论发展与梳理

🌟 技能：

• ChatGPT（哈哈哈）
• Python

🔥 热门：

• ComfyUI Workflows ZHO: 我的所有工作流（目前共 19 类 46 项）
• 简体中文版 ComfyUI: 主库，完整工作内容和时间线
• ComfyUI Assistant：GPTs帮助创建或解释自定义节点或工作流，上榜 GPTs 全球对话数据第 165 名（12.29数据），目前已达1.7k！
• ComfyUI Portrait Master 简体中文版: 人物肖像提示词生成模块，选择永远比填空更适合人类！
• Stable Diffusion 3 API ComfyUI: 通过 API 将 Stable Diffusion 3 引入 ComfyUI!
• Phi-3-mini in ComfyUI: 将闪电般速度的 Phi-3-mini-4k 模型引入到 ComfyUI 中，生成/补全提示词，解数学题，畅聊人生！
• Gemini in ComfyUI: 将 Gemini Pro 双模型引入到 ComfyUI 中，生成提示词、描述图像，也可与它畅聊人生！
• QWen-VL in ComfyUI: 将目前最好的开源视觉模型 QWen-VL-Plus & Max 引入到 ComfyUI 中，超强细节、文字识别能力，支持单/多轮对话双模式！
• ComfyUI ArtGallery | Prompt Visualization: 将近千种艺术提示词分类可视化，只需选择喜欢的图像 + 滑动选择权重，节点就会自动输出提示词，自由的在艺术世界翱翔吧！
• APISR in ComfyUI:专门用于动漫的超分模型，包含 2x 和 4x 双模型，速度飞快，效果很好
• BiRefNet in ComfyUI:目前最好的开源可商用背景抠除模型，同时支持 图像和视频 处理
• BRIA_RMBG 1.4 in ComfyUI：BRIA 开发的目前最好的背景去除模型，已支持批量处理（可去除视频背景）
• ComfyUI YoloWorld-EfficientSAM：利用全新的 YOLO-World 与 EfficientSAM 实现高效的对象检测 + 分割，支持选择指定蒙版单独输出，同时支持图像和视频
• DepthFM IN ComfyUI：CompVis 推出的 高效 + 多功能 深度估计模型，同时支持 图像和视频 深度估计
• ComfyUI TripoSR ZHO：TripoSR 在 ComfyUI 中的优化版，自带背景去除功能，修复原版黑色背景块bug，优化为按文件名保存 3D 模型
• ComfyUI PhotoMaker: 人物特征迁移与融合，支持单/多张参考图，轻松保持角色一致性！
• ComfyUI InstantID: 仅需一张图就可实现高质量的角色保持！多种风格随心变！
• ComfyUI Text_+ Image：将文字转化为图像的 ComfyUI 节点，还可配合视频生成字幕或帧计数
• ComfyUI Selector + CoInput Multilingual：CoInput 综合输入：高效整合 + 利于复用 + 简化界面 + 中英双语 + 避免efficiency-nodes重复加载的缺陷
• ComfyUI SegMoE：三个臭皮匠顶个诸葛亮！ SD 的 MoE 专家混合模型框架！
• ComfyUI PixArt-alpha Diffusers：对 PixArt-alpha-Diffusers实现，填补原本支持插件失效的空白
• Stable Video Diffusion in ComfyUI：我为 SVD 设计的 工作流 和 节点，文生视频 + 图生视频，更好的交互！
• ComfyUI I2VGenXL：目前 动效自然程度 和 光影 最好的 高清 视频模型
• ComfyUI Differential_Diffusion Workflows：我设计的 Differential Diffusion 工作流

📬 联系我：

• 邮箱：[email protected]
• QQ 群：839821928

🔗 社交媒体：

• 个人页：-Zho-
• Bilibili：我的B站主页
• X（Twitter）：我的Twitter
• 小红书：我的小红书主页

📅 未来计划：

• ComfyPark社区
• 发布 ComfyUI 2400+ 节点测试报告
• 开放精选期刊栏目（博客+订阅）
• 推出 ComfyUI 的特殊优化版本

💡 支持我：

• B站：B站充电
• 爱发电：为我充电

comfyui-instantid's Issues

No error, no effect as well

It seems no id has been applied, although no error.

Skip P:\ComfyUI_4ALL\ComfyUI\custom_nodes\ComfyUI-InstantID module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.

Hi... and thank you!!!
After install the models I got this error:
Skip P:\ComfyUI_4ALL\ComfyUI\custom_nodes\ComfyUI-InstantID module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.

Certain nodes not available in ComfyUI

I did the install and when I open the workflow (local install) it says that there are missing custon nodes :

Ipadapter_instantidLoader
IDBaseModelLoader_local
IDControlNetLoader
ID_Prompt_Styler
IDGenerationNode

they do not come up on the list of custom missing nodes to install. How can I install theses nodes?

