MULTIMODAL AI

–

14 December 2022 20h47

Photo by AI, video by AI, text by AI:

→ View original post on X — @actuiafr

14 December 2022

Thales Launches Multimodal Biometric Module for Facial and Iris Recognition

By

@actuiafr

–

14 December 2022 12h48

The new multimodal biometric module from @thalesgroup combines facial and iris recognition https://actuia.com/actualite/le-nouveau-module-biometrique-multimodal-de-thales-combine-reconnaissance-faciale-et-de-liris/
… #AI #artificialintelligence #security

14 December 2022

Face Recognition Model Quality Issues Pre-Tuning

By

–

14 December 2022 0h32

Pic example of how bad it is at faces pre-tuning

14 December 2022

SD Resolution Limits and Future Improvements for Image Quality

By

–

13 December 2022 20h12

Also a lot is it due to 512×512 limit of SD1.5, with SD2 u can do 786×786 so it gets better, but we're all upscaling so real details we will get in a few months when we can do 1024×1024 and 2048×2048 etc after, it will exponentially get better

Pre-finetuning AI models on user facial data

By

–

13 December 2022 20h11

Yep this is pre-finetune on user's face

Avatar AI Achieves Photorealistic Progress in Daily Updates

By

→ Voir le post original sur X — @levelsio

–

13 December 2022 19h15

Daily http://
avatarai.me photorealistic progress pics 2

Avatar AI Achieves Photorealistic Progress in Daily Updates

By

–

13 December 2022 19h14

Daily http://
avatarai.me photorealistic progress pics

→ View original post on X — @googleai

Robotics Transformer 1: Multi-Task Robot Learning Model

By

@googleai

–

13 December 2022 18h47

Introducing the Robotics Transformer 1, a multi-task model that tokenizes robot inputs and outputs actions to enable efficient inference at runtime. Learn how it improves zero-shot generalization to new tasks, environments and objects → https://t.co/hnsKvCJjmP pic.twitter.com/g9QFXzjs9T
— Google AI (@GoogleAI) 13 décembre 2022

Introducing the Robotics Transformer 1, a multi-task model that tokenizes robot inputs and outputs actions to enable efficient inference at runtime. Learn how it improves zero-shot generalization to new tasks, environments and objects → https://
goo.gle/3Yxomnt

→ View original post on X — @aiatmeta

Meta AI Unveils data2vec 2.0: 16x Faster Self-Supervised Learning

By

@aiatmeta

–

13 December 2022 16h01

Announcing data2vec 2.0, a new general self-supervised algorithm built by Meta AI for speech, vision & text that can train models 16x faster than the most popular existing algorithm for images while achieving the same accuracy. Read more & get the open source code