commit TransparentBackgroundUltra node, add install_requirements.bat …

…to easy install dependency package

README.MD

@@ -20,7 +20,9 @@ Some JSON workflow files in the ```workflow``` directory, That's examples of how
 
 
 ## How to install 
+(Taking ComfyUI official portable package and Aki ComfyUI package as examples, please modify the dependency environment directory for other ComfyUI environments)
 
+### Install plugin
 * Recommended use ComfyUI Manager for installation.
 
 * Or open the cmd window in the plugin directory of ComfyUI, like ```ComfyUI\custom_nodes```，type 
@@ -29,13 +31,26 @@ git clone https://github.com/chflame163/ComfyUI_LayerStyle.git
 ```
 * Or download the zip file and extracted, copy the resulting folder to ```ComfyUI\custom_ Nodes``` 
 
-* Install dependency packages, open the cmd window in the ComfyUI_LayerStyle plugin directory like 
-```ComfyUI\custom_ Nodes\ComfyUI_LayerStyle``` and enter the following command: 
+### Install dependency packages 
+* for ComfyUI official portable package, double-click the ```install_requirements.bat``` in the plugin directory, for Aki ComfyUI package double-click on the ```install_requirements_aki.bat``` in the plugin directory, and wait for the installation to complete.
+
+* Or install dependency packages, open the cmd window in the ComfyUI_LayerStyle plugin directory like 
+```ComfyUI\custom_ Nodes\ComfyUI_LayerStyle``` and enter the following command,
+
+  for ComfyUI official portable package, type:
 
 ```
-..\..\..\python_embeded\python.exe -m pip install -r requirements.txt
+..\..\..\python_embeded\python.exe -s -m pip install .\whl\docopt-0.6.2-py2.py3-none-any.whl
+..\..\..\python_embeded\python.exe -s -m pip install -r requirements.txt
+.\repair_dependency.bat
 ```
+  for Aki ComfyUI package, type:
 
+```
+..\..\python\python.exe -s -m pip install .\whl\docopt-0.6.2-py2.py3-none-any.whl
+..\..\python\python.exe -s -m pip install -r requirements.txt
+.\repair_dependency.bat
+```
 * Restart ComfyUI.
 
 ## Common Issues
@@ -65,7 +80,7 @@ This error is caused by the low version of ```transformers``` package.
 ### insightface Loading very slow
 This error is caused by the low version of ```protobuf``` package. 
 
-## For the issues with the above three dependency packages, please double click ```repair_dependency.bat``` (for Official ComfyUI Protable) or ```repair_dependency_aki.bat``` (for ComfyUI-aki-v1.x) in the plugin folder to automatically fix them.
+#### For the issues with the above three dependency packages, please double click ```repair_dependency.bat``` (for Official ComfyUI Protable) or ```repair_dependency_aki.bat``` (for ComfyUI-aki-v1.x) in the plugin folder to automatically fix them.
 
 ### ValueError: Trimap did not contain foreground values (xxxx...)
 This error is caused by the mask area being too large or too small when using the ```PyMatting``` method to handle the mask edges. 
@@ -80,6 +95,7 @@ When this error has occurred, please check the network environment.
 ## Update
 <font size="4">**If the dependency package error after updating, please reinstall the relevant dependency packages. </font><br /> 
 
+* Commit [TransparentBackgroundUltra](#TransparentBackgroundUltra) node, it remove background based on transparent-background model.
 * Change the VitMatte model of the [Ultra](#Ultra) node to a local call. Please download [all files of vitmatte model](https://huggingface.co/hustvl/vitmatte-small-composition-1k/tree/main) to the ```ComfyUI/models/vitmatte``` folder.
 * [GetColorToneV2](#GetColorToneV2) node add the ```mask``` method to the color selection option, which can accurately obtain the main color and average color within the mask.
 * [ImageScaleByAspectRatioV2](#ImageScaleByAspectRatioV2) node add the "background_color" option.
@@ -1482,6 +1498,28 @@ Node options:
 * device: Set whether the VitMatte to use cuda.
 * max_megapixels: Set the maximum size for VitMate operations.
 
+### <a id="table1">TransparentBackgroundUltra</a>
+Using the transparent-background model to remove background has better recognition ability and speed, while also having ultra-high edge details.
+
+*Download [ckpt_base.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_base.pth), 
+[ckpt_fast.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_fast.pth) and 
+[ckpt_base_nightly.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_base_nightly.pth) 
+ 3 files to ```ComfyUI/models/transparent-background``` folder.
+
+![image](image/transparent_background_ultra_example.jpg) 
+
+Node Options: 
+![image](image/transparent_background_ultra_node.jpg) 
+* model: Select the model.
+* detail_method: Edge processing methods. provides VITMatte, VITMatte(local), PyMatting, GuidedFilter. If the model has been downloaded after the first use of VITMatte, you can use VITMatte (local) afterwards.
+* detail_erode: Mask the erosion range inward from the edge. the larger the value, the larger the range of inward repair.
+* detail_dilate: The edge of the mask expands outward. the larger the value, the wider the range of outward repair.
+* black_point: Edge black sampling threshold.
+* white_point: Edge white sampling threshold.
+* process_detail: Set to false here will skip edge processing to save runtime.
+* device: Set whether the VitMatte to use cuda.
+* max_megapixels: Set the maximum size for VitMate operations.
+
 ### <a id="table1">PersonMaskUltra</a>
 Generate masks for portrait's face, hair, body skin, clothing, or accessories. Compared to the previous A Person Mask Generator node, this node has ultra-high edge details.
 The model code for this node comes from [a-person-mask-generator](https://github.com/djbielejeski/a-person-mask-generator)， edge processing code from [ComfyUI-Image-Filters](https://github.com/spacepxl/ComfyUI-Image-Filters)，thanks to the original author.

README_CN.MD

@@ -15,7 +15,9 @@
 
 
 ## 安装方法
+(以ComfyUI官方便携包和秋叶整合包为例，其他ComfyUI环境请修改依赖环境目录)
 
+### 安装插件
 * 推荐使用 ComfyUI Manager 安装。
 * 或者在CompyUI插件目录(例如“CompyUI\custom_nodes\”)中打开cmd窗口，键入 
 ```
@@ -24,13 +26,27 @@ git clone https://github.com/chflame163/ComfyUI_LayerStyle.git
   
