Skip to content

Commit

Permalink
数字人视频播放器新增Sadtalker、GeneFace++
Browse files Browse the repository at this point in the history
  • Loading branch information
Ikaros-521 committed Mar 18, 2024
1 parent 9b775f5 commit fb4e802
Show file tree
Hide file tree
Showing 5 changed files with 11 additions and 2 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@

`Luna AI` 是一款结合了最先进技术的虚拟AI主播。它的核心是一系列高效的人工智能模型,包括 `ChatterBot、GPT、Claude、langchain、chatglm、text-generation-webui、讯飞星火、智谱AI、谷歌Bard、文心一言、通义星尘、通义千问、千帆大模型、Gemini、Kimi Chat、QAnything、koboldcpp、FastGPT`。这些模型既可以在本地运行,也可以通过云端服务提供支持。当然,为了让对话照进现实,还结合了多模态模型,包括 `Gemini` 的图像识别能力,获取电脑画面进行分析讲解。

`Luna AI` 的外观由 `Live2D、Vtube Studio、xuniren、UE5 结合 Audio2Face、EasyAIVtuber、数字人视频播放器(Easy-Wav2Lip)` 技术打造,为用户提供了一个生动、互动的虚拟形象。这使得 `Luna AI` 能够在各大直播平台,如 `Bilibili、抖音、快手、微信视频号、斗鱼、YouTube、Twitch 和 TikTok`,进行实时互动直播。当然,它也可以在本地环境中与您进行个性化对话。
`Luna AI` 的外观由 `Live2D、Vtube Studio、xuniren、UE5 结合 Audio2Face、EasyAIVtuber、数字人视频播放器(Easy-Wav2Lip、Sadtalker、GeneFace++` 技术打造,为用户提供了一个生动、互动的虚拟形象。这使得 `Luna AI` 能够在各大直播平台,如 `Bilibili、抖音、快手、微信视频号、斗鱼、YouTube、Twitch 和 TikTok`,进行实时互动直播。当然,它也可以在本地环境中与您进行个性化对话。

为了使交流更加自然,`Luna AI` 使用了先进的自然语言处理技术,结合文本转语音系统,如 `Edge-TTS、VITS-Fast、elevenlabs、bark-gui、VALL-E-X、睿声AI、genshinvoice.top、tts.ai-lab.top、OpenVoice、GPT_SoVITS、clone-voice、Azure TTS、fish-speech`。这不仅让它能够生成流畅的回答,还可以通过 `so-vits-svc 和 DDSP-SVC` 实现声音的变化,以适应不同的场景和角色。

Expand Down
1 change: 1 addition & 0 deletions config.json
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
"api_ip_port": "http://127.0.0.1:7888"
},
"digital_human_video_player": {
"type": "easy_wav2lip",
"api_ip_port": "http://127.0.0.1:8091"
},
"play_audio": {
Expand Down
1 change: 1 addition & 0 deletions config.json.bak
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
"api_ip_port": "http://127.0.0.1:7888"
},
"digital_human_video_player": {
"type": "easy_wav2lip",
"api_ip_port": "http://127.0.0.1:8091"
},
"play_audio": {
Expand Down
1 change: 1 addition & 0 deletions utils/audio.py
Original file line number Diff line number Diff line change
Expand Up @@ -349,6 +349,7 @@ async def digital_human_video_player_api(self, audio_path=""):
url = urljoin(self.config.get('digital_human_video_player', 'api_ip_port'), "/show")

data = {
"type": self.config.get('digital_human_video_player', 'type'),
"audio_path": os.path.abspath(audio_path),
"insert_index": -1
}
Expand Down
8 changes: 7 additions & 1 deletion webui.py
Original file line number Diff line number Diff line change
Expand Up @@ -1557,6 +1557,7 @@ def common_textarea_handle(content):
config_data["EasyAIVtuber"]["api_ip_port"] = input_EasyAIVtuber_api_ip_port.value

if config.get("webui", "show_card", "visual_body", "digital_human_video_player"):
config_data["digital_human_video_player"]["type"] = select_digital_human_video_player_type.value
config_data["digital_human_video_player"]["api_ip_port"] = input_digital_human_video_player_api_ip_port.value

"""
Expand Down Expand Up @@ -3501,8 +3502,13 @@ def clear_tts_common_audio_card(file_path):

if config.get("webui", "show_card", "visual_body", "digital_human_video_player"):
with ui.card().style(card_css):
ui.label("digital_human_video_player")
ui.label("数字人视频播放器")
with ui.row():
select_digital_human_video_player_type = ui.select(
label='类型',
options={"easy_wav2lip": "easy_wav2lip", "sadtalker": "sadtalker", "genefaceplusplus": "GeneFacePlusPlus"},
value=config.get("digital_human_video_player", "type")
).style("width:150px")
input_digital_human_video_player_api_ip_port = ui.input(label='API地址', value=config.get("digital_human_video_player", "api_ip_port"), placeholder='对接 数字人视频播放器 监听的ip和端口')


Expand Down

0 comments on commit fb4e802

Please sign in to comment.