lipku/LiveTalking

Issues

• 人物嘴型模糊的问题

  #331 opened 21 hours ago by hour-note
  4

• 使用webrtc+musetalk的时候，视频有时候出现短暂模糊，有时候出现长时间的模糊。

  #332 opened in 3 hours by kkkwjr
  1

• 请问这个项目支持寒武纪或者国产显卡吗？

  #330 opened in 3 hours by ouyangjiajun123
  2

• x264 info输出问题

  #329 opened 21 hours ago by TigerHH6866
  0

• 有没有同学知道，训练后的数字人头部晃动幅度大，且头部忽大忽小一般是什么原因导致的？如何解决？

  #301 opened a month ago by wenjinliu
  3

• teslaT4的显卡驱动的版本号是多少

  #328 opened 3 days ago by qiqi0308
  0

• No module named '_raymarching_face'

  #305 opened a month ago by ZyairYH
  1

• sockjs-0.3.4.js 404错误

  #326 opened 5 days ago by ajiader
  1

• 打断的逻辑如何实现？

  #325 opened 6 days ago by wufxgtihub123
  1

• Connection state is connecting

  #287 opened 2 months ago by xiaomaofei
  1

• torch 1.12.1加裁权重报错，是要升级torch版本吗

  #323 opened 6 days ago by lijihua2017
  3

• 兼容cuda12

  #321 opened 8 days ago by superlbr
  2

• 考虑支持TalkingGaussian？

  #322 opened 8 days ago by superlbr
  3

• wav2lip 效果不好，有方框并且没有牙齿，比较糊，能集成 GFP-GAN 实现高清吗，其他两个模型并发没 wav2lip 好，想用 wav2lip 又不高清

  #318 opened 11 days ago by lijihua2017
  2

• cannot import name '_ignored_ops' from 'torch.utils.checkpoint'

  #320 opened 10 days ago by kkkwjr
  1

• 希望能支持服务端动态切换推理视频

  #319 opened 10 days ago by Surrin1999
  0

• 建议加个UltralightDigitalHuman版本

  #317 opened 13 days ago by cacard
  3

• 推流画质问题

  #288 opened a month ago by Denghongyuan
  5

• 使用srs作为推流服务的话，怎么实现多人对话的时候画面不共享呢。

  #282 opened 2 months ago by okay-good
  2

• 在执行python app.py --transport webrtc可以访问：8010 启用start STUN server 后命令行出现一下错误

  #316 opened 14 days ago by PiaoGengHan
  0

• 使用rtcpush 的方式推送到 srs(5.0版本), 使用rtc2rtmp官方配置, 拉到流之后, 视频变得很模糊, 这个可能是什么原因

  #315 opened 14 days ago by lswc225
  0

• 想问一下大佬们这个是什么错误

  #314 opened 14 days ago by kz-ui
  0

• 能支持语音唤醒跟语音中断的功能吗？

  #313 opened 17 days ago by chentiejin1
  0

• What may have caused the extra noise added to a face during inference after adapting the current code framework in liveTalking from ernerf to Synctalk?

  #302 opened 18 days ago by EYcab
  3

• 怎么实现同多进程并发启动数字人？

  #296 opened a month ago by hmjjj
  9

• 传入的对象None,这是为啥

  #312 opened 19 days ago by surespace1
  0

• 可以改变人物在背景中的位置吗

  #311 opened 19 days ago by fumingren
  0

• musetalk运行成功，但有bug

  #310 opened 22 days ago by min-star
  0

• 能讲讲，wav2lip 推理后，怎么将输出帧跟音频和流的吗？

  #309 opened 24 days ago by fg1813042793
  0

• 整合包 嘴型驱动正常但无语音输出

  #308 opened 24 days ago by chenkai89
  1

• 请问安装机器的硬件要求是什么呀？

  #307 opened a month ago by yun-li
  0

• 更改音色和语速

  #306 opened a month ago by cunning-program-ape
  1

• 我想这个如果能在进行中，切换角色就好了，这样可以适用更多场景

  #286 opened 2 months ago by lin-jj-engine
  3

• 请问不用 srs，换成腾讯云直播的推流服务可以吗？

  #304 opened a month ago by easonjim
  11

• 请问有训练后全身拼接的教程吗

  #289 opened 2 months ago by khk111
  1

• 如何使用fay进行语音输入

  #303 opened a month ago by hzzzwlyjh
  0

• 想问一下，如果要使用GPT-Sovits中他们预训练好的音色该怎么办呢，代码中貌似没看到选择音色的参数，只能克隆音色吗？

  #300 opened a month ago by kkkwjr
  2

• 为啥在autodl上面docker就是用不了呀，人要麻了

  #299 opened a month ago by kkkwjr
  4

• GPT-sovits 丢失一些中间短句的问题

  #292 opened 2 months ago by wangqiang9
  2

• 借助大老思路，我写的一个demo,为什么队里里播放声音很难听，甚至都不对？一卡一卡的~~

  #298 opened a month ago by gg22mm
  2

• 群链接二维码已过期

  #297 opened a month ago by Phoenix500526
  2

• REQ: Any chance of pinokio support please?

  #295 opened a month ago by holycowdude
  0

• 发送文本后，视频卡住，然后控制台报错

  #294 opened a month ago by vingin007
  1

• mimictalk support

  #293 opened 2 months ago by KelvinHuang66
  0

• 离线使用，包括大模型对话，视频生成等

  #291 opened 2 months ago by Crescentz
  0

• 服务器外网ip是什么

  #290 opened 2 months ago by nzx3A1
  0

• 能否提供一个AzureTTS的合成方案，edgetts每次版本更新后都会无法使用

  #285 opened 2 months ago by DBDXSS
  0

• 有利用语音驱动生成手势动作的开源模型吗？了解的是大部分都是只支持头部动作

  #284 opened 2 months ago by chentiejin1
  0

• How to create a digital person service for each page you create

  #283 opened 2 months ago by live-in-the-moment
  0

• Gpt-sovits返回语言后报错

  #281 opened 2 months ago by YuChuanhui3
  0