 * 或者下载解压zip文件，将得到的文件夹复制到 ```ComfyUI\custom_nodes\```。 
 
-* 安装依赖包，在资源管理器```ComfyUI\custom_nodes\ComfyUI_LayerStyle``` 插件目录位置打开cmd窗口，输入以下命令： 
+### 安装依赖包
+
+* 官方便携包请双击运行插件目录下的```install_requirements.bat```，秋叶整合包请双击运行插件目录下的```install_requirements_aki.bat```，然后等待安装完成。
+
+* 或者在资源管理器```ComfyUI\custom_nodes\ComfyUI_LayerStyle``` 插件目录位置打开cmd窗口， 
+
+  官方便携包输入以下命令：
+
 ```
-..\..\..\python_embeded\python.exe -m pip install -r requirements.txt
+..\..\..\python_embeded\python.exe -s -m pip install .\whl\docopt-0.6.2-py2.py3-none-any.whl
+..\..\..\python_embeded\python.exe -s -m pip install -r requirements.txt
+.\repair_dependency.bat
 ```
+  秋叶整合包输入以下命令：
 
-
- 重新打开ComfyUI。
+```
+..\..\python\python.exe -s -m pip install .\whl\docopt-0.6.2-py2.py3-none-any.whl
+..\..\python\python.exe -s -m pip install -r requirements.txt
+.\repair_dependency.bat
+```
+* 重新打开ComfyUI。
 
 ## 常见问题
 如果节点不能正常加载，或者使用中出现错误，请在ComfyUI终端窗口查看报错信息。以下是常见的错误及解决方法。
@@ -57,7 +73,7 @@ git clone https://github.com/chflame163/ComfyUI_LayerStyle.git
 ### insightface 加载缓慢
 这是由于```protobuf``` 版本过低造成的。
 
-## 以上三个依赖包的问题，请双击运行插件目录下的```repair_dependency.bat```(官方便携包)或者```repair_dependency_aki.bat```(秋叶整合包)自动修复。 
+#### 以上三个依赖包的问题，请双击运行插件目录下的```repair_dependency.bat```(官方便携包)或者```repair_dependency_aki.bat```(秋叶整合包)自动修复。 
 