Thanks

Some notes on getting this to work

Here are a few notes that the install guide didn't mention, as well as some issues I found along the way:

1. If you're new to this, be sure to have ComfyUI Manager installed (https://github.com/ltdrdata/ComfyUI-Manager)
2. Once you load any sample workflow, if there are nodes missing, just go into the ComfyUI Manager and select "Install Missing Custom Nodes". Lots of videos out there talks about using ComfyUI Manager that's worth watching if you're new.
3. Avoid the workflows that doesn't mention "locally" in the filename. The "fromhub" workflows attempt to download the SDXL model directly from Huggingface, but chances are you already have your model downloaded. And you need to have credentials configured to get this to work. It's just unnecessary.
4. The "V1.0 InstantID_locally【Zho】.json" workflow uses the "InstantID Generation" node that has a bug from which keep it from working with the insightface loader node. Just avoid this workflow until the bug is fixed (as of 01/24/2024)
5. Which leaves only "V2.0 InstantID_locally_pose_ref【Zho】.json" as the workflow that currently works without modifications. :)
6. Install notes ask you to download config.json from (https://huggingface.co/InstantX/InstantID/tree/main/ControlNetModel), but note that the filename downloaded will be named ControlNetModel_config.json. You'll need to rename the file back to "config.json" in order for it to work. The files should be placed under (custom_nodes/ConfyUI-InstantID/checkpoints)
7. If you want to get the art gallery workflow working, simply replace the "ID Base Model Loader from Hub" node to "ID Base Model Loader locally" node. Double click on an empty area on your workflow to start search. Type in "idbasemodelloader" and you'll see the two versions available. Select and local one and replace with the hub version. (you can't search by the actual node title as the metadata was not properly named)

That's all the gotchas I found. Good luck and have fun!

请问在 wangqixun/YamerMIX_v8 的文件放在哪个目录下

我在**国内的云服务器上使用ComfyUI-InstantID时，它会自动下载模型，但是因为文件5.4g，总是下到一半报错，我的浏览器可以下，请问下载完YamerMIX_v8内的所有文件还是部分文件，下完后放在哪里？

I get different results with active/enabled IPAdapter plus

Only two custom nodes are active:

Error occurred when executing Ipadapter_instantidLoader: 'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype'

Got the following error on executing the local workflow.

File "C:\AI\SD\ComfyUI\execution.py", line 155, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\AI\SD\ComfyUI\execution.py", line 85, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\AI\SD\ComfyUI\execution.py", line 78, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\AI\SD\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 190, in load_ip_adapter_instantid pipe.load_ip_adapter_instantid(face_adapter)
File "C:\AI\SD\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
File "C:\AI\SD\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 174, in set_image_proj_model self.image_proj_model = image_proj_model.to(self.device, dtype=self.dtype)
File "C:\AI\SD\StabilityMatrix\Data\Packages\ComfyUI\venv\lib\site-packages\diffusers\configuration_utils.py", line 137, in __getattr__ raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")

requests.exceptions.ReadTimeout: HTTPSConnectionPool(host='raw.githubusercontent.com', port=443): Read timed out. (read timeout=None)

Traceback (most recent call last):
File "F:\AIProject\ComfyUI_CMD\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI\custom_nodes\ComfyUI-InstantID\nodes.py", line 76, in sample
StableDiffusionXLPipeline.from_single_file(
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\diffusers\loaders\single_file.py", line 263, in from_single_file
pipe = download_from_original_stable_diffusion_ckpt(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py", line 1319, in download_from_original_stable_diffusion_ckpt
original_config_file = BytesIO(requests.get(config_url).content)
^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\requests\api.py", line 73, in get
return request("get", url, params=params, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\requests\api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\AIProject\ComfyUI_CMD\ComfyUI.ext\Lib\site-packages\requests\adapters.py", line 578, in send
raise ReadTimeout(e, request=request)
requests.exceptions.ReadTimeout: HTTPSConnectionPool(host='raw.githubusercontent.com', port=443): Read timed out. (read timeout=None)

What happened?

请问大神，AttributeError: 'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype' ，这个问题怎么解决？

invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}
got prompt
Prompt executor has been patched by Job Iterator!
The config attributes {'controlnet_list': ['controlnet', 'RPMultiControlNetModel'], 'requires_aesthetics_score': False} were passed to StableDiffusionXLInstantIDPipeline, but are not expected and will be ignored. Please verify your model_index.json configuration file.
Keyword arguments {'controlnet_list': ['controlnet', 'RPMultiControlNetModel'], 'requires_aesthetics_score': False, 'local_dir': './checkpoints'} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored.
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:01<00:00, 4.04it/s]
2024-01-24 15:06:06,114 - root - ERROR - !!! Exception during processing !!!
2024-01-24 15:06:06,116 - root - ERROR - Traceback (most recent call last):
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 190, in load_ip_adapter_instantid
pipe.load_ip_adapter_instantid(face_adapter)
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid
self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 174, in set_image_proj_model
self.image_proj_model = image_proj_model.to(self.device, dtype=self.dtype)
^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 137, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype'

