Merge pull request #301 from harry0703/dev

optimize UI and code

Dockerfile

@@ -1,5 +1,5 @@
 # Use an official Python runtime as a parent image
-FROM python:3.10-bullseye
+FROM python:3.10-slim
 
 # Set the working directory in the container
 WORKDIR /MoneyPrinterTurbo

app/services/llm.py

@@ -213,7 +213,7 @@ Generate a script for a video, depending on the subject of the video.
 
     final_script = ""
     logger.info(f"subject: {video_subject}")
-    logger.debug(f"prompt: \n{prompt}")
+    # logger.debug(f"prompt: \n{prompt}")
     response = _generate_response(prompt=prompt)
 
     # Return the generated script
@@ -241,6 +241,10 @@ Generate a script for a video, depending on the subject of the video.
     else:
         logging.error("gpt returned an empty response")
 
+    # g4f may return an error message
+    if final_script and "当日额度已消耗完" in final_script:
+        raise ValueError(final_script)
+
     logger.success(f"completed: \n{final_script}")
     return final_script
 
@@ -273,7 +277,7 @@ Please note that you must use English for generating video search terms; Chinese
 """.strip()
 
     logger.info(f"subject: {video_subject}")
-    logger.debug(f"prompt: \n{prompt}")
+    # logger.debug(f"prompt: \n{prompt}")
     response = _generate_response(prompt)
     search_terms = []
 

app/services/task.py

@@ -78,7 +78,11 @@ def start(task_id, params: VideoParams):
     if sub_maker is None:
         sm.state.update_task(task_id, state=const.TASK_STATE_FAILED)
         logger.error(
-            "failed to generate audio, maybe the network is not available. if you are in China, please use a VPN.")
+            """failed to generate audio:
+1. check if the language of the voice matches the language of the video script.
+2. check if the network is available. If you are in China, it is recommended to use a VPN and enable the global traffic mode.
+        """.strip()
+        )
         return
 
     audio_duration = voice.get_audio_duration(sub_maker)
@@ -174,7 +178,6 @@ def start(task_id, params: VideoParams):
     sm.state.update_task(task_id, state=const.TASK_STATE_COMPLETE, progress=100, **kwargs)
     return kwargs
 
-
 # def start_test(task_id, params: VideoParams):
 #     print(f"start task {task_id} \n")
 #     time.sleep(5)

app/services/voice.py

@@ -1023,7 +1023,6 @@ def parse_voice_name(name: str):
 
 def is_azure_v2_voice(voice_name: str):
     voice_name = parse_voice_name(voice_name)
-    print(voice_name)
     if voice_name.endswith("-V2"):
         return voice_name.replace("-V2", "").strip()
     return ""

config.example.toml

@@ -34,7 +34,7 @@ listen_port = 8502
     # No need to set it unless you want to use your own proxy
     openai_base_url = ""
     # Check your available models at https://platform.openai.com/account/limits
-    openai_model_name = "gpt-4-turbo-preview"
+    openai_model_name = "gpt-4-turbo"
 
     ########## Moonshot API Key
     # Visit https://platform.moonshot.cn/console/api-keys to get your API key.
@@ -51,7 +51,7 @@ listen_port = 8502
     ########## G4F
     # Visit https://github.com/xtekky/gpt4free to get more details
     # Supported model list: https://github.com/xtekky/gpt4free/blob/main/g4f/models.py
-    g4f_model_name = "gpt-3.5-turbo-16k-0613"
+    g4f_model_name = "gpt-3.5-turbo"
 