 ### ValueError: Trimap did not contain foreground values (xxxx...)
 这个错误是由于使用PyMatting方法处理遮罩边缘时，遮罩面积过大或者过小引起的。 
@@ -80,6 +96,7 @@ git clone https://github.com/chflame163/ComfyUI_LayerStyle.git
 ## 更新说明
 <font size="4">**如果本插件更新后出现依赖包错误，请重新安装相关依赖包。
 
+* 添加[TransparentBackgroundUltra](#TransparentBackgroundUltra) 节点，基于transparent-background模型，用于去除背景。
 * [Ultra](#Ultra) 节点的VitMatte模型改为本地调用，请下载[所有的vitmatte模型文件](https://huggingface.co/hustvl/vitmatte-small-composition-1k/tree/main)到```ComfyUI/models/vitmatte```文件夹。
 * [GetColorToneV2](#GetColorToneV2) 节点的取色选项增加```mask```方法，可精确获取遮罩内的主色和平均色。
 * [ImageScaleByAspectRatioV2](#ImageScaleByAspectRatioV2) 节点增加background_color选项。 
@@ -1462,6 +1479,29 @@ RemBgUltra的V2升级版，增加了VITMatte边缘处理方法。
 * device: 设置是否使用cuda。
 * max_megapixels: 设置vitmatte运算的最大尺寸。
 
+### <a id="table1">TransparentBackgroundUltra</a>
+使用transparent-background模型去除背景，有更好的识别能力和识别速度，同时具有超高的边缘细节。
+本节点模型部分的代码来自[github.com/plemeri/transparent-background](https://github.com/plemeri/transparent-background)，感谢原作者。
+
+*下载 [ckpt_base.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_base.pth), 
+[ckpt_fast.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_fast.pth) 和
+[ckpt_base_nightly.pth](https://github.com/plemeri/transparent-background/releases/download/1.2.12/ckpt_base_nightly.pth) 
+3 个文件至```ComfyUI/models/transparent-background```文件夹。
+
+![image](image/transparent_background_ultra_example.jpg) 
+
+节点选项说明: 
+![image](image/transparent_background_ultra_node.jpg) 
+* model: 选择模型。
+* detail_method: 边缘处理方法。提供了VITMatte, VITMatte(local), PyMatting, GuidedFilter。如果首次使用VITMatte后模型已经下载，之后可以使用VITMatte(local)。
+* detail_erode: 遮罩边缘向内侵蚀范围。数值越大，向内修复的范围越大。
+* detail_dilate: 遮罩边缘向外扩张范围。数值越大，向外修复的范围越大。
+* black_point: 边缘黑色采样阈值。
+* white_point: 边缘黑色采样阈值。
+* process_detail: 此处设为False将跳过边缘处理以节省运行时间。
+* device: 设置是否使用cuda。
+* max_megapixels: 设置vitmatte运算的最大尺寸。
+
 ### <a id="table1">PersonMaskUltra</a>
 为人物生成脸、头发、身体皮肤、衣服或配饰的遮罩。与之前的A Person Mask Generator节点相比，这个节点具有超高的边缘细节。
 本节点的模型代码来自[a-person-mask-generator](https://github.com/djbielejeski/a-person-mask-generator)，边缘处理代码来自spacepxl的[ComfyUI-Image-Filters](https://github.com/spacepxl/ComfyUI-Image-Filters)，感谢原作者。

install_requirements.bat

@@ -0,0 +1,25 @@
+@echo off
+
+set "python_exec=..\..\..\python_embeded\python.exe"
+set "repair_dependency_txt=%~dp0\repair_dependency_list.txt"
+
+echo Installing with ComfyUI Portable
+echo .
+echo Install whl...
+%python_exec% -s -m pip install ./whl/docopt-0.6.2-py2.py3-none-any.whl
+
+echo .
+echo Install requirement.txt...
+%python_exec% -s -m pip install -r ./requirements.txt
+
+echo .
+echo Fixing Dependency Package...
+%python_exec% -s -m pip uninstall -y opencv-python opencv-contrib-python opencv-python-headless opencv-contrib-python-headless
+for /f "delims=" %%i in (%repair_dependency_txt%) do (
+ %python_exec% -s -m pip install "%%i"
+ )
+
+echo .
+echo Install Finish!
+pause
+