Prompt executed in 12.06 seconds
got prompt
Prompt executor has been patched by Job Iterator!
2024-01-24 15:06:37,405 - root - ERROR - !!! Exception during processing !!!
2024-01-24 15:06:37,406 - root - ERROR - Traceback (most recent call last):
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 190, in load_ip_adapter_instantid
pipe.load_ip_adapter_instantid(face_adapter)
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid
self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
File "K:\software\ComfyU\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 174, in set_image_proj_model
self.image_proj_model = image_proj_model.to(self.device, dtype=self.dtype)
^^^^^^^^^^
File "K:\software\ComfyU\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 137, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype'

Prompt executed in 0.71 seconds

Error after InstantID Generation node

I get this error after the InstantID Generation node:

ERROR:root:!!! Exception during processing !!! ERROR:root:Traceback (most recent call last): File "H:\Stable-diffusion\ComfyUI\execution.py", line 155, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "H:\Stable-diffusion\ComfyUI\execution.py", line 85, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "H:\Stable-diffusion\ComfyUI\custom_nodes\ComfyUI-0246\utils.py", line 363, in new_func res_value = old_func(*final_args, **kwargs) File "H:\Stable-diffusion\ComfyUI\execution.py", line 78, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "H:\Stable-diffusion\ComfyUI\nodes.py", line 1415, in save_images full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0]) AttributeError: 'str' object has no attribute 'shape'

Does it work with SD1.5?

SD 1.5 or is it SDXL only?

can you PLEASE use ComfyUI_IPAdapter_plus instead of homebaked one ?

there's conflict with ComfyUI_IPAdapter_plus
https://github.com/cubiq/ComfyUI_IPAdapter_plus

renaming / reloading to ZhoInsightFaceLoader doesn't seem to work.

Some Mac (Apple Sillicon) issues

First of all, thanks for the swift work.

Couple of things I noticed on Mac:

• Installing "requirements.txt" gives the error: "Could not find a version that satisfies the requirement onnxruntime-gpu (from versions: none)" -> There is no onnxruntime-gpu for Mac (as it depends on CUDA)
• Using onnxruntime (non-gpu) instead, I get the following error: "RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'"

File "/Applications/ComfyUI/execution.py", line 155, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Applications/ComfyUI/execution.py", line 85, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Applications/ComfyUI/execution.py", line 78, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Applications/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 264, in generate_image output = pipe( ^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/Applications/ComfyUI/custom_nodes/ComfyUI-InstantID/pipeline_stable_diffusion_xl_instantid.py", line 489, in __call__ ) = self.encode_prompt( ^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py", line 381, in encode_prompt prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/models/clip/modeling_clip.py", line 816, in forward return self.text_model( ^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/models/clip/modeling_clip.py", line 725, in forward encoder_outputs = self.encoder( ^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/models/clip/modeling_clip.py", line 654, in forward layer_outputs = encoder_layer( ^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/transformers/models/clip/modeling_clip.py", line 382, in forward hidden_states = self.layer_norm1(hidden_states) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/modules/normalization.py", line 196, in forward return F.layer_norm( ^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/torch/nn/functional.py", line 2543, in layer_norm return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Invalid URL 'None': No scheme supplied. Mac M2

Hey everyone i'm doing my best to make it work but i'm stuck on something i keep getting this error when it comes to the "ID Base Model Loader Locally". I use the base model sdxl, did all the requirements needed but nothing.. help me please, thanks you

Here is the error from the terminal :

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "/Users/amibouzi/ComfyUI/execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/ComfyUI/execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/ComfyUI/execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 158, in load_model
pipe = StableDiffusionXLInstantIDPipeline.from_single_file(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/diffusers/loaders/single_file.py", line 263, in from_single_file
pipe = download_from_original_stable_diffusion_ckpt(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 1319, in download_from_original_stable_diffusion_ckpt
original_config_file = BytesIO(requests.get(original_config_file, verify=False).content)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/api.py", line 73, in get
return request("get", url, params=params, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/sessions.py", line 575, in request
prep = self.prepare_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/sessions.py", line 486, in prepare_request
p.prepare(
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/models.py", line 368, in prepare
self.prepare_url(url, params)
File "/Users/amibouzi/miniconda3/lib/python3.11/site-packages/requests/models.py", line 439, in prepare_url
raise MissingSchema(
requests.exceptions.MissingSchema: Invalid URL 'None': No scheme supplied. Perhaps you meant https://None?

