0.30.2

CNAME

@@ -0,0 +1 @@
+mixlabnodes.com

README.md

@@ -26,6 +26,8 @@
 
 #### `相关插件推荐`
 
+[comfyui-liveportrait](https://github.com/shadowcz007/comfyui-liveportrait)
+
 [Comfyui-ChatTTS](https://github.com/shadowcz007/Comfyui-ChatTTS)
 
 [comfyui-sound-lab](https://github.com/shadowcz007/comfyui-sound-lab)
@@ -167,6 +169,9 @@ pip install llama-cpp-python \
 
 > A new layer class node has been added, allowing you to separate the image into layers. After merging the images, you can input the controlnet for further processing.
 
+> The composite images node overlays a foreground image onto a background image at specified positions and scales, with optional blending modes and masking capabilities. position : 'overall',"center_center","left_bottom","center_bottom","right_bottom","left_top","center_top","right_top"
+
+
 ![layers](./assets/layers-workflow.svg)
 
 ![poster](./assets/poster-workflow.svg)
@@ -198,6 +203,12 @@ pip install llama-cpp-python \
 
 > Conveniently load images from a fixed address on the internet to ensure that default images in the workflow can be executed.
 
+#### TextImage
+
+> [下载字体](https://drxie.github.io/OSFCC/)放到 ```custom_nodes/comfyui-mixlab-nodes/assets/fonts```
+
+
+
 ### Style
 
 > Apply VisualStyle Prompting , Modified from [ComfyUI_VisualStylePrompting](https://github.com/ExponentialML/ComfyUI_VisualStylePrompting)

__init__.py

@@ -939,6 +939,10 @@ NODE_CLASS_MAPPINGS = {
 # 一个包含节点友好/可读的标题的字典
 NODE_DISPLAY_NAME_MAPPINGS = {
     "AppInfo":"App Info ♾️MixlabApp",
+    "ScreenShare":"Screen Share ♾️Mixlab",
+    "FloatingVideo":"Floating Video ♾️Mixlab",
+    "TextImage":"Text Image ♾️Mixlab",
+    
     "Color":"Color Input ♾️MixlabApp",
     "TextInput_":"Text Input ♾️MixlabApp",
     "FloatSlider":"Float Slider Input ♾️MixlabApp",
@@ -952,8 +956,7 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "SplitLongMask":"Splitting a long image into sections",
     "VAELoaderConsistencyDecoder":"Consistency Decoder Loader",
     "VAEDecodeConsistencyDecoder":"Consistency Decoder Decode",
-    "ScreenShare":"Screen Share ♾️Mixlab",
-    "FloatingVideo":"FloatingVideo ♾️Mixlab",
+    
     
     "MergeLayers":"Merge Layers ♾️Mixlab",
     "SpeechSynthesis":"SpeechSynthesis ♾️Mixlab",
@@ -988,7 +991,9 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "IncrementingListNode_":"Create Incrementing Number List ♾️Mixlab",
     "LoadImagesToBatch":"Load Images(base64) ♾️Mixlab",
     "PreviewMask_":"Preview Mask",
-    "AudioPlay":"Audio Play ♾️Mixlab"
+    "AudioPlay":"Audio Play ♾️Mixlab",
+
+     "MultiplicationNode":"Math Operation ♾️Mixlab",
 }
 
 # web ui的节点功能

nodes/ChatGPT.py

@@ -215,15 +215,28 @@ class ChatGPTNode:
 
     @classmethod
     def INPUT_TYPES(cls):
-        model_list=llama_modes_list+[
+        model_list=llama_modes_list+[ 
                     "gpt-3.5-turbo",
-                    "gpt-3.5-turbo-0125",
-                    "gpt-35-turbo",
-                    "gpt-3.5-turbo-16k", 
-                    "gpt-3.5-turbo-16k-0613", 
-                    "gpt-4-0613",
-                    "gpt-4-1106-preview",
-                    "glm-4"
+            "gpt-3.5-turbo-16k",
+            "gpt-4o",
+            "gpt-4o-2024-05-13",
+            "gpt-4",
+            "gpt-4-0314",
+            "gpt-4-0613",
+            "gpt-3.5-turbo-0301",
+            "gpt-3.5-turbo-0613",
+            "gpt-3.5-turbo-16k-0613",
+            "qwen-turbo",
+            "qwen-plus",
+            "qwen-long",
+            "qwen-max",
+            "qwen-max-longcontext",
+            "glm-4",
+            "glm-3-turbo",
+            "moonshot-v1-8k",
+            "moonshot-v1-32k",
+            "moonshot-v1-128k",
+            "deepseek-chat" 
                     ]
         return {
             "required": {

nodes/ImageNode.py

@@ -15,8 +15,8 @@ import cv2
 import string
 import math,glob
 from .Watcher import FolderWatcher
-import hashlib
 