     ########## Azure API Key
     # Visit https://learn.microsoft.com/zh-cn/azure/ai-services/openai/ to get more details

requirements.txt

@@ -10,16 +10,16 @@ streamlit~=1.33.0
 loguru~=0.7.2
 aiohttp~=3.9.3
 urllib3~=2.2.1
-pillow~=9.5.0
+pillow~=10.3.0
 pydantic~=2.6.3
-g4f~=0.2.5.4
+g4f~=0.3.0.4
 dashscope~=1.15.0
 google.generativeai~=0.4.1
 python-multipart~=0.0.9
 redis==5.0.3
 # if you use pillow~=10.3.0, you will get "PIL.Image' has no attribute 'ANTIALIAS'" error when resize video
 # please install opencv-python to fix "PIL.Image' has no attribute 'ANTIALIAS'" error
-opencv-python
+opencv-python~=4.9.0.80
 # for azure speech
 # https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/9-more-realistic-ai-voices-for-conversations-now-generally/ba-p/4099471
 azure-cognitiveservices-speech~=1.37.0

webui/Main.py

@@ -41,11 +41,14 @@ hide_streamlit_style = """
 st.markdown(hide_streamlit_style, unsafe_allow_html=True)
 st.title(f"MoneyPrinterTurbo v{config.project_version}")
 
+support_locales = ["zh-CN", "zh-HK", "zh-TW", "de-DE", "en-US", "fr-FR", "vi-VN", "th-TH"]
+
 font_dir = os.path.join(root_dir, "resource", "fonts")
 song_dir = os.path.join(root_dir, "resource", "songs")
 i18n_dir = os.path.join(root_dir, "webui", "i18n")
 config_file = os.path.join(root_dir, "webui", ".streamlit", "webui.toml")
 system_locale = utils.get_system_locale()
+# print(f"******** system locale: {system_locale} ********")
 
 if 'video_subject' not in st.session_state:
     st.session_state['video_subject'] = ''
@@ -185,6 +188,7 @@ with st.expander(tr("Basic Settings"), expanded=False):
                 break
 
         llm_provider = st.selectbox(tr("LLM Provider"), options=llm_providers, index=saved_llm_provider_index)
+        llm_helper = st.container()
         llm_provider = llm_provider.lower()
         config.app["llm_provider"] = llm_provider
 