Prompt executed in 0.12 seconds

生成速度有些慢 可以加上LCM吗

InstantID 的代码支持 LCM

无法加载工作流节点文件

如图，我使用comfyUI的load按钮，加载ComfyUI\custom_nodes\ComfyUI-InstantID\INSTANTID WORKFLOWS目录下的工作流文件，报错了，缺少这些节点

insightface加载还是不行

Prompt outputs failed validation
IDGenerationNode:

• Return type mismatch between linked nodes: insightface, INSIGHTFACE != INSIGHTFACEMODEL
• InstantID Generation节点上insightface连接load insightface后还是出现以上报错，求解决

waiting for u

兄弟，等你ready了说一下哈，InstantID那边就修改README了

windows下安装insightface 报错

python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-InstantID\requirements.txt
Building wheels for collected packages: insightface
Building wheel for insightface (pyproject.toml) ... error
error: subprocess-exited-with-error

× Building wheel for insightface (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [233 lines of output]
WARNING: pandoc not enabled

FaceAnalysis.__init__() got an unexpected keyword argument 'providers'

has anyone else seen this?

File "C:\SD\ComfyUI\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\SD\ComfyUI\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\SD\ComfyUI\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\SD\ComfyUI\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus\IPAdapterPlus.py", line 543, in load_insight_face
model = FaceAnalysis(name="buffalo_l", root=INSIGHTFACE_DIR, providers=[provider + 'ExecutionProvider',])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Queue size: 0
Extra options

填的那个相对路径到底是从哪里开始算的啊

要是写清楚就省事很多了 写绝对路径也找不到 写相对路径也找不到 主要是不知道从哪开始算

请问 'str' object has no attribute 'shape' 报错怎么解决？

Error occurred when executing PreviewImage:

'str' object has no attribute 'shape'

File "/home/bingal/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/bingal/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 "/home/bingal/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/bingal/ComfyUI/nodes.py", line 1359, in save_images
full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
^^^^^^^^^^^^^^^

After hours and hours of failing, finally got it worked! (some solutions)

I had same issues many had, I tried almost 2-3 hours yesterday with a working workflow but not getting any results but today this is what I did:

1. Deleted already installed ComfyUI-InstantID which didn't work
2. Updated comfyui via Manager (UPDATE ALL)
3. Installed ComfyUI-InstantID via comfyui-manager
4. downloaded diffusion_pytorch_model.safetensors with the config file and placed those inside custom_nodes/ComfyUI-InstantID/checkpoints/controlnet
   downloaded ip-adapter.bin and placed that inside custom_nodes/ComfyUI-InstantID/checkpoints/
5. went into custom_nodes/ComfyUI-InstantID folder, type CMD on the panel next to search bar(don't know what its called sorry), typed this pip install -r requirements.txt and ENTER of course
6. opened ComfyUI\custom_nodes\ComfyUI-InstantID\INSTANTID WORKFLOWS -> V2.0 InstantID_locally_pose_ref【Zho】.json
7. Filled instantID loader and controlNet loader with correct paths and... It worked!!!!

能不能实现官方那个用第二张图控制人物动作的功能

如果能实现，感激不尽~

报错 no file named diffusion_pytorch_model.bin

找不到文件

值填的 /data/yoke/ComfyUI/custom_nodes/ComfyUI-InstantID/checkpoints/ControlNetModel/

(venv) (py310) ➜  ControlNetModel git:(main) ✗ pwd                            
/data/yoke/ComfyUI/custom_nodes/ComfyUI-InstantID/checkpoints/ControlNetModel
(venv) (py310) ➜  ControlNetModel git:(main) ✗ ll
total 2.4G
-rw-rw-r-- 1 yoke yoke 1.4K Jan 24 23:26 config.json
-rw-rw-r-- 1 yoke yoke 2.4G Jan 22 16:51 diffusion_pytorch_model.safetensor

Error occurred when executing IDControlNetLoader:

Error no file named diffusion_pytorch_model.bin found in directory /data/yoke/ComfyUI/custom_nodes/ComfyUI-InstantID/checkpoints/ControlNetModel/.

File "/data/yoke/ComfyUI/execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/data/yoke/ComfyUI/execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/data/yoke/ComfyUI/execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/data/yoke/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 96, in load_idcontrolnet
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
File "/data/yoke/ComfyUI/venv/lib/python3.10/site-packages/diffusers/models/modeling_utils.py", line 769, in from_pretrained
model_file = _get_model_file(
File "/data/yoke/ComfyUI/venv/lib/python3.10/site-packages/diffusers/utils/hub_utils.py", line 284, in _get_model_file
raise EnvironmentError(

GR not defined with anime style pose image

I am on windows, just went through tricky installation process and was trying to use the local workflow with pose image.
However, I have been getting "GR not defined" error.
I was thinking it might be because my input is more in anime style, but I remember getting it work on the huggingface demo with anime style drawings so I wasn't sure what makes it not work here.

attached is my comfyui log:

能在Instant ID Generation中恢复自定义宽高的功能吗

感谢作者，现在默认生成1280*960大小的图，对显卡压力太大了，

Out Of Memory Error

Error occurred when executing IDGenerationNode:

Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 9.85 GiB
Requested : 640.00 MiB
Device limit : 12.00 GiB
Free (according to CUDA): 0 bytes
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB

I am getting the above error.
I'm using an RTX 3080 Ti 12GB.

