Old Photo Restoration XL
5.0
1 reviewsDescription
Node Diagram
Discussion
非常好用
- BOPBTL_ScratchMask 🔗
- BOPBTL_RestoreOldPhotos 🔗
- BOPBTL_LoadScratchMaskModel 🔗
- BOPBTL_LoadRestoreOldPhotosModel 🔗
swears at these nodes, what should I do? even though they are installed
You may not have dlib installed correctly.
I have same problem, install microsoft visual studio, cmake and dlib. Make it PATH, tested at cmd and installed correctly. But the BOPBTL nodes still in red.
I am waiting someone make youtube tutorial:)
metoo,但我用github中提到的第二种方法安装成功了:你可以在这个地方找到文件,并尝试安装。 https://github.com/eddiehe99/dlib-whl
Does anyone have a video tutorial? I have the same problem
劳烦问下,这里Ollama推荐运行的是什么模型?
大佬,以bopbtl\开头并以.pt 和 .pth结尾的存储模型参数和状态的文件,例如bopbtl\mapping_Patch_Attention\latest_net_mapping_net.pth、bopbtl\detection\FT_Epoch_latest.pt等。在哪里可以获取到。
在那个github仓库的中有 就是那个custom中的back old pic to life这个插件
这个怎么解决?
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "I:\ComfyUI-aki-v1.3\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "I:\ComfyUI-aki-v1.3\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "I:\ComfyUI-aki-v1.3\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "I:\ComfyUI-aki-v1.3\custom_nodes\ComfyUi-Ollama-YN\CompfyuiOllama.py", line 81, in ollama_vision
response = client.generate(model=model, prompt=query, keep_alive=keep_alive, options=options, images=images_b64)
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\ollama\_client.py", line 162, in generate
return self._request_stream(
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\ollama\_client.py", line 98, in _request_stream
return self._stream(*args, **kwargs) if stream else self._request(*args, **kwargs).json()
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\ollama\_client.py", line 69, in _request
response = self._client.request(method, url, **kwargs)
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_client.py", line 827, in request
return self.send(request, auth=auth, follow_redirects=follow_redirects)
File "<enhanced_experience vendors.sentry_sdk.integrations.httpx>", line 84, in send
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_client.py", line 914, in send
response = self._send_handling_auth(
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_client.py", line 1015, in _send_single_request
response = transport.handle_request(request)
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_transports\default.py", line 232, in handle_request
with map_httpcore_exceptions():
File "I:\ComfyUI-aki-v1.3\python\lib\contextlib.py", line 153, in __exit__
self.gen.throw(typ, value, traceback)
File "I:\ComfyUI-aki-v1.3\python\lib\site-packages\httpx\_transports\default.py", line 86, in map_httpcore_exceptions
raise mapped_exc(message) from exc httpx.ConnectError: [WinError 10061] 由于目标计算机积极拒绝,无法连接。
How My Ollama vision node works. I have installed Ollama app, but i have no clue what should i do to make the node work
When i followed github to install ComfyUI-BOPBTL, theres instruction i didnt understand " Set device_ids as a comma separated list of device ids (i.e. 0 or 1,2). Use -1 for cpu."
Anyone know how to set 'device_ids"?
Load Restore Old Photos Model中的mapping_net
Load Scratch Mask Model中的scratch_model
这两个加载的是什么模型啊~~~
abnormal result...
why?
Bringing-Old-Photos-Back-to-Life is not working properly. It may be that the model is not set correctly.