install_requirements_aki.bat

@@ -0,0 +1,25 @@
+@echo off
+
+set "python_exec=..\..\python\python.exe"
+set "repair_dependency_txt=%~dp0\repair_dependency_list.txt"
+
+echo Installing with ComfyUI Portable
+echo .
+echo Install whl...
+%python_exec% -s -m pip install ./whl/docopt-0.6.2-py2.py3-none-any.whl
+
+echo .
+echo Install requirement.txt...
+%python_exec% -s -m pip install -r ./requirements.txt
+
+echo .
+echo Fixing Dependency Package...
+%python_exec% -s -m pip uninstall -y opencv-python opencv-contrib-python opencv-python-headless opencv-contrib-python-headless
+for /f "delims=" %%i in (%repair_dependency_txt%) do (
+ %python_exec% -s -m pip install "%%i"
+ )
+
+echo .
+echo Install Finish!
+pause
+

py/imagefunc.py

@@ -1097,29 +1097,6 @@ def gamma_trans(image:Image, gamma:float) -> Image:
  _corrected = cv2.LUT(cv2_image,gamma_table)
  return cv22pil(_corrected)
 
-# def apply_lut(image:Image, lut_file:str, log:bool=False) -> Image:
-# from colour.io.luts.iridas_cube import read_LUT_IridasCube, LUT3D, LUT3x1D
-# lut: Union[LUT3x1D, LUT3D] = read_LUT_IridasCube(lut_file)
-# lut.name = os.path.splitext(os.path.basename(lut_file))[0] # use base filename instead of internal LUT name
-#
-# im_array = np.asarray(image.convert('RGB'), dtype=np.float32) / 255
-# is_non_default_domain = not np.array_equal(lut.domain, np.array([[0., 0., 0.], [1., 1., 1.]]))
-# dom_scale = None
-# if is_non_default_domain:
-# dom_scale = lut.domain[1] - lut.domain[0]
-# im_array = im_array * dom_scale + lut.domain[0]
-# if log:
-# im_array = im_array ** (1 / 2.2)
-# im_array = lut.apply(im_array)
-# if log:
-# im_array = im_array ** (2.2)
-# if is_non_default_domain:
-# im_array = (im_array - lut.domain[0]) / dom_scale
-# im_array = im_array * 255
-# ret_image = Image.fromarray(np.uint8(im_array))
-#
-# return ret_image
-
 def apply_lut(image:Image, lut_file:str, colorspace:str, strength:int, clip_values:bool=True) -> Image:
  """
  Apply a LUT to an image.
@@ -2071,7 +2048,7 @@ def chat_response(self, message, history, image_path):
  **model_inputs,
  max_new_tokens=512,
  do_sample=True,
- temperature=0.7,
+ temperature=0.3,
  repetition_penalty=1.2,
  stopping_criteria=StoppingCriteriaList([stop])
  )

