MULTIMODAL AI - AI Dynamics

Language Quantized AutoEncoders Enable Few-Shot Image Classification

By

–

20 February 2023 15h07

6). Language Quantized AutoEncoders (LQAE) – an unsupervised method for text-image alignment that leverages pretrained language models; it enables few-shot image classification with LLMs.

→ View original post on X — @dair_ai

20 February 2023

pix2pix3D: 3D-Aware Conditional Generative Model for Image Synthesis

By

@dair_ai

–

20 February 2023 15h07

3). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis. https://t.co/Xkmw0NJieC
— DAIR.AI (@dair_ai) 20 février 2023

3). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis.

→ View original post on X — @dair_ai

20 February 2023

Electron Microscope Photograph of Two Cells in Love

By

@hardmaru

–

20 February 2023 13h06

Electron microscope photograph of 2 cells in love with each other. #StableDiffusion2 #AIart

→ View original post on X — @hardmaru

20 February 2023

VR and Stable Diffusion Creating Impressive Creative Results

By

@dotcsv

–

20 February 2023 1h48

La gente haciendo ya cosas muy chulas combinando VR y Stable Diffusion. Y fijaos que esto aún no está usando modelos 3D, sino texturas planas. Y aún así el resultado es bastante interesante. https://t.co/DUeUIbE4Sq
— Carlos Santana (@DotCSV) 20 février 2023

La gente haciendo ya cosas muy chulas combinando VR y Stable Diffusion. Y fijaos que esto aún no está usando modelos 3D, sino texturas planas. Y aún así el resultado es bastante interesante.

→ View original post on X — @dotcsv

20 February 2023

Real-time 3D renders from 2D drawings: ChatGPT for 3D assets

By

@aibreakfast

–

19 February 2023 23h23

3D renders (and images) based on a 2D drawing, editable in real-time.

Incredible.

This could be the ChatGPT for 3D assets ↓ pic.twitter.com/FBuxAo9Pss
— AI Breakfast (@AiBreakfast) 19 février 2023

3D renders (and images) based on a 2D drawing, editable in real-time. Incredible. This could be the ChatGPT for 3D assets ↓

→ View original post on X — @aibreakfast

19 February 2023

Free extension adds layers to GPT with voice and data

By

@aibreakfast

–

19 February 2023 22h14

This is a pretty simple, free extension. The voice tech is old, but it shows how easy it is to add layers to GPT. Digital faces, custom voices, and customized data to pull from (the complete works of a particular author, for instance) can all be easily added layers to create an

→ View original post on X — @aibreakfast

19 February 2023

Real-time voice conversations with ChatGPT via Chrome extension and ElevenLabs

By

@aibreakfast

–

19 February 2023 21h55

Real-time voice conversations with ChatGPT: This Chrome extension allows you to have a back-and-forth voice dialogue with ChatGPT. Soon we could see this with photorealistic avatars, and custom voice cloning using @elevenlabs

→ View original post on X — @aibreakfast

19 February 2023

Vision Transformers: Next Video on Visual Recognition Systems

By

@jeande_d

–

18 February 2023 13h40

The next video will be about Vision Transformers. (Vision) Transformers are an integral part of current large-scale visual recognition systems and have made it easy to build multimodal systems, language and vision in particular. Working on it slowly, but surely.

→ View original post on X — @jeande_d

18 February 2023

Solve Rubik’s Cube with Augmented Reality and AI

By

@pascal_bornet

–

18 February 2023 6h30

Learn how to solve your Rubik's Cube using Augmented Reality and AI#augmentedreality #artificialintelligence pic.twitter.com/rvqQ93DMVw
— Pascal Bornet (@pascal_bornet) 18 février 2023

Learn how to solve your Rubik's Cube using Augmented Reality and AI #augmentedreality #artificialintelligence

→ View original post on X — @pascal_bornet

18 February 2023