default workflow same https://github.com/cdb-boop/ComfyUI-Bringing-Old-Photos-Back-to-Life/issues/13
(Edited)用本地部署多模态羊驼来生成提示词,约束生图的质量,可以说实棋高一着了,有没有推荐的亚洲人底膜?用你这个生出来的图全是洋人面相~
ComfyUI-Bringing-Old-Photos-Back-to-Life
这个插件一定要python 3.11版本吗 你的python版本是什么
python 3.10, dlib using 19.24.2, installed dlib using wheel library: https://github.com/eddiehe99/dlib-whl/blob/main/dlib-19.24.2-cp310-cp310-win_amd64.whl
Error occurred when executing DepthAnythingV2Preprocessor: No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 1925, 12, 64) (torch.float32) key : shape=(1, 1925, 12, 64) (torch.float32) value : shape=(1, 1925, 12, 64) (torch.float32) attn_bias :
p : 0.0
`cutlassF` is not supported because:
xFormers wasn't build with CUDA support
Operator wasn't built - see `python -m xformers.info` for more info
`flshattF` is not supported because:
xFormers wasn't build with CUDA support
dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})
Operator wasn't built - see `python -m xformers.info` for more info
`tritonflashattF` is not supported because:
xFormers wasn't build with CUDA support
dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})
Operator wasn't built - see `python -m xformers.info` for more info
triton is not available
requires A100 GPU
`smallkF` is not supported because:
xFormers wasn't build with CUDA support
max(query.shape[-1] != value.shape[-1]) > 32
Operator wasn't built - see `python -m xformers.info` for more info
unsupported embed per head: 64
File "D:\comfyui\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\comfyui\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\comfyui\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\depth_anything_v2.py", line 20, in execute
out = common_annotator_call(model, image, resolution=resolution, max_depth=1)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\utils.py", line 85, in common_annotator_call
np_result = model(np_image, output_type="np", detect_resolution=detect_resolution, **kwargs)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\__init__.py", line 44, in __call__
depth = self.model.infer_image(cv2.cvtColor(input_image, cv2.COLOR_RGB2BGR), input_size=518, max_depth=max_depth)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dpt.py", line 189, in infer_image
depth = self.forward(image, max_depth)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dpt.py", line 179, in forward
features = self.pretrained.get_intermediate_layers(x, self.intermediate_layer_idx[self.encoder], return_class_token=True)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2.py", line 308, in get_intermediate_layers
outputs = self._get_intermediate_layers_not_chunked(x, n)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2.py", line 277, in _get_intermediate_layers_not_chunked
x = blk(x)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2_layers\block.py", line 247, in forward
return super().forward(x_or_x_list)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2_layers\block.py", line 105, in forward
x = x + attn_residual_func(x)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2_layers\block.py", line 84, in attn_residual_func
return self.ls1(self.attn(self.norm1(x)))
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "D:\comfyui\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\depth_anything_v2\dinov2_layers\attention.py", line 76, in forward
x = memory_efficient_attention(q, k, v, attn_bias=attn_bias)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\xformers\ops\fmha\__init__.py", line 192, in memory_efficient_attention
.. code-block:: python
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\xformers\ops\fmha\__init__.py", line 290, in _memory_efficient_attention
def memory_efficient_attention_forward(
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\xformers\ops\fmha\__init__.py", line 306, in _memory_efficient_attention_forward
query=query,
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\xformers\ops\fmha\dispatch.py", line 104, in _dispatch_fw
priority_list_ops.remove(flash.FwOp)
File "C:\tools\Miniconda3\envs\comflowy\lib\site-packages\xformers\ops\fmha\dispatch.py", line 79, in _run_priority_list
if not mqa_or_gqa:
这个怎么解决,我是windows环境,搞了一天了
我这里直接下载的也是缺少三个节点,可以再更新一下吗
Im running on dlib 19.24.2 (using library wheel) and it is fine as 19.24.1 always installed with failure, I dont know why.
I notice that there are two Ollama models, but I can only run one at once. Can I know how to run 2 at once in the system? Or halfway in the generations, run the second model?
请问这是什么问题?