+from itertools import product
 
 
 # 将PIL图片转换为OpenCV格式
@@ -29,142 +29,102 @@ def opencv_to_pil(image):
     pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
     return pil_image
 
+# 列出目录下面的所有文件
+def get_files_with_extension(directory, extension):
+    file_list = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            if file.endswith(extension):
+                file = os.path.splitext(file)[0]
+                file_path = os.path.join(root, file)
+                file_name = os.path.relpath(file_path, directory)
+                file_list.append(file_name)
+    return file_list
 
-def composite_images(foreground, background, mask,is_multiply_blend=False,position="overall"):
-    width,height=foreground.size
- 
-    bg_image=background
+def composite_images(foreground, background, mask, is_multiply_blend=False, position="overall", scale=0.25):
+    width, height = foreground.size
+    bg_image = background
+    bwidth, bheight = bg_image.size
 
-    bwidth,bheight=bg_image.size
+    scale=max(scale,1/bwidth)
+    scale=max(scale,1/bheight)
 
-    # 按z-index排序
-    if position=="overall":
+    def determine_scale_option(width, height):
+        return 'height' if height > width else 'width'
+
+    if position == "overall":
         layer = {
-                "x":0,
-                "y":0,
-                "width":bwidth,
-                "height":bheight,
-                "z_index":88,
-                "scale_option":'overall',
-                "image":foreground,
-                "mask":mask
+            "x": 0,
+            "y": 0,
+            "width": bwidth,
+            "height": bheight,
+            "z_index": 88,
+            "scale_option": 'overall',
+            "image": foreground,
+            "mask": mask
         }
+    else:
+        scale_option = determine_scale_option(width, height)
+        if scale_option == 'height':
+            scale = int(bheight * scale) / height
+        else:
+            scale = int(bwidth * scale) / width
 
-    elif position=='center_bottom':
-        
-        scale = int(bwidth*0.25) / width
+        new_width = int(width * scale)
         new_height = int(height * scale)
 
-        layer = {
-                "x":int(bwidth*0.75*0.5),
-                "y":bheight-new_height-24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
-        }
-
-    elif position=='right_bottom':
-        
-        scale = int(bwidth*0.25) / width
-        new_height = int(height * scale)
+        if position == 'center_bottom':
+            x_position = int((bwidth - new_width) * 0.5)
+            y_position = bheight - new_height - 24
+        elif position == 'right_bottom':
+            x_position = bwidth - new_width - 24
+            y_position = bheight - new_height - 24
+        elif position == 'center_top':
+            x_position = int((bwidth - new_width) * 0.5)
+            y_position = 24
+        elif position == 'right_top':
+            x_position = bwidth - new_width - 24
+            y_position = 24
+        elif position == 'left_top':
+            x_position = 24
+            y_position = 24
+        elif position == 'left_bottom':
+            x_position = 24
+            y_position = bheight - new_height - 24
+        elif position == 'center_center':
+            x_position = int((bwidth - new_width) * 0.5)
+            y_position = int((bheight - new_height) * 0.5)
 
         layer = {
-                "x":bwidth-int(bwidth*0.25)-24,
-                "y":bheight-new_height-24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
+            "x": x_position,
+            "y": y_position,
+            "width": new_width,
+            "height": new_height,
+            "z_index": 88,
+            "scale_option": scale_option,
+            "image": foreground,
+            "mask": mask
         }
 
+    layer_image = layer['image']
+    layer_mask = layer['mask']
 
-    elif position=='center_top':
-        
-        scale = int(bwidth*0.25) / width
-        new_height = int(height * scale)
+    bg_image = merge_images(bg_image,
+                            layer_image,
+                            layer_mask,
+                            layer['x'],
+                            layer['y'],
+                            layer['width'],
+                            layer['height'],
+                            layer['scale_option'],
+                            is_multiply_blend)
 
-        layer = {
-                "x":int( bwidth*0.75*0.5),
-                "y":24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
-        }
+    bg_image = bg_image.convert('RGB')
 
-    elif position=='right_top':
-        
-        scale = int(bwidth*0.25) / width
-        new_height = int(height * scale)
-
-        layer = {
-                "x":bwidth-int(bwidth*0.25)-24,
-                "y":24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
-        }
-    elif position=='left_top':
-        
-        scale = int(bwidth*0.25) / width
-        new_height = int(height * scale)
-
-        layer = {
-                "x":24,
-                "y":24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
-        }
-    elif position=='left_bottom':
-        
-        scale = int(bwidth*0.25) / width
-        new_height = int(height * scale)
-
-        layer = {
-                "x":24,
-                "y":bheight-new_height-24,
-                "width":int(bwidth*0.25),
-                "height":int(bheight*0.25),
-                "z_index":88,
-                "scale_option":'width',
-                "image":foreground,
-                "mask":mask
-        }
-                
-    # width, height = bg_image.size
-
-    layer_image=layer['image']
-    layer_mask=layer['mask']
-    
-    bg_image=merge_images(bg_image,
-                        layer_image,
-                        layer_mask,
-                        layer['x'],
-                        layer['y'],
-                        layer['width'],
-                        layer['height'],
-                        layer['scale_option'],
-                        is_multiply_blend )
-                   
-    bg_image=bg_image.convert('RGB')
-    
     return bg_image
 