Has anybody actulay got this to work ?

I'm at a stage where I think this is just a malicious prank breaking everybody's confyUI's

yaml.scanner.ScannerError: mapping values are not allowed here

InstantIDNode 节点报，使用dreamshaperXL10模型，或其它XL模型，都会报yaml.scanner.ScannerError: mapping values are not allowed here错误，麻烦看看什么问题

Error building insightface?

Having problems with the "insightface" dependency. The error implies I just needed to install some MS build tools but even after installing those from the URL indicated the error persists for me.

      copying insightface\thirdparty\face3d\mesh\cython\mesh_core_cython.pyx -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
      copying insightface\thirdparty\face3d\mesh\cython\setup.py -> build\lib.win-amd64-cpython-311\insightface\thirdparty\face3d\mesh\cython
      running build_ext
      building 'insightface.thirdparty.face3d.mesh.cython.mesh_core_cython' extension
      error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for insightface
Failed to build insightface
ERROR: Could not build wheels for insightface, which is required to install pyproject.toml-based projects```

No module named 'diffusers', but its installed?

I'm getting the error upon startup:
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1872, 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:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID_init.py", line 1, in
from .InstantIDNode import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 1, in
import diffusers
ModuleNotFoundError: No module named 'diffusers'

Cannot import D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID module for custom nodes: No module named 'diffusers'

Usually to fix this i would install diffusers via pip but I already have it installed (requirement already satisfied).

question about lora loading error

I tried loading lora, which gave me the following error:

Can not switch model

Once one model is used, switching to another model will cause this error

Error occurred when executing IDBaseModelLoader_local:Vith loal _iles_only set to Nlone，you mst first loally save the tolkenizer in the following path:'openai/clip-vit-large-patch14'

Error occurred when executing IDBaseModelLoader_local:Vith loal _iles_only set to Nlone，you mst first loally save the tolkenizer in the following path:'openai/clip-vit-large-patch14'

Prompt outputs failed validation IDGenerationNode: - Return type mismatch between linked nodes: insightface, INSIGHTFACE != INSIGHTFACEMODEL

This is a joke

after fixing my first error i now get this error:
Error occurred when executing Ipadapter_instantidLoader:

'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype'

File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_ezXY\autoCastPatch.py", line 299, in map_node_over_list
return _map_node_over_list(obj, input_data_all, func, allow_interrupt)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 191, in load_ip_adapter_instantid
pipe.load_ip_adapter_instantid(face_adapter)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid
self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 174, in set_image_proj_model
self.image_proj_model = image_proj_model.to(self.device, dtype=self.dtype)
File "D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\diffusers\configuration_utils.py", line 137, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=DESKTOP-J2QDS4A ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider.cc ; line=173 ; expr=cublasCreate(&cublas_handle_);

Error occurred when executing Ipadapter_instantidLoader:

Error occurred when executing Ipadapter_instantidLoader:

'StableDiffusionXLInstantIDPipeline' object has no attribute 'dtype'

File "C:\ComfyUI\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 191, in load_ip_adapter_instantid
pipe.load_ip_adapter_instantid(face_adapter)
File "C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid
self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
File "C:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 174, in set_image_proj_model
self.image_proj_model = image_proj_model.to(self.device, dtype=self.dtype)
^^^^^^^^^^
File "C:\ComfyUI\python_embeded\Lib\site-packages\diffusers\configuration_utils.py", line 137, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

Close

Return type mismatch between linked nodes: insightface, INSIGHTFACE != INSIGHTFACEMODEL

No errors or warnings during boot, all requirements satisfied and present.

Workflow doesn't even attempt to start. Hits the INSIGHTFACE loader and stops.

ERROR:root:Failed to validate prompt for output 12:
ERROR:root:* IDGenerationNode 15:
ERROR:root:  - Return type mismatch between linked nodes: insightface, INSIGHTFACE != INSIGHTFACEMODEL
ERROR:root:Output will be ignored
invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}}

suggestion to include workflow using this

https://github.com/civitai/civitai_comfy_nodes

FAIL : LoadLibrary failed with error 126

i have all requirements satisfied
how can i solve this, please?

got prompt
2024-01-26 04:27:18.9442572 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "Z:\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: Z:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
2024-01-26 04:27:19.3800489 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "Z:\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: Z:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
2024-01-26 04:27:19.4384249 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "Z:\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: Z:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
2024-01-26 04:27:19.5679445 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "Z:\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: Z:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2\glintr100.onnx recognition ['None', 3, 112, 112] 127.5 127.5
2024-01-26 04:27:20.0757093 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "Z:\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
find model: Z:\ComfyUI\ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2\scrfd_10g_bnkps.onnx detection [1, 3, '?', '?'] 127.5 128.0
set det-size: (640, 640)
Z:\ComfyUI\python_embeded\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.

