OpenTalker/SadTalker issues and pull requests

#964 - SD下载扩展后，不显示扩展

Issue - State: open - Opened by hellotyj about 24 hours ago

#963 - SUGGESTION: set specific output FPS ?

Issue - State: open - Opened by AlonDan about 1 month ago

#962 - 通过webui能正常生成视频通过api接口无法生成

Issue - State: open - Opened by anyunzhong about 1 month ago

#961 - No module named 'distutils.msvccompiler'

Issue - State: open - Opened by ytlviv about 1 month ago

#960 - Add links in README for downloading more pre-trained models, fix for 'Row' object has no attribute 'style'

Pull Request - State: open - Opened by hixuco about 1 month ago

#959 - Installing requirements for SadTalker WebUI (may take longer time in first time)

Issue - State: open - Opened by MrGan90 about 2 months ago - 1 comment

#958 - My fixes

Pull Request - State: closed - Opened by TiE23 about 2 months ago

#957 - Sadtalker

Issue - State: open - Opened by cnmzsjbz199328 about 2 months ago

#956 - SD extension webui error

Issue - State: open - Opened by pipixie7 2 months ago - 1 comment

#955 - SadTalker generates error

Issue - State: open - Opened by buchenhui 3 months ago

#952 - It is SAD that Sadtalker is Dead

Issue - State: open - Opened by oisilener1982 3 months ago

#951 - 生成视频就错误Error when generating video

Issue - State: open - Opened by huahuaguoke 3 months ago - 1 comment

#950 - The login URL appears for me but I still get an error and cannot open it.

Issue - State: open - Opened by huahuaguoke 3 months ago - 1 comment

#949 - 现在哪个版本可以用?

Issue - State: open - Opened by xiaofanku 3 months ago - 4 comments

#948 - Segmentation Fault in New Installation of SadTalker

Issue - State: open - Opened by yogesh030 4 months ago

#947 - Trojan Detected

Issue - State: open - Opened by islegendary 4 months ago

#945 - 运行inference.py报错，求大神告知怎么解决

Issue - State: open - Opened by guo-huan 4 months ago - 3 comments

#944 - 模型训练

Issue - State: open - Opened by guo-king666 4 months ago - 1 comment

#943 - 即使指定GPU，但是仍然存在部分运算在GPU0 上

Issue - State: closed - Opened by SevenMpp 4 months ago - 1 comment

#942 - tb-nightly版本找不到

Issue - State: open - Opened by gu725 4 months ago

#941 - Any plan to integrate the face vid2vid model trained by Live Portrait?

Issue - State: open - Opened by hoveychen 4 months ago - 2 comments

#940 - How to script a sadTalker face.

Issue - State: open - Opened by Toolfolks 4 months ago

#939 - generate_blink_seq_randomly does not work for 21 frames

Issue - State: open - Opened by SanderGi 5 months ago

#938 - Unenable to use SadTalker Gradio WebUI on Kaggle

Issue - State: open - Opened by HebatullahHesham 5 months ago

#937 - Error executing callback ui_tabs_callback for D:\Program Files\STABLE UI\webui\extensions\SadTalker\scripts\extension.py

Issue - State: closed - Opened by orkun41 5 months ago - 1 comment

#936 - An alternative project EchoMimic is open-sourced

Issue - State: open - Opened by lymhust 5 months ago

#935 - RuntimeError: CUDA error: device-side assert triggered. Help please guys :(

Issue - State: open - Opened by rphoenix136 5 months ago

#934 - 怎样使用样板视频？

Issue - State: open - Opened by luckytalk 5 months ago

#933 - Train from scratch script

Issue - State: open - Opened by sundi133 5 months ago - 1 comment

#932 - Update install.md

Pull Request - State: open - Opened by Mudit18 5 months ago

#931 - FFmpeg cannot edit existing files in-place. Please Help me.

Issue - State: open - Opened by kevin2862 5 months ago - 1 comment

#930 - New Updated Version Doesn't Work!