 
+
 def count_files_in_directory(directory):
     file_count = 0
     for _, _, files in os.walk(directory):
@@ -201,7 +161,8 @@ class AnyType(str):
 any_type = AnyType("*")
 
 
-FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),'../assets/王汉宗颜楷体繁.ttf'))
+FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),'../assets/fonts'))
+
 
 MAX_RESOLUTION=8192
 
@@ -803,85 +764,78 @@ def multiply_blend(image1, image2):
 
 # cv2.imwrite('result.jpg', result)
 
+# 使用gpt4o优化代码
+# 为了消除图像合并时出现的灰色描边，可以使用以下方法：
+# 调整透明度：确保透明像素不会引入不需要的颜色。
+# 预处理图像：在缩放图像之前，可以先将图像的边缘进行预处理，例如扩展边缘颜色，减少抗锯齿带来的过渡效果。
 
-def merge_images(bg_image, layer_image, mask, x, y, width, height, scale_option,is_multiply_blend=False):
+def merge_images(bg_image, layer_image, mask, x, y, width, height, scale_option, is_multiply_blend=False):
     # 打开底图
     bg_image = bg_image.convert("RGBA")
 
     # 打开图层
     layer_image = layer_image.convert("RGBA")
-    # layer_image = layer_image.resize((width, height))
-
+   
     # 根据缩放选项调整图像大小
     if scale_option == "height":
         # 按照高度比例缩放
         original_width, original_height = layer_image.size
         scale = height / original_height
         new_width = int(original_width * scale)
-        layer_image = layer_image.resize((new_width, height))
+        layer_image = layer_image.resize((new_width, height), Image.NEAREST)
     elif scale_option == "width":
         # 按照宽度比例缩放
         original_width, original_height = layer_image.size
         scale = width / original_width
         new_height = int(original_height * scale)
-        layer_image = layer_image.resize((width, new_height))
+        layer_image = layer_image.resize((width, new_height), Image.NEAREST)
     elif scale_option == "overall":
         # 整体缩放
-        layer_image = layer_image.resize((width, height))
-
+        layer_image = layer_image.resize((width, height), Image.NEAREST)
     elif scale_option == "longest":
         original_width, original_height = layer_image.size
         if original_width > original_height:
-            new_width=width
+            new_width = width
             scale = width / original_width
             new_height = int(original_height * scale)
-            x=0
-            y=int((height-new_height)*0.5)
+            x = 0
+            y = int((height - new_height) * 0.5)
         else:
-            new_height=height
+            new_height = height
             scale = height / original_height
             new_width = int(original_height * scale)
-            x=int((width-new_width)*0.5)
-            y=0
-    # elif side == "shortest":
-    #         if width < height:
-    #              
-    #         else:
-    #              
-    
+            x = int((width - new_width) * 0.5)
+            y = 0
 
     # 调整mask的大小
     nw, nh = layer_image.size
-    mask = mask.resize((nw, nh))
+    mask = mask.resize((nw, nh), Image.NEAREST)
 
-    # # 分离出a通道
-    # r, g, b, alpha = layer_image.split()
-    # alpha = ImageOps.invert(alpha)
-    # # 创建一个新的RGB图像
-    # new_rgb_image = Image.new("RGB", layer_image.size)
-    # # 将透明通道粘贴到新的RGB图像上
-    # new_rgb_image.paste(layer_image, (0, 0), mask=alpha)
-   
-    # new_rgb_image.paste(layer_image, (x, y), mask=mask)
-    # mask=new_rgb_image.convert('L')
-    # mask = ImageOps.invert(mask)
+    # 预处理图像边缘以减少灰色描边
+    layer_image = layer_image.filter(ImageFilter.SMOOTH)
 
     if is_multiply_blend:
-        bg_image_white=Image.new("RGB", bg_image.size,(255, 255, 255))
+        bg_image_white = Image.new("RGB", bg_image.size, (255, 255, 255))
 
         bg_image_white.paste(layer_image, (x, y), mask=mask)
-        bg_image=multiply_blend(bg_image_white,bg_image)
-        bg_image=bg_image.convert("RGBA")
+        bg_image = multiply_blend(bg_image_white, bg_image)
+        bg_image = bg_image.convert("RGBA")
     else:
-        transparent_img = Image.new("RGBA",layer_image.size, (255, 255, 255, 0))
-        transparent_img.paste(layer_image,(0, 0), mask)
-        # transparent_img.save('test.png')
-        bg_image.paste(transparent_img, (x, y), transparent_img)
+        transparent_img = Image.new("RGBA", layer_image.size, (255, 255, 255, 0))
+        # 调整透明度处理
+        for i in range(transparent_img.size[0]):
+            for j in range(transparent_img.size[1]):
+                r, g, b, a = transparent_img.getpixel((i, j))
+                if a > 0:
+                    transparent_img.putpixel((i, j), (r, g, b, 255))
 