comfyUI manager: import failed

Im on windows, trying to install it via comfy manager and followed the instruction to download files and place in appropraite folder, but keep getting "import failed" error

my CMD log on bootup:

C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --preview-method auto
** ComfyUI startup time: 2024-01-24 12:02:39.111625
** Platform: Windows
** Python version: 3.11.6 (tags/v3.11.6:8b6ee5b, Oct 2 2023, 14:57:12) [MSC v.1935 64 bit (AMD64)]
** Python executable: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\python_embeded\python.exe
** Log path: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\comfyui.log

Prestartup times for custom nodes:
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Marigold
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 16376 MB, total RAM 32540 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 : cudaMallocAsync
VAE dtype: torch.bfloat16
Using pytorch cross attention
[Allor]: 0 nodes were overridden.
[Allor]: 12 modules were enabled.
[Allor]: 98 nodes were loaded.

Loading: ComfyUI-Impact-Pack (V4.56)

Loading: ComfyUI-Impact-Pack (Subpack: V0.4)

[Impact Pack] Wildcards loading done.
Traceback (most recent call last):
File "C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1872, 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 "C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID_init.py", line 1, in
from .InstantIDNode import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
File "C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 14, in
from insightface.app import FaceAnalysis
ModuleNotFoundError: No module named 'insightface'

Cannot import C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID module for custom nodes: No module named 'insightface'

Loading: ComfyUI-Manager (V1.17.1)

ComfyUI Revision: 1928 [3762e676] | Released on '2024-01-23'

FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.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/model-list.json

Comfyroll Custom Nodes v1.55 : 165 Nodes Loaded

[comfyui_controlnet_aux] | INFO -> Using ckpts path: C:\Users\ssm05\Desktop\myFolder\Art\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']
[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/custom-node-list.json
DWPose: Onnxruntime with acceleration providers detected
FizzleDorf Custom Nodes: Loaded
Requirement already satisfied: segment_anything in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from -r requirements.txt (line 1)) (1.0)
Requirement already satisfied: timm in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from -r requirements.txt (line 2)) (0.9.12)
Requirement already satisfied: addict in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from -r requirements.txt (line 3)) (2.4.0)
Requirement already satisfied: yapf in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from -r requirements.txt (line 4)) (0.40.2)
Requirement already satisfied: torch>=1.7 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from timm->-r requirements.txt (line 2)) (2.1.2+cu121)
Requirement already satisfied: torchvision in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from timm->-r requirements.txt (line 2)) (0.16.2+cu121)
Requirement already satisfied: pyyaml in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from timm->-r requirements.txt (line 2)) (6.0.1)
Requirement already satisfied: huggingface-hub in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from timm->-r requirements.txt (line 2)) (0.19.4)
Requirement already satisfied: safetensors in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from timm->-r requirements.txt (line 2)) (0.4.1)
Requirement already satisfied: importlib-metadata>=6.6.0 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from yapf->-r requirements.txt (line 4)) (7.0.1)
Requirement already satisfied: platformdirs>=3.5.1 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from yapf->-r requirements.txt (line 4)) (4.1.0)
Requirement already satisfied: tomli>=2.0.1 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from yapf->-r requirements.txt (line 4)) (2.0.1)
Requirement already satisfied: zipp>=0.5 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from importlib-metadata>=6.6.0->yapf->-r requirements.txt (line 4)) (3.17.0)
Requirement already satisfied: filelock in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (3.13.1)
Requirement already satisfied: typing-extensions in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (4.9.0)
Requirement already satisfied: sympy in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (1.12)
Requirement already satisfied: networkx in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (3.2.1)
Requirement already satisfied: jinja2 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (3.1.2)
Requirement already satisfied: fsspec in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm->-r requirements.txt (line 2)) (2023.12.2)
Requirement already satisfied: requests in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm->-r requirements.txt (line 2)) (2.31.0)
Requirement already satisfied: tqdm>=4.42.1 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm->-r requirements.txt (line 2)) (4.66.1)
Requirement already satisfied: packaging>=20.9 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm->-r requirements.txt (line 2)) (23.2)
Requirement already satisfied: numpy in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm->-r requirements.txt (line 2)) (1.26.2)
Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm->-r requirements.txt (line 2)) (9.5.0)
Requirement already satisfied: colorama in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from tqdm>=4.42.1->huggingface-hub->timm->-r requirements.txt (line 2)) (0.4.6)
Requirement already satisfied: MarkupSafe>=2.0 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch>=1.7->timm->-r requirements.txt (line 2)) (2.1.3)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm->-r requirements.txt (line 2)) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm->-r requirements.txt (line 2)) (3.6)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm->-r requirements.txt (line 2)) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm->-r requirements.txt (line 2)) (2023.11.17)
Requirement already satisfied: mpmath>=0.19 in c:\users\ssm05\desktop\myfolder\art\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch>=1.7->timm->-r requirements.txt (line 2)) (1.3.0)
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: ffmpeg_bin_path is not set in C:\Users\ssm05\Desktop\myFolder\Art\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 198 nodes successfully.