@@ -192,9 +196,97 @@ with st.expander(tr("Basic Settings"), expanded=False):
         llm_base_url = config.app.get(f"{llm_provider}_base_url", "")
         llm_model_name = config.app.get(f"{llm_provider}_model_name", "")
         llm_account_id = config.app.get(f"{llm_provider}_account_id", "")
+
+        tips = ""
+        if llm_provider == 'ollama':
+            if not llm_model_name:
+                llm_model_name = "qwen:7b"
+            if not llm_base_url:
+                llm_base_url = "http://localhost:11434/v1"
+
+            with llm_helper:
+                tips = """
+                       ##### Ollama配置说明
+                       - **API Key**: 随便填写，比如 123
+                       - **Base Url**: 一般为 http://localhost:11434/v1
+                       - **Model Name**: 使用 `ollama list` 查看，比如 `qwen:7b`
+                       """
+
+        if llm_provider == 'openai':
+            if not llm_model_name:
+                llm_model_name = "gpt-3.5-turbo"
+            with llm_helper:
+                tips = """
+                       ##### OpenAI 配置说明
+                       > 需要VPN开启全局流量模式
+                       - **API Key**: [点击到官网申请](https://platform.openai.com/api-keys)
+                       - **Base Url**: 可以留空
+                       - **Model Name**: 填写**有权限**的模型，[点击查看模型列表](https://platform.openai.com/settings/organization/limits)
+                       """
+
+        if llm_provider == 'moonshot':
+            if not llm_model_name:
+                llm_model_name = "moonshot-v1-8k"
+            with llm_helper:
+                tips = """
+                       ##### Moonshot 配置说明
+                       - **API Key**: [点击到官网申请](https://platform.moonshot.cn/console/api-keys)
+                       - **Base Url**: 固定为 https://api.moonshot.cn/v1
+                       - **Model Name**: 比如 moonshot-v1-8k，[点击查看模型列表](https://platform.moonshot.cn/docs/intro#%E6%A8%A1%E5%9E%8B%E5%88%97%E8%A1%A8)
+                       """
+
+        if llm_provider == 'qwen':
+            if not llm_model_name:
+                llm_model_name = "qwen-max"
+            with llm_helper:
+                tips = """
+                       ##### 通义千问Qwen 配置说明
+                       - **API Key**: [点击到官网申请](https://dashscope.console.aliyun.com/apiKey)
+                       - **Base Url**: 留空
+                       - **Model Name**: 比如 qwen-max，[点击查看模型列表](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction#3ef6d0bcf91wy)
+                       """
+
+        if llm_provider == 'g4f':
+            if not llm_model_name:
+                llm_model_name = "gpt-3.5-turbo"
+            with llm_helper:
+                tips = """
+                       ##### gpt4free 配置说明
+                       > [GitHub开源项目](https://github.com/xtekky/gpt4free)，可以免费使用GPT模型，但是**稳定性较差**
+                       - **API Key**: 随便填写，比如 123
+                       - **Base Url**: 留空
+                       - **Model Name**: 比如 gpt-3.5-turbo，[点击查看模型列表](https://github.com/xtekky/gpt4free/blob/main/g4f/models.py#L308)
+                       """
+        if llm_provider == 'azure':
+            with llm_helper:
+                tips = """
+                       ##### Azure 配置说明
+                       > [点击查看如何部署模型](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/how-to/create-resource)
+                       - **API Key**: [点击到Azure后台创建](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/OpenAI)
+                       - **Base Url**: 留空
+                       - **Model Name**: 填写你实际的部署名
+                       """
+
+        if llm_provider == 'gemini':
+            if not llm_model_name:
+                llm_model_name = "gemini-1.0-pro"
+
+            with llm_helper:
+                tips = """
+                        ##### Gemini 配置说明
+                        > 需要VPN开启全局流量模式
+                       - **API Key**: [点击到官网申请](https://ai.google.dev/)
+                       - **Base Url**: 留空
+                       - **Model Name**: 比如 gemini-1.0-pro
+                       """
+
+        if tips and config.ui['language'] == 'zh':
+            st.info(tips)
+
         st_llm_api_key = st.text_input(tr("API Key"), value=llm_api_key, type="password")
         st_llm_base_url = st.text_input(tr("Base Url"), value=llm_base_url)
         st_llm_model_name = st.text_input(tr("Model Name"), value=llm_model_name)
+
         if st_llm_api_key:
             config.app[f"{llm_provider}_api_key"] = st_llm_api_key
         if st_llm_base_url:
@@ -234,7 +326,7 @@ with left_panel:
         video_languages = [
             (tr("Auto Detect"), ""),
         ]
-        for code in ["zh-CN", "zh-TW", "de-DE", "en-US", "vi-VN"]:
+        for code in support_locales:
             video_languages.append((code, code))
 
         selected_index = st.selectbox(tr("Script Language"),
@@ -300,7 +392,7 @@ with middle_panel:
     with st.container(border=True):
         st.write(tr("Audio Settings"))
         voices = voice.get_all_azure_voices(
-            filter_locals=["zh-CN", "zh-HK", "zh-TW", "de-DE", "en-US", "fr-FR", "vi-VN"])
+            filter_locals=support_locales)
         friendly_names = {
             v: v.
             replace("Female", tr("Female")).
@@ -313,7 +405,7 @@ with middle_panel:
             saved_voice_name_index = list(friendly_names.keys()).index(saved_voice_name)
         else:
             for i, v in enumerate(voices):
-                if v.lower().startswith(st.session_state['ui_language'].lower()):
+                if v.lower().startswith(st.session_state['ui_language'].lower()) and "V2" not in v:
                     saved_voice_name_index = i
                     break
 
@@ -324,6 +416,7 @@ with middle_panel:
         voice_name = list(friendly_names.keys())[list(friendly_names.values()).index(selected_friendly_name)]
         params.voice_name = voice_name
         config.ui['voice_name'] = voice_name
+
         if voice.is_azure_v2_voice(voice_name):
             saved_azure_speech_region = config.azure.get(f"speech_region", "")
             saved_azure_speech_key = config.azure.get(f"speech_key", "")
@@ -434,12 +527,16 @@ if start_button:
     scroll_to_bottom()
 