+        transparent_img.paste(layer_image, (0, 0), mask)
+        bg_image.paste(transparent_img, (x, y), transparent_img)
 
     # 输出合成后的图片
     return bg_image
 
+#MixCopilot
 
 def resize_2(img):
     # 检查图像的高度是否是2的倍数，如果不是，则调整高度
@@ -955,53 +909,13 @@ def resize_image(layer_image, scale_option, width, height,color="white"):
     return layer_image
 
 
-
-
-
-
-# def generate_text_image(text_list, font_path, font_size, text_color, vertical=True, spacing=0):
-#     # Load Chinese font
-#     font = ImageFont.truetype(font_path, font_size)
-
-#     # Calculate image size based on the number of characters and orientation
-#     if vertical:
-#         width = font_size + 100
-#         height = font_size * len(text_list) + (len(text_list) - 1) * spacing + 100
-#     else:
-#         width = font_size * len(text_list) + (len(text_list) - 1) * spacing + 100
-#         height = font_size + 100
-
-#     # Create a blank image
-#     image = Image.new('RGBA', (width, height), (255, 255, 255,0))
-#     draw = ImageDraw.Draw(image)
-
-#     # Draw text
-#     if vertical:
-#         for i, char in enumerate(text_list):
-#             char_position = (50, 50 + i * font_size)
-#             draw.text(char_position, char, font=font, fill=text_color)
-#     else:
-#         for i, char in enumerate(text_list):
-#             char_position = (50 + i * (font_size + spacing), 50)
-#             draw.text(char_position, char, font=font, fill=text_color)
-
-#     # Save the image
-#     # image.save(output_image_path)
-
-#     # 分离alpha通道
-#     alpha_channel = image.split()[3]
-
-#     # 创建一个只有alpha通道的新图像
-#     alpha_image = Image.new('L', image.size)
-#     alpha_image.putdata(alpha_channel.getdata())
-
-#     image=image.convert('RGB')
-
-#     return (image,alpha_image)
-def generate_text_image(text, font_path, font_size, text_color, vertical=True, stroke=False, stroke_color=(0, 0, 0), stroke_width=1, spacing=0):
+def generate_text_image(text, font_path, font_size, text_color, vertical=True, stroke=False, stroke_color=(0, 0, 0), stroke_width=1, spacing=0, padding=4):
     # Split text into lines based on line breaks
     lines = text.split("\n")
 
+    # Load font
+    font = ImageFont.truetype(font_path, font_size)
+
     # 1. Determine layout direction
     if vertical:
         layout = "vertical"
@@ -1010,49 +924,46 @@ def generate_text_image(text, font_path, font_size, text_color, vertical=True, s
 
     # 2. Calculate absolute coordinates for each character
     char_coordinates = []
-    if layout == "vertical":
-        x = 0
-        y = 0
-        for i in range(len(lines)):
-            line = lines[i]
-            for char in line:
-                char_coordinates.append((x, y))
-                y += font_size + spacing
-            x += font_size + spacing
-            y = 0
-    else:
-        x = 0
-        y = 0
-        for line in lines:
-            for char in line:
-                char_coordinates.append((x, y))
-                x += font_size + spacing
-            y += font_size + spacing
-            x = 0
+    x, y = padding, padding
+    max_width, max_height = 0, 0
 
-    # 3. Calculate image width and height
     if layout == "vertical":
-        width = (len(lines) * (font_size + spacing)) - spacing
-        height = ((len(max(lines, key=len)) + 1) * (font_size + spacing)) + spacing
+        for line in lines:
+            max_char_width = max(font.getsize(char)[0] for char in line)
+            for char in line:
+                char_width, char_height = font.getsize(char)
+                char_coordinates.append((x, y))
+                y += char_height + spacing
+                max_height = max(max_height, y + padding)
+            x += max_char_width + spacing
+            y = padding
+        max_width = x
     else:
-        width = (len(max(lines, key=len)) * (font_size + spacing)) - spacing
-        height = ((len(lines) - 1) * (font_size + spacing)) + font_size
+        for line in lines:
+            line_width, line_height = font.getsize(line)
+            for char in line:
+                char_width, char_height = font.getsize(char)
+                char_coordinates.append((x, y))
+                x += char_width + spacing
+                max_width = max(max_width, x + padding)
+            y += line_height + spacing
+            x = padding
+        max_height = y
+
+    # 3. Create image with calculated width and height
+    image = Image.new('RGBA', (max_width, max_height), (255, 255, 255, 0))
+    draw = ImageDraw.Draw(image)
 