    "Art is not a thing; it is a way." - Elbert Hubbard

Import times for custom nodes:
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\clip_text_encode_split.py
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\canvas_tab
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-portrait-master-zh-cn
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Image-Selector
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\cg-use-everywhere
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Logic
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\masquerade-nodes-comfyui
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\stability-ComfyUI-nodes
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-post-processing-nodes
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-yanc
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WD14-Tagger
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Text_Image-Composite
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\images-grid-comfy-plugin
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-PhotoMaker
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Marigold
0.0 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
0.0 seconds (IMPORT FAILED): C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID
0.1 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Moore-AnimateAnyone
0.1 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\LCM_Inpaint-Outpaint_Comfy
0.1 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
0.1 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
0.1 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_FizzNodes
0.2 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Gemini
0.2 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux
0.3 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
0.3 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\clipseg.py
0.4 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Allor
0.9 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui
1.7 seconds: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_segment_anything

Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: C:\Users\ssm05\Desktop\myFolder\Art\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json

大神 这问题怎么解决呀

Error occurred when executing IDControlNetLoader:

It looks like the config file at 'E:\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID-main\checkpoints\controlnet\controlnet_checkpoint.ckpt' is not a valid JSON file.

是不是只能在周更版本上使用

Cannot import D:\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID module for custom nodes: cannot import name 'PipelineImageInput' from 'diffusers.image_processor' (D:\AI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\diffusers\image_processor.py)
试着装了下依赖，很多老版本的。

Error Trying to use workflow... If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

after intall and trying to use 1 of your v2 workflows i get this error...

raise OSError(
OSError: Unable to load weights from checkpoint file for 'D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\checkpoints\controlnet\ControlNetModel_config.json' at 'D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID\checkpoints\controlnet\ControlNetModel_config.json'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

mat1 and mat2 shapes cannot be multiplied (32x2048 and 768x320)

I suspect it's the controlnet / sd vs sdxl
what config / implementation is it looking for?

UPDATE
cloning this - hopefully works
https://huggingface.co/thibaud/controlnet-openpose-sdxl-1.0

tokenizer_config.json: 100%|███████████████████████████| 904/904 [00:00<00:00, 2.56MB/s]
vocab.json: 100%|█████████████████████████████████████| 862k/862k [00:01<00:00, 494kB/s]
merges.txt: 100%|█████████████████████████████████████| 525k/525k [00:01<00:00, 508kB/s]
special_tokens_map.json: 100%|█████████████████████████| 389/389 [00:00<00:00, 1.08MB/s]
tokenizer.json: 100%|███████████████████████████████| 2.22M/2.22M [00:04<00:00, 534kB/s]
config.json: 100%|█████████████████████████████████| 4.88k/4.88k [00:00<00:00, 12.1MB/s]
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "/media/2TB/ComfyUI/execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 190, in load_ip_adapter_instantid
    pipe.load_ip_adapter_instantid(face_adapter)
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/pipeline_stable_diffusion_xl_instantid.py", line 156, in load_ip_adapter_instantid
    self.set_image_proj_model(model_ckpt, image_emb_dim, num_tokens)
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/pipeline_stable_diffusion_xl_instantid.py", line 175, in set_image_proj_model
    state_dict = torch.load(model_ckpt, map_location="cpu")
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/serialization.py", line 997, in load
    with _open_file_like(f, 'rb') as opened_file:
         ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/serialization.py", line 444, in _open_file_like
    return _open_file(name_or_buffer, mode)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/serialization.py", line 425, in __init__
    super().__init__(open(name, mode))
                     ^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: '/content/ComfyUI/models/checkpoints/ip-adapter.bin'

Prompt executed in 16.53 seconds
got prompt
  0%|                                                            | 0/50 [00:00<?, ?it/s]
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "/media/2TB/ComfyUI/execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 264, in generate_image
    output = pipe(
             ^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/pipeline_stable_diffusion_xl_instantid.py", line 669, in __call__
    down_block_res_samples, mid_block_res_sample = self.controlnet(
                                                   ^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/controlnet.py", line 800, in forward
    sample, res_samples = downsample_block(
                          ^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/unet_2d_blocks.py", line 1160, in forward
    hidden_states = attn(
                    ^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/transformer_2d.py", line 392, in forward
    hidden_states = block(
                    ^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention.py", line 366, in forward
    attn_output = self.attn2(
                  ^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention_processor.py", line 527, in forward
    return self.processor(
           ^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention_processor.py", line 1246, in __call__
    key = attn.to_k(encoder_hidden_states, *args)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 116, in forward
    return F.linear(input, self.weight, self.bias)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (32x2048 and 768x320)