Mapping: You are using multi-scale patch attention, conv combine + mask input
!!! Exception during processing !!! unpickling stack underflow
Traceback (most recent call last):
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\Global\models\base_model.py", line 98, in load_network_from_path
network.load_state_dict(torch.load(save_path))
^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 86, in torch_load
return _torch_load(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 86, in torch_load
return _torch_load(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1040, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1262, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
_pickle.UnpicklingError: unpickling stack underflow
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "F:\shirley\Program\ComfyUI_windows_portable\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 "F:\shirley\Program\ComfyUI_windows_portable\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 "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\nodes.py", line 222, in run
return BOPBTL_LoadRestoreOldPhotosModel.load_models(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\nodes.py", line 209, in load_models
model = Restorer.load_model(opt)
^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\Global\test.py", line 110, in load_model
model.initialize(opt)
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\Global\models\mapping_model.py", line 141, in initialize
self.load_network(self.netG_A, "G", opt.use_vae_which_epoch, opt.load_pretrainA, test_path=opt.test_vae_a)
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\Global\models\base_model.py", line 76, in load_network
BaseModel.load_network_from_path(network, test_path)
File "F:\shirley\Program\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bringing-Old-Photos-Back-to-Life-master\Global\models\base_model.py", line 101, in load_network_from_path
pretrained_dict = torch.load(save_path)
^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 86, in torch_load
return _torch_load(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 86, in torch_load
return _torch_load(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1040, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\shirley\Program\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1262, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
_pickle.UnpicklingError: unpickling stack underflow
When loading the graph, the following node types were not found:
- DisplayText_Zho
- ConcatText_Zho
- easy cleanGpuUsed
- ReActorFaceSwap
- Automatic CFG
- BOPBTL_ScratchMask
- BOPBTL_RestoreOldPhotos
- BOPBTL_LoadScratchMaskModel
- ComfyUI_Image_Round__ImageRoundAdvanced
- BOPBTL_LoadRestoreOldPhotosModel
- ImageScaleToMegapixels
- ComfyUI_Image_Round__ImageCropAdvanced
- OllamaVision
- OllamaGenerate
- DepthAnythingV2Preprocessor
Nodes that have failed to load will show as red on the graph.
大佬,你好。一些有破损的老照片,跑完没法自动补全生成图像,是什么原因。是我模型选择的原因吗
要具体看是卡在哪个节点了,报错信息是什么
没有报错,就是说照片有破损的部位,他生成后不会识别破损的部位,没法补全破损的那块,而是会自己生成其他的东西。
安装(IMPORT FAILED) ComfyUI Bringing Old Photos Back to Life
1、打开工作流报错:
Missing Node Types
When loading the graph, the following node types were not found
BOPBTL_ScratchMask
BOPBTL_RestoreOIdPhotos
BOPBTL_LoadScratchMaskModel
BOPBTL_LoadRestoreOldPhotosModel
2、插件安装后报错:(IMPORT FAILED) ComfyUI Bringing Old Photos Back to Life
3、运行工作流报:Cannot execute because a node is missing the class_type property.: Node ID '#85'
请问大佬,怎么解决呢?谢谢
你好需要设置什么关键词吗。我跑完还是黑白照片,没有上色,只是比原来的照片清晰了
Node Details
Primitive Nodes (3)
DepthAnythingV2Preprocessor (1)
DownloadAndLoadFlorence2Model (1)
Florence2Run (1)
Custom Nodes (29)
ComfyUI
- ControlNetLoader (3)
- CLIPTextEncode (2)
- PreviewImage (3)
- VAEEncode (1)
- ControlNetApplyAdvanced (3)
- VAEDecode (1)
- CheckpointLoaderSimple (1)
- KSampler (1)
- SaveImage (1)
- LoadImage (1)
- BOPBTL_ScratchMask (1)
- BOPBTL_RestoreOldPhotos (1)
- BOPBTL_LoadScratchMaskModel (1)
- BOPBTL_LoadRestoreOldPhotosModel (1)
- easy cleanGpuUsed (1)
- DWPreprocessor (1)
- ImageScaleToMegapixels (1)
- Automatic CFG (1)
- DisplayText_Zho (1)
- ComfyUI_Image_Round__ImageRoundAdvanced (1)
- ComfyUI_Image_Round__ImageCropAdvanced (1)
- ReActorFaceSwap (1)
Model Details
Checkpoints (1)
sdxl\juggernautXL_v9Rdphoto2Lightning.safetensors
LoRAs (0)