     # 4. Draw each character on the image
-    image = Image.new('RGBA', (width, height), (255, 255, 255, 0))
-    draw = ImageDraw.Draw(image)
-    font = ImageFont.truetype(font_path, font_size)
-
     index = 0
-    for i, line in enumerate(lines):
-        for j, char in enumerate(line):
+    for line in lines:
+        for char in line:
             x, y = char_coordinates[index]
-            
             if stroke:
-                draw.text((x-stroke_width, y), char, font=font, fill=stroke_color)
-                draw.text((x+stroke_width, y), char, font=font, fill=stroke_color)
-                draw.text((x, y-stroke_width), char, font=font, fill=stroke_color)
-                draw.text((x, y+stroke_width), char, font=font, fill=stroke_color)
+                draw.text((x-stroke_width, y), char, font=font, fill=text_color)
+                draw.text((x+stroke_width, y), char, font=font, fill=text_color)
+                draw.text((x, y-stroke_width), char, font=font, fill=text_color)
+                draw.text((x, y+stroke_width), char, font=font, fill=text_color)
             
             draw.text((x, y), char, font=font, fill=text_color)
             index += 1
@@ -1579,7 +1490,7 @@ class ImageCropByAlpha:
 
 
 
-
+# get_files_with_extension(FONT_PATH,'.ttf')
 
 class TextImage:
     @classmethod
@@ -1587,7 +1498,7 @@ class TextImage:
         return {"required": { 
             
                     "text": ("STRING",{"multiline": True,"default": "龍馬精神迎新歲","dynamicPrompts": False}),
-                    "font_path": ("STRING",{"multiline": False,"default": FONT_PATH,"dynamicPrompts": False}),
+                    "font": (get_files_with_extension(FONT_PATH,'.ttf'),),#后缀为 ttf
                     "font_size": ("INT",{
                                 "default":100, 
                                 "min": 100, #Minimum value
@@ -1602,6 +1513,13 @@ class TextImage:
                                 "step": 1, #Slider's step
                                 "display": "number" # Cosmetic only: display as "number" or "slider"
                                 }), 
+                    "padding": ("INT",{
+                                "default":8, 
+                                "min": 0, #Minimum value
+                                "max": 200, #Maximum value
+                                "step": 1, #Slider's step
+                                "display": "number" # Cosmetic only: display as "number" or "slider"
+                                }), 
                     "text_color":("STRING",{"multiline": False,"default": "#000000","dynamicPrompts": False}),
                     "vertical":("BOOLEAN", {"default": True},),
                     "stroke":("BOOLEAN", {"default": False},),
@@ -1609,7 +1527,7 @@ class TextImage:
                 }
     
     RETURN_TYPES = ("IMAGE","MASK",)
-    # RETURN_NAMES = ("WIDTH","HEIGHT","X","Y",)
+    RETURN_NAMES = ("image","mask",)
 
     FUNCTION = "run"
 
@@ -1618,11 +1536,14 @@ class TextImage:
     INPUT_IS_LIST = False
     OUTPUT_IS_LIST = (False,False,)
 
-    def run(self,text,font_path,font_size,spacing,text_color,vertical,stroke):
+    def run(self,text,font,font_size,spacing,padding,text_color,vertical,stroke):
         
-        # text_list=list(text)
+        font_path=os.path.join(FONT_PATH,font+'.ttf')
+
+        if text=="":
+            text=" "
         # stroke=False, stroke_color=(0, 0, 0), stroke_width=1, spacing=0
-        img,mask=generate_text_image(text,font_path,font_size,text_color,vertical,stroke,(0, 0, 0),1,spacing)
+        img,mask=generate_text_image(text,font_path,font_size,text_color,vertical,stroke,(0, 0, 0),1,spacing,padding)
         
         img=pil2tensor(img)
         mask=pil2tensor(mask)
@@ -1855,10 +1776,16 @@ class CompositeImages:
                     "mask":("MASK",),
                     "background": ("IMAGE",),
                     },
-             "optional":{
-                           
+             "optional":{ 
                   "is_multiply_blend":  ("BOOLEAN", {"default": False}),
-                  "position":  (['overall',"center_bottom","center_top","right_bottom","left_bottom","right_top","left_top"],),    
+                  "position":  (['overall',"center_center","left_bottom","center_bottom","right_bottom","left_top","center_top","right_top"],),
+                   "scale": ("FLOAT",{
+                                "default":0.35, 
+                                "min": 0.01, #Minimum value
+                                "max": 1, #Maximum value
+                                "step": 0.01, #Slider's step
+                                "display": "number" # Cosmetic only: display as "number" or "slider"
+                            }), 
                     }
                 }
     
@@ -1871,15 +1798,33 @@ class CompositeImages:
 
