Update pyproject.toml

textimge节点增加对otf后缀字体支持

__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 +991,7 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "IncrementingListNode_":"Create Incrementing Number List ♾️Mixlab",
     "LoadImagesToBatch":"Load Images(base64) ♾️Mixlab",
     "PreviewMask_":"Preview Mask",
-    "AudioPlay":"Audio Play ♾️Mixlab",
+    "AudioPlay":"Preview Audio ♾️Mixlab",
 
      "MultiplicationNode":"Math Operation ♾️Mixlab",
 }
@@ -1097,7 +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/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

@@ -30,17 +30,20 @@ def opencv_to_pil(image):
     return pil_image
 
 # 列出目录下面的所有文件
-def get_files_with_extension(directory, extension):
+def get_files_with_extension(directory, extensions):
     file_list = []
+    # 确保extensions参数是一个list，即使只有一个元素
+    if not isinstance(extensions, (tuple, list)):
+        extensions = [extensions]
     for root, dirs, files in os.walk(directory):
+        # print(f"Files at {root}: {files}")  # 确认files是一个字符串列表
         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)
+            # 检查文件是否以任何一个提供的扩展名结尾
+            if any(file.endswith(ext) for ext in extensions):
+                # 直接将文件名添加到列表中
+                file_list.append(file)
     return file_list
-
+	
 def composite_images(foreground, background, mask, is_multiply_blend=False, position="overall", scale=0.25):
     width, height = foreground.size
     bg_image = background
@@ -161,7 +164,7 @@ 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
@@ -1498,7 +1501,7 @@ class TextImage:
         return {"required": { 
             
                     "text": ("STRING",{"multiline": True,"default": "龍馬精神迎新歲","dynamicPrompts": False}),
-                    "font": (get_files_with_extension(FONT_PATH,'.ttf'),),#后缀为 ttf
+                    "font": (get_files_with_extension(FONT_PATH,['.ttf','.otf']),),#后缀为 ttf
                     "font_size": ("INT",{
                                 "default":100, 
                                 "min": 100, #Minimum value
@@ -1538,7 +1541,7 @@ class TextImage:
 
     def run(self,text,font,font_size,spacing,padding,text_color,vertical,stroke):
         
-        font_path=os.path.join(FONT_PATH,font+'.ttf')
+        font_path=os.path.join(FONT_PATH,font)
 
         if text=="":
             text=" "
@@ -3201,4 +3204,4 @@ class ImageListToBatch_:
 
         out = torch.cat(out, dim=0)
 
-        return (out,)
+        return (out,)

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

@@ -545,12 +545,16 @@ class LoadAndCombinedAudio_:
         if duration > -1:
             crop_audio(audio_file, start_time, duration)
 
-        return (audio_file, {
-                "filename": audio_file_name,
-                "subfolder": "",
-                "type": "output",
-                "audio_path":audio_file
-                } ,)
+        waveform, sample_rate = torchaudio.load(audio_file)
+        audio = {
+            "filename": audio_file_name,
+            "subfolder": "",
+            "type": "output",
+            "audio_path":audio_file,
+            "waveform": waveform.unsqueeze(0), 
+            "sample_rate": sample_rate}
+
+        return (audio_file,audio ,)
 
 class CombineAudioVideo:
     @classmethod
@@ -904,7 +908,7 @@ class scenesNode_:
                      },}
 
     RETURN_TYPES = ('IMAGE','INT',)
-    RETURN_NAMES = ("frames","count",)
+    RETURN_NAMES = ("video frames (batch)","count",)
     # OUTPUT_IS_LIST = (False,)
 
     FUNCTION = "run"
@@ -967,7 +971,7 @@ 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

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui-mixlab-nodes"
 description = "3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other Nodes, ..."
-version = "0.30.2"
+version = "0.30.5"
 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"]
 

web/javascript/audio_mixlab.js

@@ -555,6 +555,7 @@ app.registerExtension({
           e.preventDefault()
           let inputAudio = document.createElement('input')
           inputAudio.type = 'file'
+          inputAudio.accept = "audio/*"
           inputAudio.style.display = 'none'
           inputAudio.addEventListener('change', async e => {
             e.preventDefault()

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 = 'v0.30.2'
+const version =  'v0.30.5'
 
 fetch(`https://api.github.com/repos/${repoOwner}/${repoName}/releases/latest`)
   .then(response => response.json())

web/javascript/ui_mixlab.js

@@ -100,7 +100,7 @@ async function start_llama (model = 'Phi-3-mini-4k-instruct-Q5_K_S.gguf') {
     })
 
     const data = await response.json()
-    if (data.llama_cpp_error) {
+    if (data.llama_cpp_error||!data.port) {
       return
     }