Issue - State: open - Opened by davidraymondcross 5 months ago - 6 comments

#929 - Not working in Automatic1111 version: v1.9.4

Issue - State: closed - Opened by nitinmukesh 5 months ago - 14 comments

#928 - ValidationError

Issue - State: open - Opened by GP-GUO 5 months ago

#927 - Error: "FFmpeg cannot edit existing files in-place"; but directories are separate

Issue - State: open - Opened by robertdeanmoore 5 months ago

#926 - ERROR: Could not find a version that satisfies the requirement torch==1.12.1+cu113 (from versions: 2.0.0, 2.0.1, 2.1.0, 2.1.1, 2.1.2, 2.2.0, 2.2.1, 2.2.2, 2.3.0, 2.3.1) ERROR: No matching distribution found for torch==1.12.1+cu113 Traceback (most recent call last): File "D:\sad talker\SadTalker\Launcher.py", line 203, in <module> prepare_environment() File "D:\sad talker\SadTalker\Launcher.py", line 187, in prepare_environment run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True) File "D:\sad talker\SadTalker\Launcher.py", line 70, in run raise RuntimeError(f"""{errdesc or 'Error running command'}. RuntimeError: Couldn't install torch. Command: "D:\sad talker\SadTalker\venv\Scripts\python.exe" -m pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113 Error code: 1 Launch unsuccessful. Exiting.

Issue - State: open - Opened by panini0123 6 months ago - 2 comments

#925 - TypeError: TiffWriter.write() got an unexpected keyword argument 'fps'

Issue - State: open - Opened by zachysaur 6 months ago - 1 comment

#924 - MacOS ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

Issue - State: open - Opened by mlvps 6 months ago - 1 comment

#923 - help TnT

Issue - State: open - Opened by dscr945 6 months ago - 1 comment

#921 - 为什么生成的音频的声音不是自己提供的声音，求指教

Issue - State: open - Opened by ck1123456 6 months ago

#920 - Error executing callback ui_tabs_callback for /Users/luanyang/99-rdmiddle/stable-diffusion-webui/extensions/SadTalker/scripts/extension.py

Issue - State: open - Opened by luanyang5986844 6 months ago - 3 comments

#919 - ERROR: Exception: Traceback (most recent call last):

Issue - State: closed - Opened by Carolinett777 6 months ago - 3 comments

#918 - How to force to use directml in SadTalker instead of CUDA or CPU?

Issue - State: open - Opened by cjimenezcmyk 6 months ago - 2 comments

#917 - 音画不同步

Issue - State: open - Opened by haomole 6 months ago - 2 comments

#915 - About Pose Style

Issue - State: open - Opened by 2uocAnh 6 months ago - 2 comments

#914 - torch版本兼容性问题，无法在Mac M3上运行

Issue - State: open - Opened by trempcn 6 months ago

#913 - GFPGAN as Face enhancer 点上特别满进度然后失败进度进行不下去了应该怎么解决呢

Issue - State: open - Opened by lipeng6723 6 months ago

#912 - Multiple GPUs

Issue - State: open - Opened by mf0212 6 months ago

#911 - Fixed paste_pic.py

Pull Request - State: open - Opened by 6DEADSHOT9 7 months ago

#910 - Fixbug bylsdy

Pull Request - State: open - Opened by lsdy 7 months ago

#909 - who can help me

Issue - State: open - Opened by fzy1229 7 months ago - 1 comment

#905 - what's worry??

Issue - State: open - Opened by fzy1229 7 months ago - 1 comment

#904 - Who

Issue - State: open - Opened by ghost 7 months ago - 2 comments

#903 - 我的研究进展

Issue - State: closed - Opened by daikankan 7 months ago

#899 - TypeError: 'ModelManager' object is not subscriptable

Issue - State: open - Opened by cxiaowen 7 months ago - 1 comment

#898 - ERROR: Cannot activate python venv, aborting...

Issue - State: open - Opened by MrMedNajm 7 months ago - 1 comment

#896 - 希望大神光顾这个问题~

Issue - State: closed - Opened by RAYaaaaaaaaaaaaa 7 months ago - 29 comments

#895 - 这个问题怎么解决呀，求大神指点

Issue - State: open - Opened by Ethon1999 7 months ago - 2 comments

#891 - FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints\\auido2pose_00140-model.pth'

Issue - State: open - Opened by keanablase 7 months ago - 6 comments

#890 - add support to macOS GPU for inference

Pull Request - State: open - Opened by huiofficial 7 months ago - 3 comments

#881 - 无法调用GPU参与工作

Issue - State: open - Opened by ThisBug 7 months ago - 1 comment

#878 - ubuntu22.04上部署，看起来是安装TTS出错了

Issue - State: open - Opened by hanqingchina 7 months ago - 7 comments

#876 - 执行推理代码出错，救我

Issue - State: closed - Opened by xiaolong-li1 7 months ago - 1 comment

#865 - mac M1系统按照install.md里通过conda安装成功了，怎么启动web界面呢，有安装成功的小伙伴吗

Issue - State: open - Opened by qwewdrf 8 months ago - 2 comments

#853 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: open - Opened by DevLenn 8 months ago - 11 comments

#840 - 请问可以多显卡处理吗？May I ask if it is possible to use multiple GPU graphics cards?