     # OUTPUT_IS_LIST = (True,)
 
-    def run(self, foreground,mask,background,is_multiply_blend,position):
-        foreground= tensor2pil(foreground)
-        mask= tensor2pil(mask)
-        background= tensor2pil(background)
-        res=composite_images(foreground,background,mask,is_multiply_blend,position)
+    # def run(self, foreground,mask,background,is_multiply_blend,position,scale):
+    #     foreground= tensor2pil(foreground)
+    #     mask= tensor2pil(mask)
+    #     background= tensor2pil(background)
+    #     res=composite_images(foreground,background,mask,is_multiply_blend,position,scale)
         
-        return (pil2tensor(res),)
+    #     return (pil2tensor(res),)
 
+    def run(self, foreground,mask,background, is_multiply_blend, position, scale):
+        results = []
+        
+        f1=[]
+        for fg, mask in zip(foreground, mask ):
+            f1.append([fg,mask])
 
+        
+        for f, bg in product(f1, background):
+            [fg,mask]=f
+            fg_pil = tensor2pil(fg)
+            mask_pil = tensor2pil(mask)
+            bg_pil = tensor2pil(bg)
+            res = composite_images(fg_pil, bg_pil, mask_pil, is_multiply_blend, position, scale)
+            results.append(pil2tensor(res))
+        
+        output_image = torch.cat(results, dim=0)
+
+        return (output_image,)
 
 
 class EmptyLayer:

nodes/Lama.py

@@ -85,8 +85,6 @@ class LaMaInpainting:
             "image": ("IMAGE",),
             "mask": ("MASK",),
                              },
-
-            
                 }
     
     RETURN_TYPES = ("IMAGE",)

nodes/ScreenShareNode.py

@@ -90,7 +90,7 @@ class ScreenShareNode:
                 } }
     
     RETURN_TYPES = ('IMAGE','STRING','FLOAT',"INT")
-    RETURN_NAMES = ("IMAGE","PROMPT","FLOAT","INT")
+    RETURN_NAMES = ("current frame (image)","prompt","denoise (float)","seed (int)")
     FUNCTION = "run"
 
     CATEGORY = "♾️Mixlab/Screen"
@@ -109,7 +109,7 @@ class FloatingVideo:
     @classmethod
     def INPUT_TYPES(s):
         return { "required":{
-            "images": ("IMAGE",)
+            "image": ("IMAGE",)
         }, }
     
     # RETURN_TYPES = ('IMAGE','MASK')
@@ -124,16 +124,16 @@ class FloatingVideo:
     # OUTPUT_IS_LIST = (False,False,)
   
     # 运行的函数
-    def run(self,images):
+    def run(self,image):
        
         results = list()
     
-        for image in images:
-            image=tensor2pil(image)
+        for im in image:
+            im=tensor2pil(im)
             # image_base64 = base64.b64encode(image.tobytes())
 
             buffered = BytesIO()
-            image.save(buffered, format="JPEG")
+            im.save(buffered, format="JPEG")
             image_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
 
             results.append(image_base64)

nodes/Utils.py

@@ -566,7 +566,7 @@ class AppInfo:
                              },
 
                 "optional":{
-                    "IMAGE": ("IMAGE",),
+                    "image": ("IMAGE",),
                     "description":("STRING",{"multiline": True,"default": "","dynamicPrompts": False}),
                     "version":("INT", {
                         "default": 1, 
@@ -594,12 +594,12 @@ class AppInfo:
     INPUT_IS_LIST = True
     # OUTPUT_IS_LIST = (True,)
 
-    def run(self,name,input_ids,output_ids,IMAGE,description,version,share_prefix,link,category,auto_save):
+    def run(self,name,input_ids,output_ids,image,description,version,share_prefix,link,category,auto_save):
         name=name[0]
         
         im=None
-        if IMAGE:
-            im=IMAGE[0][0]
+        if image:
+            im=image[0][0]
             #TODO batch 的方式需要处理
             im=create_temp_file(im)
         # image [img,] img[batch,w,h,a] 列表里面是batch，

nodes/Video.py

@@ -179,6 +179,9 @@ def split_video(video_path, video_segment_frames, transition_frames, output_dir)
         
         # 打印当前片段的起始帧和结束帧
         print(f"Segment {i+1}: Start Frame {start_frame}, End Frame {end_frame}")
+
+        if end_frame<start_frame:
+            break
         
         # 保存当前片段为一个视频文件
         segment_video_path = f"{output_dir}/segment_{i+1}.avi"
@@ -187,6 +190,7 @@ def split_video(video_path, video_segment_frames, transition_frames, output_dir)
         segment_video = cv2.VideoWriter(segment_video_path, fourcc, fps, (int(video_capture.get(cv2.CAP_PROP_FRAME_WIDTH)),
                                                               int(video_capture.get(cv2.CAP_PROP_FRAME_HEIGHT))))
         
+
         for frame_num in range(start_frame, end_frame):
             ret, frame = video_capture.read()
             if ret:
@@ -526,22 +530,27 @@ class LoadAndCombinedAudio_:
 
     CATEGORY = "♾️Mixlab/Audio"
 
