Google Driver: download our pre-trained model from this link (main checkpoints) and gfpgan (offline patch) We also provide an offline patch ( gfpgan/), thus, no model will be downloaded when generating. You can run the following script to put all the models in the right place. More tips about installnation on Macbook and the Docker file can be founded here □ 2. Run start.bat from Windows Explorer as normal, non-administrator, user, a gradio WebUI demo will be started.Download the checkpoint and gfpgan below↓.Download our SadTalker repository, for example by running git clone.Install ffmpeg, following this instruction (OR using scoop install ffmpeg via scoop). ![]() Install git manually (OR scoop install git via scoop).Install Python 3.10.6, checking "Add Python to PATH".# pip install TTS Windows ( 中文windows教程): Tutorials from communities: 中文windows教程 | 日本語コース Linux:Ĭreating the env and install the requirements. If you have any problem, please view our FAQ before opening an issue. integrade with stable-diffusion-web-ui.Generating 4D free-view talking examples from audio and a single image.Generating 2D face from a single Image.: v0.0.2, full image animation, adding baidu driver for download checkpoints. : ❗️ ❗️ ❗️ In v0.0.2, we add a logo watermark to the generated video to prevent abusing since it is very realistic. : Fixed the sd-webui safe issues becasue of the 3rd packages, optimize the output path in sd-webui-extension. : adding a more detailed sd-webui installation document, fixed reinstallation problem. : Adding automatic1111 colab by thanks for this awesome colab. □ Changelog (Previous changelog can be founded here) □ Happy to see more community demos at bilibili, Youtube and twitter #sadtalker. Input image Several new mode, eg, still mode, reference mode, resize mode are online for better and custom applications. □ full image mode is online! checkout here for more details.□ The extension of the stable-diffusion-webui is online. ![]() TL DR: single portrait image □♂️ + audio □ = talking head video □. 1 Xi'an Jiaotong University 2 Tencent AI Lab 3 Ant Group
0 Comments
Leave a Reply. |