py/transparent_background_ultra.py

@@ -0,0 +1,85 @@
+from transparent_background import Remover
+from .imagefunc import *
+
+NODE_NAME = 'TransparentBackgroundUltra'
+model_file_list = glob.glob(os.path.join(folder_paths.models_dir, "transparent-background") + '/*.pth')
+model_dict = {}
+for i in range(len(model_file_list)):
+ _, __filename = os.path.split(model_file_list[i])
+ model_dict[__filename] = model_file_list[i]
+model_list = list(model_dict.keys())
+mode_dict = {"ckpt_base.pth": "base", "ckpt_base_nightly.pth": "base-nightly", "ckpt_fast.pth": "fast"}
+class TransparentBackgroundUltra:
+
+ @classmethod
+ def INPUT_TYPES(cls):
+ method_list = ['VITMatte', 'VITMatte(local)', 'PyMatting', 'GuidedFilter', ]
+ device_list = ['cuda','cpu']
+ return {
+ "required": {
+ "image": ("IMAGE",),
+ "model": (model_list,),
+ "detail_method": (method_list,),
+ "detail_erode": ("INT", {"default": 6, "min": 1, "max": 255, "step": 1}),
+ "detail_dilate": ("INT", {"default": 6, "min": 1, "max": 255, "step": 1}),
+ "black_point": ("FLOAT", {"default": 0.01, "min": 0.01, "max": 0.98, "step": 0.01, "display": "slider"}),
+ "white_point": ("FLOAT", {"default": 0.99, "min": 0.02, "max": 0.99, "step": 0.01, "display": "slider"}),
+ "process_detail": ("BOOLEAN", {"default": True}),
+ "device": (device_list,),
+ "max_megapixels": ("FLOAT", {"default": 2.0, "min": 1, "max": 999, "step": 0.1}),
+ },
+ "optional": {
+ }
+ }
+
+ RETURN_TYPES = ("IMAGE", "MASK", )
+ RETURN_NAMES = ("image", "mask", )
+ FUNCTION = "transparent_background_ultra"
+ CATEGORY = '😺dzNodes/LayerMask'
+
+ def transparent_background_ultra(self, image, model, detail_method, detail_erode, detail_dilate,
+ black_point, white_point, process_detail, device, max_megapixels):
+ ret_images = []
+ ret_masks = []
+
+ if detail_method == 'VITMatte(local)':
+ local_files_only = True
+ else:
+ local_files_only = False
+
+ remover = Remover(mode=mode_dict[model], jit=False, device=device, ckpt=model_dict[model])
+ for i in image:
+ i = torch.unsqueeze(i, 0)
+ orig_image = tensor2pil(i).convert('RGB')
+ ret_image = remover.process(orig_image, type='rgba')
+ _mask = ret_image.split()[3]
+ _mask = adjust_levels(_mask, 64, 192)
+
+ if process_detail:
+ detail_range = detail_erode + detail_dilate
+ _mask = pil2tensor(_mask)
+ if detail_method == 'GuidedFilter':
+ _mask = guided_filter_alpha(i, _mask, detail_range // 6 + 1)
+ _mask = tensor2pil(histogram_remap(_mask, black_point, white_point))
+ elif detail_method == 'PyMatting':
+ _mask = tensor2pil(mask_edge_detail(i, _mask, detail_range // 8 + 1, black_point, white_point))
+ else:
+ _trimap = generate_VITMatte_trimap(_mask, detail_erode, detail_dilate)
+ _mask = generate_VITMatte(orig_image, _trimap, local_files_only=local_files_only, device=device, max_megapixels=max_megapixels)
+ _mask = tensor2pil(histogram_remap(pil2tensor(_mask), black_point, white_point))
+ ret_image = RGB2RGBA(orig_image, _mask.convert('L'))
+
+ ret_images.append(pil2tensor(ret_image))
+ ret_masks.append(image2mask(_mask))
+
+ log(f"{NODE_NAME} Processed {len(ret_images)} image(s).", message_type='finish')
+
+ return (torch.cat(ret_images, dim=0), torch.cat(ret_masks, dim=0),)
+
+NODE_CLASS_MAPPINGS = {
+ "LayerMask: TransparentBackgroundUltra": TransparentBackgroundUltra,
+}
+
+NODE_DISPLAY_NAME_MAPPINGS = {
+ "LayerMask: TransparentBackgroundUltra": "LayerMask: Transparent Background Ultra",
+}

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui_layerstyle"
 description = "A set of nodes for ComfyUI it generate image like Adobe Photoshop's Layer Style. the Drop Shadow is first completed node, and follow-up work is in progress."
-version = "1.0.16"
+version = "1.0.17"
 license = "MIT"
 dependencies = ["numpy", "pillow", "torch", "matplotlib", "Scipy", "scikit_image", "opencv-contrib-python", "pymatting", "segment_anything", "timm", "addict", "yapf", "colour-science", "wget", "mediapipe", "loguru", "typer_config", "fastapi", "rich", "google-generativeai", "diffusers", "omegaconf", "tqdm", "transformers", "kornia", "image-reward", "ultralytics", "blend_modes", "blind-watermark", "qrcode", "pyzbar", "psd-tools"]
 

repair_dependency_list.txt

@@ -1,3 +1,4 @@
-opencv-contrib-python>=4.9.0.80
+huggingface_hub==0.23.3
 transformers>=4.38.1
-protobuf>=4.25.3
+protobuf>=4.25.3
+opencv-contrib-python>=4.9.0.80

requirements.txt

@@ -29,4 +29,5 @@ blend_modes
 blind-watermark
 qrcode
 pyzbar
+transparent-background
 psd-tools