-    RETURN_TYPES = ("STRING",)
-    RETURN_NAMES = ("audio_file_path",)
+    RETURN_TYPES = ("STRING","AUDIO",)
+    RETURN_NAMES = ("audio_file_path","audio",)
     FUNCTION = "run"
 
     def run(self,audios, start_time, duration):
         output_dir = folder_paths.get_output_directory()
         counter=get_new_counter(output_dir,'audio_')
 
-        audio_file = f"audio_{counter:05}.wav"
+        audio_file_name = f"audio_{counter:05}.wav"
 
-        audio_file=save_audio_base64s_to_file(audios['base64'],output_dir,audio_file)
+        audio_file=save_audio_base64s_to_file(audios['base64'],output_dir,audio_file_name)
         # duration == -1 则不裁切
         if duration > -1:
             crop_audio(audio_file, start_time, duration)
 
-        return (audio_file,)
+        return (audio_file, {
+                "filename": audio_file_name,
+                "subfolder": "",
+                "type": "output",
+                "audio_path":audio_file
+                } ,)
 
 class CombineAudioVideo:
     @classmethod
@@ -615,8 +624,8 @@ class VideoCombine_Adv:
             },
         }
 
-    RETURN_TYPES = ("STRING",)
-    RETURN_NAMES = ("video_file_path",)
+    RETURN_TYPES = ("SCENE_VIDEO",)
+    RETURN_NAMES = ("scenes_video",)
     OUTPUT_NODE = True
     CATEGORY = "♾️Mixlab/Video"
     FUNCTION = "run"
@@ -890,7 +899,7 @@ class scenesNode_:
         
         return {"required": {
                     "scenes_video": ('SCENE_VIDEO',),
-                     "index": ("INT", {"default": 0, "min": 0, "step": 1}),
+                    "index": ("INT", {"default": 0, "min": 0, "step": 1}),
                      
                      },}
 
@@ -903,7 +912,7 @@ class scenesNode_:
     INPUT_IS_LIST = True
 
     def load_video_cv_fallback(self, video, frame_load_cap, skip_first_frames):
-        print('#video',video)
+        # print('#video',video)
         try:
             video_cap = cv2.VideoCapture(video)
             if not video_cap.isOpened():

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui-mixlab-nodes"
 description = "3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other Nodes, ..."
-version = "0.28.3"
+version = "0.30.2"
 license = "MIT"
 dependencies = ["numpy", "pyOpenSSL", "watchdog", "opencv-python-headless", "matplotlib", "openai", "simple-lama-inpainting", "clip-interrogator==0.6.0", "transformers>=4.36.0", "lark-parser", "imageio-ffmpeg", "rembg[gpu]", "omegaconf==2.3.0", "Pillow>=9.5.0", "einops==0.7.0", "trimesh>=4.0.5", "huggingface-hub", "scikit-image"]
 

requirements.txt

@@ -17,4 +17,4 @@ trimesh>=4.0.5
 huggingface-hub
 scikit-image
 torchaudio
-soundfile
+soundfile>=0.12.1

web/index.html

@@ -3460,7 +3460,7 @@
 
                 createAppList(window._apps);
 
-                if (window._apps.length > 0) await createHistoryList(category || '');
+                // if (window._apps.length > 0) await createHistoryList(category || '');
 
                 createApp(window._appData);
             }

web/javascript/app_mixlab.js

@@ -418,7 +418,7 @@ async function save (json, download = false, showInfo = true) {
 
 function getInputsAndOutputs () {
   const inputs =
-      `LoadImage LoadImagesToBatch ImagesPrompt_ LoadAndCombinedAudio_ VHS_LoadVideo CLIPTextEncode PromptSlide TextInput_ Color FloatSlider IntNumber CheckpointLoaderSimple LoraLoader`.split(
+      `LoadImage LoadImagesToBatch ImagesPrompt_ LoadAndCombinedAudio_ LoadVideoAndSegment_ VHS_LoadVideo CLIPTextEncode PromptSlide TextInput_ Color FloatSlider IntNumber CheckpointLoaderSimple LoraLoader`.split(
         ' '
       ),
     outputs =
@@ -526,7 +526,7 @@ app.registerExtension({
 
         //td bg
         const tdBG = document.createElement('button')
-        tdBG.innerText = 'TDBG'
+        tdBG.innerText = 'Canvas Mode'
         tdBG.style = style
         tdBG.style.marginLeft = '12px'
 