     result = tm.start(task_id=task_id, params=params)
+    if not result or "videos" not in result:
+        st.error(tr("Video Generation Failed"))
+        logger.error(tr("Video Generation Failed"))
+        scroll_to_bottom()
+        st.stop()
 
     video_files = result.get("videos", [])
     st.success(tr("Video Generation Completed"))
     try:
         if video_files:
-            # center the video player
             player_cols = st.columns(len(video_files) * 2 + 1)
             for i, url in enumerate(video_files):
                 player_cols[i * 2 + 1].video(url)

webui/i18n/de.json

@@ -50,6 +50,7 @@
     "Generating Video": "Video wird erstellt, bitte warten...",
     "Start Generating Video": "Beginne mit der Generierung",
     "Video Generation Completed": "Video erfolgreich generiert",
+    "Video Generation Failed": "Video Generierung fehlgeschlagen",
     "You can download the generated video from the following links": "Sie können das generierte Video über die folgenden Links herunterladen",
     "Basic Settings": "**Grunde Instellungen**",
     "Pexels API Key": "Pexels API Key (:red[Required] [Get API Key](https://www.pexels.com/api/))",

webui/i18n/en.json

@@ -50,6 +50,7 @@
     "Generating Video": "Generating video, please wait...",
     "Start Generating Video": "Start Generating Video",
     "Video Generation Completed": "Video Generation Completed",
+    "Video Generation Failed": "Video Generation Failed",
     "You can download the generated video from the following links": "You can download the generated video from the following links",
     "Pexels API Key": "Pexels API Key (:red[Required] [Get API Key](https://www.pexels.com/api/))",
     "Basic Settings": "**Basic Settings** (:blue[Click to expand])",

webui/i18n/vi.json

@@ -50,6 +50,7 @@
     "Generating Video": "Đang tạo video, vui lòng đợi...",
     "Start Generating Video": "Bắt Đầu Tạo Video",
     "Video Generation Completed": "Hoàn Tất Tạo Video",
+    "Video Generation Failed": "Tạo Video Thất Bại",
     "You can download the generated video from the following links": "Bạn có thể tải video được tạo ra từ các liên kết sau",
     "Pexels API Key": "Khóa API Pexels (:red[Bắt Buộc] [Lấy Khóa API](https://www.pexels.com/api/))",
     "Basic Settings": "**Cài Đặt Cơ Bản** (:blue[Nhấp để mở rộng])",

webui/i18n/zh.json

@@ -19,12 +19,12 @@
     "Video Ratio": "视频比例",
     "Portrait": "竖屏 9:16（抖音视频）",
     "Landscape": "横屏 16:9（西瓜视频）",
-    "Clip Duration": "视频片段最大时长(秒)",
+    "Clip Duration": "视频片段最大时长(秒)（**不是视频总长度**，是指每个**合成片段**的长度）",
     "Number of Videos Generated Simultaneously": "同时生成视频数量",
     "Audio Settings": "**音频设置**",
-    "Speech Synthesis": "朗读声音（:red[尽量与文案语言保持一致]）",
+    "Speech Synthesis": "朗读声音（:red[**与文案语言保持一致**。注意：V2版效果更好，但是需要API KEY]）",
     "Speech Region": "服务区域 (:red[必填，[点击获取](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
-    "Speech Key": "API Key(:red[必填，[点击获取](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
+    "Speech Key": "API Key (:red[必填，密钥1 或 密钥2 均可 [点击获取](https://portal.azure.com/#view/Microsoft_Azure_ProjectOxford/CognitiveServicesHub/~/SpeechServices)])",
     "Speech Volume": "朗读音量（1.0表示100%）",
     "Male": "男性",
     "Female": "女性",
@@ -50,6 +50,7 @@
     "Generating Video": "正在生成视频，请稍候...",
     "Start Generating Video": "开始生成视频",
     "Video Generation Completed": "视频生成完成",
+    "Video Generation Failed": "视频生成失败",
     "You can download the generated video from the following links": "你可以从以下链接下载生成的视频",
     "Basic Settings": "**基础设置** (:blue[点击展开])",
     "Language": "界面语言",