Andzej Ktowierzy

🔥🎭🌟 New Research Alert - LivePortrait (Avatars Collection)! 🌟🎭🔥
📄 Title: LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control 🔝

📝 Description: LivePortrait is an efficient video-driven portrait animation framework that uses implicit keypoints and stitching/retargeting modules to generate high-quality, controllable animations from a single source image.

👥 Authors: @cleardusk , Dingyun Zhang, Xiaoqiang Liu, Zhizhou Zhong, Yuan Zhang, Pengfei Wan, and Di Zhang

🤗 Demo: https://huggingface.co/spaces/KwaiVGI/LivePortrait

📄 Paper: LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control (2407.03168)

🌐 Github Page: https://liveportrait.github.io/
📁 Repository: https://github.com/KwaiVGI/LivePortrait

🔥 Model 🤖: https://huggingface.co/KwaiVGI/LivePortrait

🚀 CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

🚀 WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

🚀 ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

🔍 Keywords: #LivePortrait #PortraitAnimation #ComputerVision #MachineLearning #DeepLearning #ComputerGraphics #FacialAnimation #GenerativeAI #RealTimeRendering #AI

reacted to prithivMLmods's post with ❤️ about 2 years ago

Post

3287

🚨 New Release: ultralytics8.2.51
🍺Live Space : https://huggingface.co/spaces/prithivMLmods/YOLO-VIDEO , Duplicate the Space to avoid queuing issues.
🍺T4 Colab : https://colab.research.google.com/drive/1BKgFUfk2Me1cSPFmbtZSVCn_4cYImPO-?au
👉🏻For HPC, use A100/T4 under controlled conditions.
👉🏻Speed Estimation, Object Counting, Distance Calculation, Workout Monitoring, Heatmaps,etc.

Ultralytics dropped the YOLOv8 - #Ultralytics 8.2.51 🔥, YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.

🔗 https://pypi.org/project/ultralytics/8.2.58/

🚀More Features You can try:
✅ Classes selection support added
✅ Live FPS display in the sidebar
✅ Webcam and video support added
✅ Confidence and NMS threshold option to modify.
✅ Segmentation, detection, and pose models support added.

🙀Ultralytics Live inference: https://docs.ultralytics.com/guides/streamlit-live-inference/

from ultralytics import solutions
solutions.inference()
### Make sure to run the file using command `streamlit run <file-name.py>`

⚡yolo streamlit-predict

👉🏻Advantages of Live Inference

☑️ Seamless Real-Time Object Detection: Streamlit combined with YOLOv8 enables real-time object detection directly from your webcam feed. This allows for immediate analysis and insights, making it ideal for applications requiring instant feedback.
☑️Efficient Resource Utilization: YOLOv8 optimized algorithm ensure high-speed processing with minimal computational resources.
🙀Ultralytics feature Models: https://docs.ultralytics.com/models/, Ultralytics new Solutions: https://docs.ultralytics.com/solutions/

👉🏻Official Documentation:
Ultralytics YOLOv8 Documentation: Refer to the official YOLOv8 documentation for comprehensive guides and insights on various computer vision tasks and projects. 🔗 https://docs.ultralytics.com/

Andzej Ktowierzy

AI & ML interests

Recent Activity

Organizations

Andzej-75's activity

OpenGPT 4o