@@ -709,6 +709,7 @@ app.registerExtension({
         this.serialize_widgets = true //需要保存参数
 
         window._mixlab_app_json = null
+ 
       }
 
       const onExecuted = nodeType.prototype.onExecuted
@@ -725,7 +726,7 @@ app.registerExtension({
 
           const div = this.widgets.filter(w => w.div)[0].div
           Array.from(div.querySelectorAll('button'), b =>
-            b.innerText != 'TDBG' ? (b.style.background = 'yellow') : ''
+            b.innerText != 'Canvas Mode' ? (b.style.background = 'yellow') : ''
           )
         } catch (error) {}
       }

web/javascript/audio_mixlab.js

@@ -444,13 +444,23 @@ const createInputAudioForBatch = (base64, widget) => {
   // Create a delete button
   let deleteButton = document.createElement('button')
   deleteButton.textContent = 'Delete'
-  deleteButton.style = 'margin-left: 10px;'
+
+  deleteButton.style = `cursor: pointer;
+        font-weight: 300;
+        margin: 2px; 
+        margin-left: 10px;
+        color: var(--descrip-text);
+        background-color: var(--comfy-input-bg);
+        border-radius: 8px;
+        border-color: var(--border-color);
+        border-style: solid;height: 30px;min-width: 122px;
+       `
 
   // Create a container for the audio and delete button
   let container = document.createElement('div')
   container.appendChild(audio)
   container.appendChild(deleteButton)
-  container.style= `display: flex`
+  container.style = `display: flex;margin-top: 12px;`
 
   // Add event listener for the delete button
   deleteButton.addEventListener('click', e => {
@@ -571,7 +581,7 @@ app.registerExtension({
         // document.addEventListener('wheel', handleMouseWheel)
 
         const onRemoved = this.onRemoved
-        this.onRemoved = () => { 
+        this.onRemoved = () => {
           widget.div.remove()
           try {
             // document.removeEventListener('wheel', handleMouseWheel)

web/javascript/checkVersion_mixlab.js

@@ -3,7 +3,7 @@ import { app } from '../../../scripts/app.js'
 const repoOwner = 'shadowcz007' // 替换为仓库的所有者
 const repoName = 'comfyui-mixlab-nodes' // 替换为仓库的名称
 
-const version = 'v0.30.0'
+const version = 'v0.30.2'
 
 fetch(`https://api.github.com/repos/${repoOwner}/${repoName}/releases/latest`)
   .then(response => response.json())

web/javascript/gpt_mixlab.js

@@ -209,13 +209,16 @@ app.registerExtension({
         text = text.filter(t => t && t?.trim())
 
         if (this.widgets) {
+          // console.log('#ShowTextForGPT',this.widgets)
           // const pos = this.widgets.findIndex(w => w.name === 'text')
           for (let i = 0; i < this.widgets.length; i++) {
-            if (this.widgets[i].name == 'show_text') this.widgets[i].onRemove?.()
+            if (this.widgets[i].name == 'show_text')
+              this.widgets[i].onRemove?.()
+            console.log('#ShowTextForGPT', this.widgets[i])
           }
-          this.widgets.length = 1
+          this.widgets.length = 2
         }
-        // console.log('ShowTextForGPT',text)
+
         for (let list of text) {
           if (list) {
             // console.log('#####', list)
@@ -228,6 +231,8 @@ app.registerExtension({
             w.inputEl.readOnly = true
             w.inputEl.style.opacity = 0.6
 
+            // w.inputEl.style.display='none'
+
             try {
               if (typeof list != 'string') {
                 let data = JSON.parse(list)
@@ -280,5 +285,24 @@ app.registerExtension({
 
       this.serialize_widgets = true //需要保存参数
     }
+  },
+  async loadedGraphNode (node, app) {
+    if (node.type === 'ShowTextForGPT') {
+      let widget = node.widgets.filter(w => w.name == 'show_text')[0]
+
+      // if (widget.value) {
+      //   let [url, prompt] = widget.value
+
+      //   this[`wavesurfer_${node.id}`] = updateWaveWidgetValue(
+      //     node.widgets,
+      //     node.id,
+      //     url,
+      //     prompt,
+      //     this[`wavesurfer_${node.id}`]
+      //   )
+      // }
+
+      console.log('#loadedGraphNode', node)
+    }
   }
 })

web/javascript/main_mixlab.js

@@ -1267,7 +1267,7 @@ app.registerExtension({
         })
 
         widget.PictureInPicture = $el('button', {
-          innerText: 'PictureInPicture',
+          innerText: 'Picture In Picture',
           style: {
             display: 'pictureInPictureEnabled' in document ? 'block' : 'none',
             cursor: 'pointer',

web/javascript/ui_mixlab.js

@@ -1439,10 +1439,14 @@ app.registerExtension({
 
     LGraphCanvas.prototype.fixTheNode = function (node) {
       let new_node = LiteGraph.createNode(node.comfyClass)
-      new_node.pos = [node.pos[0], node.pos[1]]
-      app.canvas.graph.add(new_node, false)
-      copyNodeValues(node, new_node)
-      app.canvas.graph.remove(node)
+      console.log(node)
+      if(new_node){
+        new_node.pos = [node.pos[0], node.pos[1]]
+        app.canvas.graph.add(new_node, false)
+        copyNodeValues(node, new_node)
+        app.canvas.graph.remove(node)
+      }
+     
     }
 
     smart_init()