Comfyui InstantID 换脸色图一键整合包

a931386

35099500 发表于 2025-11-16 15:07
打开是英文版，不会转中文，小白一枚

35099500

a931386 发表于 2025-11-16 21:16

谢谢大佬

35099500

rror occurred when executing PreviewImage:

'NoneType' object is not subscriptable

File "E:\Comfyui InstantID\ComfyUI_windows_InstantID\ComfyUI\execution.py", line 317, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Comfyui InstantID\ComfyUI_windows_InstantID\ComfyUI\execution.py", line 192, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Comfyui InstantID\ComfyUI_windows_InstantID\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "E:\Comfyui InstantID\ComfyUI_windows_InstantID\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Comfyui InstantID\ComfyUI_windows_InstantID\ComfyUI\nodes.py", line 1494, 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])

35099500

35099500 发表于 2025-11-17 17:00
rror occurred when executing PreviewImage:

'NoneType' object is not subscriptable

这个是啥意思呀 楼主大大

a931386

35099500 发表于 2025-11-17 17:01
这个是啥意思呀 楼主大大

貌似找不到參考圖片,確認一下本地的資料夾路徑有沒有填入

35099500

大佬能不能出一个小显存能玩的，您发的这个直接卡不动了~3060 12G小显存眼巴巴

aihualp

您好大佬，请问为什么我只要到这一步就会崩溃，用的是整个包，配置4060ti - 16G显存 - 32G内存：

Requested to load SDXL
Requested to load ControlNet
Requested to load ControlNet
Loading 3 new models
loaded completely 0.0 2386.120147705078 True
loaded completely 0.0 2386.120147705078 True
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [02:00<00:00,  8.02s/it]
Requested to load AutoencoderKL
Loading 1 new model
loaded completely 0.0 159.55708122253418 True
model weight dtype torch.float16, manual cast: None
model_type EPS
Using pytorch attention in VAE
Using pytorch attention in VAE
Requested to load SDXLClipModel
Loading 1 new model
loaded completely 0.0 1560.802734375 True
loaded straight to GPU
Requested to load SDXL
Loading 1 new model
loaded completely 0.0 4897.0483474731445 True
Requested to load SDXLRefinerClipModel
Loading 1 new model
loaded completely 0.0 1324.95849609375 True
Loading weights to:  cuda:0
Diffusion using fp16
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Attempting to load SDXL model from node inputs
Requested to load SDXL
Loading 1 new model

D:\LP-aihua\InstantID一LP\ComfyUI_windows_InstantID>pause
请按任意键继续. . .

别看我我不在

大佬，能批量换脸吗？