Issue - State: open - Opened by ffhelly 8 months ago - 2 comments

#838 - 当添加了reference video ，就报错 “exceptions must derive from BaseException ”

Issue - State: open - Opened by yslion 8 months ago - 1 comment

#832 - Apple M1安装错误集合和解决方法

Issue - State: open - Opened by Danny0802 9 months ago - 16 comments

#830 - SadTalker Tab missing on Stable Diffusion Forge (automatic1111) installed on an M1

Issue - State: open - Opened by pete-burgess 9 months ago - 3 comments

#828 - CANNOT ANIMATE TWO FACES SIMULTANEOUSLY? ANY WAY TO DO THIS?

Issue - State: open - Opened by OculusQuestVR 9 months ago - 3 comments

#822 - After updating WebUI 1.8, Sadtalker error appears and the tab is not visible

Issue - State: open - Opened by zaZaza7979 9 months ago - 26 comments

#786 - --pose_style 的0-46分别代表什么动作呢

Issue - State: open - Opened by luyao-cv 11 months ago - 1 comment

#780 - numba Mac M2 install failed?

Issue - State: open - Opened by xieyezi 11 months ago - 4 comments

#779 - sadtalker

Issue - State: open - Opened by zhangnn520 11 months ago - 1 comment

#777 - 各位大佬好，我发现本项目只有推理的部分，请问哪里可以获取训练的代码，我想对一些业务视频进行微调。

Issue - State: open - Opened by zhangnn520 11 months ago - 2 comments

#773 - blue_1_src_image

Pull Request - State: open - Opened by kronkertonk 11 months ago

#770 - Not working

Issue - State: closed - Opened by Dartvauder 11 months ago - 1 comment

#768 - FFmpeg cannot edit existing files in-place

Issue - State: open - Opened by MODOMison 11 months ago - 17 comments

#765 - WebUI Install Issue on Windows - Conda and GitClone python app_sadtalker.py run error

Issue - State: open - Opened by mynumu 11 months ago - 5 comments

#756 - python app_sadtalker.py run error

Issue - State: closed - Opened by ashishakkumar 11 months ago - 6 comments

#749 - Head animations

Issue - State: open - Opened by MaxaAI 12 months ago - 4 comments

#713 - 如何优化嘴部动作和音频对齐

Issue - State: open - Opened by Edanaw about 1 year ago - 1 comment

#708 - 为啥一眨眼头就往下一低，我把什么头部旋转全部置0都没用

Issue - State: open - Opened by xiaoyang333 about 1 year ago - 2 comments

#705 - How did you train this models?

Issue - State: open - Opened by Meshwa428 about 1 year ago - 3 comments

#698 - How to config for shoulders don't move when the head moves?

Issue - State: open - Opened by ThuyyTran about 1 year ago - 3 comments

#693 - AttributeError: 'Row' object has no attribute 'style'

Issue - State: open - Opened by DiosMuerto about 1 year ago - 40 comments

#692 - 启动报错

Issue - State: open - Opened by sleechengn about 1 year ago - 2 comments

#675 - 如何基于 3d facial landmarks~(from 3dmm render)生成 blendshape

Issue - State: open - Opened by chuck-ma about 1 year ago - 1 comment

#674 - How to avoid the moving face frame?

Issue - State: open - Opened by ziyantengrao about 1 year ago - 2 comments

#673 - cv2.error: OpenCV(4.6.0) : -1: error: (-5:Bad argument) in function 'cvtColor'

Issue - State: open - Opened by nemoiee about 1 year ago - 3 comments

#672 - ValueError: input_path must be a valid path to video/image file

Issue - State: open - Opened by nemoiee about 1 year ago - 5 comments

#660 - Cannot run in cpu only mode via docker

Issue - State: open - Opened by risharde about 1 year ago - 3 comments

#659 - Support Inpainting of face regions

Issue - State: open - Opened by doogyhatts about 1 year ago - 2 comments

#639 - support transparent background

Issue - State: open - Opened by jackleibest about 1 year ago - 2 comments

#611 - I encountered a problem at runtime: AttributeError: _2D, how can I solve it?

Issue - State: open - Opened by LGDJCY about 1 year ago - 6 comments

#592 - 生成的音频的声音不是自己提供的声音？

Issue - State: open - Opened by jcxian over 1 year ago - 3 comments

GitHub / OpenTalker/SadTalker issues and pull requests