search

novitalabs / sd-webui-cleaner

An extension for stable-diffusion-webui to remove any object.
MIT License
228 stars 17 forks source link

[Bug] #1

Open HansonChan opened 9 months ago

HansonChan commented 9 months ago

Traceback (most recent call last): File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1431, in process_api result = await self.call_function( File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1103, in call_function prediction = await anyio.to_thread.run_sync( File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run result = context.run(func, args) File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/utils.py", line 707, in wrapper response = f(args, **kwargs) File "/Users/Shuai/AI/stable-diffusion-webui/extensions/sd-webui-cleaner/scripts/lama.py", line 13, in clean_object_init_img_with_mask return clean_object(init_img_with_mask['image'],init_img_with_mask['mask']) File "/Users/Shuai/AI/stable-diffusion-webui/extensions/sd-webui-cleaner/scripts/lama.py", line 18, in clean_object Lama = LiteLama2() File "/Users/Shuai/AI/stable-diffusion-webui/extensions/sd-webui-cleaner/scripts/lama.py", line 62, in init self.load() File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/litelama/litelama.py", line 19, in load self._model = load_model(config_path=self._config_path, checkpoint_path=self._checkpoint_path, use_safetensors=use_safetensors) File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/litelama/model.py", line 60, in load_model with safetensors.safe_open(checkpoint_path, framework="pt", device="cpu") as f: safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

It seems haven't got the right device type?

ka1tte commented 9 months ago

@HansonChan Are you using a Mac?

HansonChan commented 9 months ago

@ka1tte Yes. Mac with M2. I try to move the models to "mps", but aother error appeared.

Traceback (most recent call last): File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1434, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1335, in postprocess_data prediction_value = block.postprocess(prediction_value) File "/Users/Shuai/AI/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/components/gallery.py", line 205, in postprocess raise ValueError(f"Cannot process type as image: {type(img)}") ValueError: Cannot process type as image: <class 'NoneType'>

ka1tte commented 9 months ago

@HansonChan I provide a parameter that can use the CPU for inference. You can configure it through the setting page or api.

{
    "cleaner_use_gpu": true
}
ka1tte commented 9 months ago

In my Mac, It works normally.

LinTevis commented 9 months ago

I solved my issue by downloading the model at https://huggingface.co/smartywu/big-lama and replacing it.

zopi4k commented 9 months ago

I have same error on windows : 

Traceback (most recent call last):
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
    result = await self.call_function(
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "D:\stable-diffusion-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "D:\stable-diffusion-webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "D:\stable-diffusion-webui\extensions\sd-webui-cleaner\scripts\lama.py", line 14, in clean_object_init_img_with_mask
    return clean_object(init_img_with_mask['image'],init_img_with_mask['mask'])
  File "D:\stable-diffusion-webui\extensions\sd-webui-cleaner\scripts\lama.py", line 19, in clean_object
    Lama = LiteLama2()
  File "D:\stable-diffusion-webui\extensions\sd-webui-cleaner\scripts\lama.py", line 69, in __init__
    self.load(location="cpu")
  File "D:\stable-diffusion-webui\venv\lib\site-packages\litelama\litelama.py", line 19, in load
    self._model = load_model(config_path=self._config_path, checkpoint_path=self._checkpoint_path, use_safetensors=use_safetensors)
  File "D:\stable-diffusion-webui\venv\lib\site-packages\litelama\model.py", line 60, in load_model
    with safetensors.safe_open(checkpoint_path, framework="pt", device="cpu") as f:
safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

And I have change the model like Keny25 : https://huggingface.co/anyisalin/big-lama/tree/main

image

It's work well.

zopi4k commented 9 months ago

But the error for me is now in "Clean Up Upload" ...

image

Traceback (most recent call last):
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1434, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1335, in postprocess_data
    prediction_value = block.postprocess(prediction_value)
  File "D:\stable-diffusion-webui\venv\lib\site-packages\gradio\components\gallery.py", line 205, in postprocess
    raise ValueError(f"Cannot process type as image: {type(img)}")
ValueError: Cannot process type as image: <class 'NoneType'>
ka1tte commented 9 months ago

@zopi4k Do you have a GPU? I have only tested it on Linux and Mac, and I have not run it on Windows.

zopi4k commented 9 months ago

Yes Ka1tte ^^) I have a NVidia GeForce RTX 3070 Laptop GPU. if you change just the Model it's possible to work.

And Thx for this extention ! I've been looking for one since February xDD

LinTevis commented 9 months ago

@zopi4k I was able to replicate those errors when trying to use the extention and generating an image, otherwise it's working as intended

Rkkss commented 8 months ago

@zopi4k I was able to replicate those errors when trying to use the extention and generating an image, otherwise it's working as intended

same error. How do we fix it?

derFleder commented 7 months ago

I also encounter the error: Error while deserializing header: HeaderTooLarge

It works pretty well on Mac OSX, but on my Windows Machine I encounter that error. I also tried replacing the safetensor files. It did not work.

Is this project still maintained?

xiaoshun111 commented 6 months ago

*** Error loading script: clean_up_tab.py Traceback (most recent call last): File "D:\ Stable Diffusion\sd-webui-aki-v4\modules\scripts.py", line 319, in load_scripts script_module = script_loading.load_module(scriptfile.path) File "D:\ Stable Diffusion\sd-webui-aki-v4\modules\script_loading.py", line 10, in load_module module_spec.loader.exec_module(module) File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "D:\AStable Diffusion\sd-webui-aki-v4\extensions\sd-webui-cleaner\scripts\clean_up_tab.py", line 7, in from modules.ui_components import ToolButton, ResizeHandleRow ImportError: cannot import name 'ResizeHandleRow' from 'modules.ui_components' (D:\ Stable Diffusion\sd-webui-aki-v4\modules\ui_components.py)

How do you fix this error

tomchify commented 3 months ago

A possibly helpful tip: the mask and image must be the same size for the API to work. Remember to mask.resize(image.size) before b64 encoding the images.

gitesend commented 3 months ago

{ "cleaner_use_gpu": true } @ka1tte May I ask which file this parameter is added to？My Mac is running with an error message

ValueError(f"Cannot process type as image: {type(img)}") ValueError: Cannot process type as image: <class 'NoneType'>

douyan2662 commented 3 months ago

你好，我的mac也出现了同样的问题 Traceback (most recent call last): File "/Users/apple/Documents/AI/SD/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/Users/apple/Documents/AI/SD/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1434, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "/Users/apple/Documents/AI/SD/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1335, in postprocess_data prediction_value = block.postprocess(prediction_value) File "/Users/apple/Documents/AI/SD/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/components/gallery.py", line 205, in postprocess raise ValueError(f"Cannot process type as image: {type(img)}") ValueError: Cannot process type as image: <class 'NoneType'> 请问如何解决，谢谢！