LivePortrait AI: Transform Static Photos into Talking Videos. Now Supports Video-to-Video Conversion and Superior Expression Transfer at Incredible Speed
A new tutorial is anticipated to showcase the latest changes and features in V3, which introduces Video-to-Video functionality and other enhancements.
This post provides information for both Windows (local) and Cloud installations (including Massed Compute, RunPod, and free Kaggle Account).
The V3 update incorporates video-to-video capabilities. If you’re seeking a one-click installation method for LivePortrait, an open-source zero-shot image-to-animation application on Windows, for local use, this tutorial is essential. It introduces the cutting-edge LivePortrait generator, which creates stunning animations from static images and driving videos in mere seconds. LivePortrait’s exceptional speed and ability to preserve input video facial expressions are truly remarkable.
Windows Local Installation Tutorial ️⤵️
▶️ https://youtu.be/FPtpNrmuwXk
LivePortrait Installers Scripts ⤵️
▶️ https://www.patreon.com/posts/107609670
Requirements Step by Step Tutorial ⤵️
▶️ https://youtu.be/-NjNy7afOQ0
Cloud Massed Compute, RunPod & Kaggle Tutorial (Mac users can follow this tutorial) ⤵️
▶️ https://youtu.be/wG7oPp01COg
Official LivePortrait GitHub Repository ⤵️
▶️ https://github.com/KwaiVGI/LivePortrait
SECourses Discord Channel to Get Full Support ⤵️
▶️ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
Paper of LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control ⤵️
▶️ https://arxiv.org/pdf/2407.03168
The tutorial covers:
0:00 Introduction to LivePortrait
2:20 Downloading and installing LivePortrait Gradio application
3:27 Requirements and installation process
4:07 Verifying correct installation of requirements
5:02 Confirming successful installation and saving logs
5:37 Launching LivePortrait after installation
5:57 Additional materials provided (portrait images, driving video, rendered videos)
7:28 Using LivePortrait
8:06 VRAM usage for generating 73-second animation
8:33 First image animation
8:50 Monitoring animation progress
10:10 First rendered animation video
10:24 Resolution of rendered animations
10:45 Original output resolution of LivePortrait
11:27 Improvements and new features added to the official demo app
11:51 Default save location for generated animations
12:35 Effect of Relative Motion option
13:41 Effect of Do Crop option
14:17 Effect of Paste Back option
15:01 Effect of Target Eyelid Open Ratio option
17:02 Joining SECourses Discord channel
The V3 update includes video-to-video functionality. For those interested in using LivePortrait but lacking a powerful GPU, using a Mac, or preferring cloud-based solutions, this tutorial is ideal. It guides you through the one-click installation process for LivePortrait on #MassedCompute, #RunPod, and even a free #Kaggle account. After following this guide, using LivePortrait on cloud services will be as straightforward as running it on your own computer. LivePortrait is the latest state-of-the-art static image to talking animation generator, surpassing even paid services in both speed and quality.
Cloud (no-GPU) Installations Tutorial for Massed Compute, RunPod and free Kaggle Account ️⤵️
▶️ https://youtu.be/wG7oPp01COg
LivePortrait Installers Scripts ⤵️
▶️ https://www.patreon.com/posts/107609670
Windows Tutorial – Watch To Learn How To Use ⤵️
▶️ https://youtu.be/FPtpNrmuwXk
Official LivePortrait GitHub Repository ⤵️
▶️ https://github.com/KwaiVGI/LivePortrait
SECourses Discord Channel to Get Full Support ⤵️
▶️ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
Paper of LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control ⤵️
▶️ https://arxiv.org/pdf/2407.03168
Upload / download big files / models on cloud via Hugging Face tutorial ⤵️
▶️ https://youtu.be/X5WVZ0NMaTg
How to use permanent storage system of RunPod (storage network volume) ⤵️
▶️ https://youtu.be/8Qf4x3-DFf4
Massive RunPod tutorial (shows runpodctl) ⤵️
▶️ https://youtu.be/QN1vdGhjcRc
The cloud tutorial covers:
0:00 Introduction to LivePortrait cloud tutorial
2:26 Installing and using LivePortrait on MassedCompute with discount
4:28 Applying special Massed Compute coupon for 50% discount
4:50 Setting up ThinLinc client for Massed Compute virtual machine
5:33 Configuring ThinLinc client synchronization folder
6:20 Transferring installer files to Massed Compute sync folder
6:39 Connecting to Massed Compute VM and installing LivePortrait
9:22 Starting and using LivePortrait on MassedCompute
10:20 Running a second LivePortrait instance on the second GPU
12:20 Locating and downloading generated animations
13:23 Installing LivePortrait on RunPod
14:54 Selecting the appropriate RunPod template
15:20 Configuring RunPod proxy access ports
16:21 Uploading installer files to RunPod’s JupyterLab interface
17:07 Launching LivePortrait on RunPod post-installation
17:17 Starting a second LivePortrait instance on RunPod
17:31 Connecting to LivePortrait via RunPod’s proxy connection
17:55 Animating the first image on RunPod with a 73-second driving video
18:27 Animation generation time (impressive speed)
18:41 Troubleshooting input upload errors
19:17 One-click download of all generated animations on RunPod
20:28 Monitoring animation progress
21:07 Installing and using LivePortrait on a free Kaggle account
24:10 Generating the first animation on Kaggle
24:22 Ensuring complete upload of input files to avoid errors
24:35 Tracking animation progress on Kaggle
24:45 Resource usage and animation speed on Kaggle
25:05 Downloading all generated animations on Kaggle
26:12 Restarting LivePortrait on Kaggle without reinstalling
26:36 Joining SECourses Discord channel for support and discussion
暂无评论内容