Prompt executed in 1.89 seconds
FETCH DATA from: /media/2TB/ComfyUI/custom_nodes/ComfyUI-Manager/extension-node-map.json
got prompt
  0%|                                                            | 0/50 [00:00<?, ?it/s]
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "/media/2TB/ComfyUI/execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/InstantIDNode.py", line 264, in generate_image
    output = pipe(
             ^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/media/2TB/ComfyUI/custom_nodes/ComfyUI-InstantID/pipeline_stable_diffusion_xl_instantid.py", line 669, in __call__
    down_block_res_samples, mid_block_res_sample = self.controlnet(
                                                   ^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/controlnet.py", line 800, in forward
    sample, res_samples = downsample_block(
                          ^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/unet_2d_blocks.py", line 1160, in forward
    hidden_states = attn(
                    ^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/transformer_2d.py", line 392, in forward
    hidden_states = block(
                    ^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention.py", line 366, in forward
    attn_output = self.attn2(
                  ^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention_processor.py", line 527, in forward
    return self.processor(
           ^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/diffusers/models/attention_processor.py", line 1246, in __call__
    key = attn.to_k(encoder_hidden_states, *args)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/oem/miniconda3/envs/comfyui/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 116, in forward
    return F.linear(input, self.weight, self.bias)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (32x2048 and 768x320)

Prompt executed in 0.15 seconds

Any sample workflow?

Hello, can you please add some workflows like you did for PhotoMaker? that would be awesome!
Thank you a lot

StableDiffusionXLControlNetPipeline.__init__() got an unexpected keyword argument 'safety_checker'

Got this error using the workflow: instant-id.json

Used the local workflow sample and changed the path to controlnet models to:

custom_nodes/ComfyUI-InstantID/checkpoints/controlnet

UI error:

Error occurred when executing IDBaseModelLoader_local:

StableDiffusionXLControlNetPipeline.__init__() got an unexpected keyword argument 'safety_checker'


File "E:\code\stable-difusion\ComfyUI2\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "E:\code\stable-difusion\ComfyUI2\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "E:\code\stable-difusion\ComfyUI2\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "E:\code\stable-difusion\ComfyUI2\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 157, in load_model
pipe = StableDiffusionXLInstantIDPipeline.from_single_file(
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn
return fn(*args, **kwargs)
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\loaders\single_file.py", line 263, in from_single_file
pipe = download_from_original_stable_diffusion_ckpt(
File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py", line 1676, in download_from_original_stable_diffusion_ckpt
pipe = pipeline_class(

Terminal error:

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "E:\code\stable-difusion\ComfyUI2\execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "E:\code\stable-difusion\ComfyUI2\execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "E:\code\stable-difusion\ComfyUI2\execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "E:\code\stable-difusion\ComfyUI2\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 157, in load_model    pipe = StableDiffusionXLInstantIDPipeline.from_single_file(
  File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\huggingface_hub\utils\_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
  File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\loaders\single_file.py", line 263, in from_single_file
    pipe = download_from_original_stable_diffusion_ckpt(
  File "C:\Users\fcmen\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py", line 1676, in download_from_original_stable_diffusion_ckpt
    pipe = pipeline_class(
TypeError: StableDiffusionXLControlNetPipeline.__init__() got an unexpected keyword argument 'safety_checker'     

"LayerNormKernelImpl" not implemented for 'Half'

Error occurred when executing IDGenerationNode:

"LayerNormKernelImpl" not implemented for 'Half'

File "D:\Ai\SD-N\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI\custom_nodes\ComfyUI-InstantID\InstantIDNode.py", line 288, in id_generate_image
output = pipe(
^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI\custom_nodes\ComfyUI-InstantID\pipeline_stable_diffusion_xl_instantid.py", line 489, in call
) = self.encode_prompt(
^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\diffusers\pipelines\controlnet\pipeline_controlnet_sd_xl.py", line 381, in encode_prompt
prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\transformers\models\clip\modeling_clip.py", line 798, in forward
return self.text_model(
^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\transformers\models\clip\modeling_clip.py", line 703, in forward
encoder_outputs = self.encoder(
^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\transformers\models\clip\modeling_clip.py", line 630, in forward
layer_outputs = encoder_layer(
^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\transformers\models\clip\modeling_clip.py", line 371, in forward
hidden_states = self.layer_norm1(hidden_states)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\modules\normalization.py", line 190, in forward
return F.layer_norm(
^^^^^^^^^^^^^
File "D:\Ai\SD-N\ComfyUI.ext\Lib\site-packages\torch\nn\functional.py", line 2515, in layer_norm
return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^