0.30.3

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)

__init__.py

@@ -179,7 +179,7 @@ def create_for_https():
 
 # workflow  目录下的所有json
 def read_workflow_json_files_all(folder_path):
-    print('#read_workflow_json_files_all',folder_path)
+    # print('#read_workflow_json_files_all',folder_path)
     json_files = []
     for root, dirs, files in os.walk(folder_path):
         for file in files:
@@ -760,8 +760,7 @@ async def start_local_llm(data):
             if file.startswith(file_name):
                 clip_model_path=os.path.join(os.path.dirname(model),file)
                 chat_format='llava-1-5'
-    print('#clip_model_path',chat_format,clip_model_path)
-
+    # print('#clip_model_path',chat_format,clip_model_path,model)
 
     address="127.0.0.1"
     port=9090
@@ -779,38 +778,39 @@ async def start_local_llm(data):
     server_settings=ServerSettings(host=address,port=port)
 
     name, ext = os.path.splitext(os.path.basename(model))
-    print('#model',name)
-    app = create_app(
-                server_settings=server_settings,
-                model_settings=[
-                    ModelSettings(
-                    model=model,
-                    model_alias=name,
-                    n_gpu_layers=n_gpu_layers,
-                    n_ctx=4098,
-                    chat_format=chat_format,
-                    embedding=False,
-                    clip_model_path=clip_model_path
-                    )])
+    if name:
+        # print('#model',name)
+        app = create_app(
+                    server_settings=server_settings,
+                    model_settings=[
+                        ModelSettings(
+                        model=model,
+                        model_alias=name,
+                        n_gpu_layers=n_gpu_layers,
+                        n_ctx=4098,
+                        chat_format=chat_format,
+                        embedding=False,
+                        clip_model_path=clip_model_path
+                        )])
 
-    def run_uvicorn():
-        uvicorn.run(
-                app,
-                host=os.getenv("HOST", server_settings.host),
-                port=int(os.getenv("PORT", server_settings.port)),
-                ssl_keyfile=server_settings.ssl_keyfile,
-                ssl_certfile=server_settings.ssl_certfile,
-            )
+        def run_uvicorn():
+            uvicorn.run(
+                    app,
+                    host=os.getenv("HOST", server_settings.host),
+                    port=int(os.getenv("PORT", server_settings.port)),
+                    ssl_keyfile=server_settings.ssl_keyfile,
+                    ssl_certfile=server_settings.ssl_certfile,
+                )
 
-    # 创建一个子线程
-    thread = threading.Thread(target=run_uvicorn)
+        # 创建一个子线程
+        thread = threading.Thread(target=run_uvicorn)
 
-    # 启动子线程
-    thread.start()
+        # 启动子线程
+        thread.start()
 
-    llama_port=port
-    llama_model=data['model']
-    llama_chat_format=chat_format
+        llama_port=port
+        llama_model=data['model']
+        llama_chat_format=chat_format
 
     return  {"port":llama_port,"model":llama_model,"chat_format":llama_chat_format}
 
@@ -991,7 +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
@@ -1095,7 +1097,7 @@ try:
         "VideoCombine_Adv":"Video Combine",
         "LoadAndCombinedAudio_":"Load And Combined Audio",
         "CombineAudioVideo":"Combine Audio Video",
-        "ScenesNode_":"Scenes Node", 
+        "ScenesNode_":"Select Scene", 
         "GenerateFramesByCount":"Generate Frames By Count"
     }
 

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/ClipInterrogator.py

@@ -79,7 +79,7 @@ def get_clip_interrogator_path():
 
 cache_path=get_clip_interrogator_path()
 
-caption_model_path=os.path.join(cache_path, "Salesforce/blip-image-captioning-base")
+caption_model_path=os.path.join(cache_path, "Salesforce","blip-image-captioning-base")
 if not os.path.exists(caption_model_path):
     print(f"## clip_interrogator_model not found: {caption_model_path}, pls download from https://huggingface.co/Salesforce/blip-image-captioning-base")
     caption_model_path='Salesforce/blip-image-captioning-base'

nodes/ImageNode.py

@@ -16,7 +16,7 @@ import string
 import math,glob
 from .Watcher import FolderWatcher
 
-
+from itertools import product
 
 
 # 将PIL图片转换为OpenCV格式
@@ -46,6 +46,9 @@ def composite_images(foreground, background, mask, is_multiply_blend=False, posi
     bg_image = background
     bwidth, bheight = bg_image.size
 
+    scale=max(scale,1/bwidth)
+    scale=max(scale,1/bheight)
+
     def determine_scale_option(width, height):
         return 'height' if height > width else 'width'
 
@@ -158,7 +161,7 @@ class AnyType(str):
 any_type = AnyType("*")
 
 
-FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),'../assets/fonts'))
+FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),"..","assets","fonts"))
 
 
 MAX_RESOLUTION=8192
@@ -957,10 +960,10 @@ def generate_text_image(text, font_path, font_size, text_color, vertical=True, s
         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
@@ -1777,7 +1780,7 @@ class CompositeImages:
                   "is_multiply_blend":  ("BOOLEAN", {"default": False}),
                   "position":  (['overall',"center_center","left_bottom","center_bottom","right_bottom","left_top","center_top","right_top"],),
                    "scale": ("FLOAT",{
-                                "default":0, 
+                                "default":0.35, 
                                 "min": 0.01, #Minimum value
                                 "max": 1, #Maximum value
                                 "step": 0.01, #Slider's step
@@ -1795,15 +1798,33 @@ class CompositeImages:
 
     # OUTPUT_IS_LIST = (True,)
 
-    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)
+    # 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/Utils.py

@@ -133,7 +133,7 @@ def get_font_files(directory):
 
     return font_files
 
-r_directory = os.path.join(os.path.dirname(__file__), '../assets/')
+r_directory = os.path.join(os.path.dirname(__file__), '..','assets','/')
 
 font_files = get_font_files(r_directory)
 # print(font_files)

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"
@@ -890,12 +899,12 @@ class scenesNode_:
         
         return {"required": {
                     "scenes_video": ('SCENE_VIDEO',),
-                     "index": ("INT", {"default": 0, "min": 0, "step": 1}),
+                    "index": ("INT", {"default": 0, "min": 0, "step": 1}),
                      
                      },}
 
     RETURN_TYPES = ('IMAGE','INT',)
-    RETURN_NAMES = ("frames","count",)
+    RETURN_NAMES = ("video frames (batch)","count",)
     # OUTPUT_IS_LIST = (False,)
 
     FUNCTION = "run"
@@ -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():
@@ -958,7 +967,7 @@ class scenesNode_:
         index=index[0]
         if len(scenes_video) > index:
             vp=scenes_video[index]
-
-            return self.load_video_cv_fallback(vp,0,0)
+        else:
+            vp=scenes_video[-1]
         
-        return ([], 0,)
+        return self.load_video_cv_fallback(vp,0,0)

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "comfyui-mixlab-nodes"
 description = "3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other Nodes, ..."
-version = "0.30.1"
+version = "0.30.3"
 license = "MIT"
-dependencies = ["scikit-image","soundfile","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"]
+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"]
 
 [project.urls]
 Repository = "https://github.com/shadowcz007/comfyui-mixlab-nodes"

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 =

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 = 'v0.30.1'
+const version = 'v0.30.3'
 
 fetch(`https://api.github.com/repos/${repoOwner}/${repoName}/releases/latest`)
   .then(response => response.json())

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()