Update pyproject.toml

textimge节点增加对otf后缀字体支持

__init__.py

@@ -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",
 }

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
@@ -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/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

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui-mixlab-nodes"
 description = "3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other Nodes, ..."
-version = "0.30.3"
+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 = 'v0.30.3'
+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
     }