graemeniedermayer / clothseg Goto Github PK

This is a wrapper of rem_bg for auto1111's stable diffusion gui. It can do clothing segmentation, background removal, and background masking.

Python 100.00%

clothseg's People

Contributors

Stargazers

Watchers

Forkers

sdbds zcloud2014 vorstcavry jinwook-shim

clothseg's Issues

Error loading script: remove_bg.py in latest sd webui?

Hi @graemeniedermayer

thx for all the efforts there.

so far, my sd will shows following error on start after installation

Python 3.10.0 (default, Aug 27 2023, 13:35:08) [GCC 12.3.0]
Version: v1.6.0

This extension has been automatically deactivated
Please remove this extension
==========================================================================

*** Error loading script: remove_bg.py
    Traceback (most recent call last):
      File "/home/xxx/servers/stable-diffusion-webui/modules/scripts.py", line 382, in load_scripts
        script_module = script_loading.load_module(scriptfile.path)
      File "/home/xxx/servers/stable-diffusion-webui/modules/script_loading.py", line 10, in load_module
        module_spec.loader.exec_module(module)
      File "<frozen importlib._bootstrap_external>", line 883, in exec_module
      File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
      File "/home/xxx/servers/stable-diffusion-webui/extensions/clothseg/scripts/remove_bg.py", line 19, in <module>
        from rembg import remove, new_session
    ModuleNotFoundError: No module named 'rembg'

---

even I've executed

pip install rem_bg

successfully, it still cannot load, any ideas why?

thx in advance!

I like the idea! But how do I run it?

I installed via URL, not sure what to do next :)

A few questions when using the Extras / Batch and mask padding?

Thanks for this script. Everything works as described for individual images.

I was trying to do batch clothing segmentation using the extras tab. It works but it always spits out the 3 masks all in one image (Top+bottom+combined). Is there a way to only spit out one? I'm not sure if I'm missing a step here.

2 addition questions:

will there be an ALL clothing option? For example, TOP+BOTTOM+COMBINED for masking?
when masking, is there way to pad / expand the mask a bit by user entered # of pixels? I find the mask sometimes has missed just a little bit so I end up using manual inpainting. If I can expand the mask by say 15 pixels, everything would be perfect.

Thanks again for the great work!

TypeError: _argmax_dispatcher() got an unexpected keyword argument 'keepdims'

Error completing request
Arguments: ('task(nc1hvqo5kce170y)', 0, '', '', [], <PIL.Image.Image image mode=RGBA size=1440x1800 at 0x7F60747EB7F0>, None, None, None, None, None, None, 20, 0, 4, 0, 1, False, False, 1, 1, 7, 0, -1.0, -1.0, 0, 0, 0, False, 512, 512, 1, 0, 32, 0, '', '', '', [], 9, '<ul>\n<li><code>CFG Scale</code> should be 2 or lower.</li>\n</ul>\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 1, '<p style="margin-bottom:0.75em">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', False, False, '', '<p style="margin-bottom:0.75em">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>', 64, 0, 2, 1, '', 0, '', 0, '', True, False, False, False, 'u2net_cloth_seg', True, True, True, True) {}
Traceback (most recent call last):
  File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/img2img.py", line 166, in img2img
    processed = modules.scripts.scripts_img2img.run(p, *args)
  File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 376, in run
    processed = script.run(p, *script_args)
  File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/clothseg/scripts/remove_bg.py", line 83, in run
    remove_img = remove(processed.images[count], session=session)
  File "/usr/local/lib/python3.8/dist-packages/rembg/bg.py", line 135, in remove
    masks = session.predict(img)
  File "/usr/local/lib/python3.8/dist-packages/rembg/session_cloth.py", line 64, in predict
    pred = np.argmax(pred, axis=1, keepdims=True)
  File "<__array_function__ internals>", line 4, in argmax
TypeError: _argmax_dispatcher() got an unexpected keyword argument 'keepdims'

This problem is only with u2net_cloth_seg. Other models work fine.

Maybe I'm just doing something wrong?
I go into img2img and select the image, then in Script I select remove_bg v0.0.2 and run.

Denoising strength to 0 (I don't want the image to change).

automated dependency installation?

I tried this recently and it works very nicely. any way we could have rembg install automatically?

the package requests Pillow 9.3, and webui uses 9.4

i can see why the install of rembg can cause issues.

graemeniedermayer / clothseg Goto Github PK

clothseg's People

Contributors

Stargazers

Watchers

Forkers

clothseg's Issues

Error loading script: remove_bg.py in latest sd webui?

I like the idea! But how do I run it?

A few questions when using the Extras / Batch and mask padding?

TypeError: _argmax_dispatcher() got an unexpected keyword argument 'keepdims'

automated dependency installation?

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent