LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. To enhance the generation quality and generalization ability, we scale up the training data to about 69 million high-quality frames, adopt a mixed image-video training strategy, upgrade the network architecture, and design better motion transformation and optimization objectives. Additionally, we discover that compact implicit keypoints can effectively represent a kind of blendshapes and meticulously propose a stitching and two retargeting modules, which utilize a small MLP with negligible computational overhead, to enhance the controllability.

page: https://liveportrait.github.io/

paper: https://arxiv.org/abs/2407.03168

code: https://github.com/KwaiVGI/LivePortrait

jupyter: https://github.com/camenduru/LivePortrait-jupyter

https://news.1rj.ru/str/DataScienceT ⭐️

Guess what? There's a chance to snag 10 million $Whale tokens! 🐳

And the best part? You can get them for FREE right now! 🎁

Here’s how:

1️⃣ Share your referral link from the "Earn" section at @Whale.
2️⃣ Every USD you earn equals a $Whale token.
3️⃣ Earn cash bonuses for every friend you invite!

Get your tokens before they’re all gone! 🥰

⚡️⚡️ SAM v2 is out! ❤️‍🔥❤️‍🔥

✅ #Meta announced SAM 2, the novel unified model for real-time promptable segmentation in images and videos. 6x faster, it's the new SOTA by a large margin. Source Code, Dataset, Models & Demo released under permissive licenses 💙

🔗 Review: https://t.ly/oovJZ

✅ Paper: https://t.ly/sCxMY

✅ Demo: https://sam2.metademolab.com

🔥 Project: ai.meta.com/blog/segment-anything-2/

⭐️ Models: github.com/facebookresearch/segment-anything-2

https://news.1rj.ru/str/DataScienceT 🗣

🖥 StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset.

🖥 Github: https://github.com/huochf/StackFLOW

📕 Paper: https://arxiv.org/abs/2407.20545v1

🚀 Dataset: https://paperswithcode.com/dataset/behave

https://news.1rj.ru/str/DataScienceT ⭐️

This channels is for Programmers, Coders, Software Engineers.

0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages

✅ https://news.1rj.ru/str/addlist/8_rRW2scgfRhOTc0

✅ https://news.1rj.ru/str/Python53

⚡️ EMO-Disentanger

🖥 Github: https://github.com/yuer867/emo-disentanger

📕 Paper: https://arxiv.org/abs/2407.20955v1

🚀 Dataset: https://paperswithcode.com/dataset/emopia

https://news.1rj.ru/str/DataScienceT ⭐️

✅ Don't worry about data for your projects anymore!
🔻 Get to know MagPie-Ultra, the first quality synthetic dataset!

👨🏻‍💻 Have you ever thought about what makes artificial intelligence projects and machine learning models work better and smarter? The answer is simple: quality data!

✅ Now with MagPie-Ultra, the first synthetic dataset created by Llama 3.1 405B-Instruct advanced artificial intelligence model, you have a ready, high-quality and diverse dataset for training and improving artificial intelligence models , which can make your projects more accurate and smarter and reach Help for better results.👇

┌ 💸 MagPie-Ultra
├ 🖥 Pipeline
└ 💰 Dataset

🌐 https://news.1rj.ru/str/DataScienceT ⭐️

✅ Good evening: We have launched an urgent donation campaign in order to continue our channels with the momentum you are accustomed to. Contribute if you think our work deserves thanks.

🥇 BTC:
bc1qgjmr3ffh48jw5vw2tqad9useumutt5tql0pa6w

💲 USDT TRC20:
TMzAr8AFcZ1n5RXZa3BHPXHBRqugx9Skr7

🐬 TON:
UQAVMaOmfh8vsaXTykpBX45A3tsYv4Guo09eMw1Tl_uSYFcq

🏦 PAYPAL:
https://www.paypal.me/HusseinSheikho

No learning rates needed: Introducing SALSA - Stable Armijo Line Search Adaptation

💻 Github: https://github.com/themody/no-learning-rates-needed-introducing-salsa-stable-armijo-line-search-adaptation

📕 Paper: https://arxiv.org/abs/2407.20650v1

✈️ Dataset: https://paperswithcode.com/dataset/cifar-10

🌐 https://news.1rj.ru/str/DataScienceT ⭐️

DeepInteraction & DeepInteraction++

🖥 Github: https://github.com/fudan-zvg/deepinteraction

📕 Paper: https://arxiv.org/abs/2408.05075v1

🚀 Dataset: https://paperswithcode.com/dataset/nuscenes

🐋 WHALE — TOKEN, NFT, AND A BRIGHT FUTURE AHEAD 🐋

Exciting News, Friends! 🚀

@whale has just unveiled their new roadmap, and it’s packed with potential! According to their plans, the value of their NFT is set to rise significantly in the near future 🐳📈

And that’s not all! They’re also hosting an airdrop of 10 million $Whale tokens,💰 which you can claim right now!

⭐️ Claim Your Share:
🟠 Referral System: Earn tokens by inviting friends to join.
🟠 Winnings (Coming Soon): Every $1 you win = $1Whale!

If you are not with them yet, now is the perfect time to join! 👇

Paper Name: The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper: https://arxiv.org/pdf/2408.06292v2.pdf

Code: https://github.com/sakanaai/ai-scientist

🌐 https://news.1rj.ru/str/DataScienceT ⭐️