MULTIMODAL AI - AI Dynamics

Transformers and VQGAN: Alternative to Modern Diffusion Models

By

–

03 January 2023 20h38

Y es que a diferencia de Stable Diffusion, DALL-E, Midjourney e Imagen, este modelo no usa las modernas arquitecturas de Diffusion. Sino que recupera la tendencia de 2021: los Transformers y las VQGAN. ¿Y eso qué es…? Pues aquí te lo explico

→ View original post on X — @dotcsv

3 January 2023

Muse generates images 3x faster than Stable Diffusion

By

@dotcsv

–

03 January 2023 20h38

Por último, otra cualidad más de Muse es que es MÁS RÁPIDO que sus otros compañeros, logrando generar imágenes ~3 veces más rápido que Stable Diffusion y entre 8-10 veces más rápido que su hermano mayor, Imagen.

→ View original post on X — @dotcsv

3 January 2023

Comparative Visualization for AI Image Generation Solutions

By

@saboo_shubham_

–

03 January 2023 11h06

Will be good to prepare a comparative visualization for all the AI image generation solutions out there! Will start working on it soon!!

→ View original post on X — @saboo_shubham_

3 January 2023

Hand Movement Control with Uploaded Images in AI Systems

By

@levelsio

–

02 January 2023 23h38

Were you able to move hands with an uploaded image? Haven't been able to yet

→ View original post on X — @levelsio

2 January 2023

Most Impactful Emerging Technologies for Business Predicted

By

@mikequindazzi

–

02 January 2023 17h44

Do you agree with #chatgpt3? >>> What do you predict will be the most impactful #EmergingTech on business? >>> #AI #Analytics #Automation #ImageRecognition #NLP >>> #CES2023

→ View original post on X — @mikequindazzi

2 January 2023

AI-Generated Selfies Through Time: From Ancient Rome to Present

By

@dotcsv

–

02 January 2023 10h13

Esta cuenta, usando Stable Diffusion, nos hace viajar a través del tiempo mediante selfies creados con IA. Y aquí ya se ha superado llevándonos al origen del meme, en la Roma del 46 a.c Maravilloso!

→ View original post on X — @dotcsv

2 January 2023

Limitations of bulk conversion services for short-form video content

By

@alexalbert__

–

02 January 2023 3h33

these services might be suitable for bulk conversion tasks (e.g. an audiobook or other long-form stuff) but for smaller tasks like videos (ads, voiceover, etc) they are still (even the best ones) lacking in their tone, cadence, and emote

→ View original post on X — @alexalbert__

2 January 2023

AI Model Predicts Car Price Make Model From Photo

By

@gdb

–

01 January 2023 21h40

Predicting price/make/model/etc from a photo of a car. Pretty cool that these days you can do this kind of thing as a side project.

→ View original post on X — @gdb

1 January 2023

AI Advances in Human-Like Edge Detection with Line Drawing Models

By

@aibreakfast

–

01 January 2023 2h25

Human-like edge detection has been a complex problem in Computer Vision for decades, but it is getting much better:

"Learning to generate line drawings that convey geometry and semantics" – links, demo, and paper below ↓ pic.twitter.com/Vb7r4wADXm
— AI Breakfast (@AiBreakfast) 1 janvier 2023

Human-like edge detection has been a complex problem in Computer Vision for decades, but it is getting much better: "Learning to generate line drawings that convey geometry and semantics" – links, demo, and paper below ↓

→ View original post on X — @aibreakfast

1 January 2023

2023 Tech Wishes: AI, Learning, Video, Open Models, Robotics

By

@reza_zadeh

–

31 December 2022 23h18

In 2023, may your: – Generative AI produce beautiful images & text
– Active Learning framework ask the right questions – generations be as beautiful as image
– Model be OSS without censors
– Robotics simulation be faithful to real world Happy New Year everyone!

→ View original post on X — @reza_zadeh

31 December 2022