dmvrg

@[email protected]
244 Followers
268 Following
87 Posts
Product Design x Creative Technology
dmvrgFeb 6, 2023

Gen-1: The Next Step Forward for Generative AI
Use words and images to generate new videos out of existing ones.

https://research.runwayml.com/gen1

Gen-1 by Runway

The Next Step Forward for Generative AI

Runway
dmvrgJan 31, 2023

Shape-aware Text-driven Layered Video Editing

"[A] pre-trained text-conditioned diffusion model as guidance for refining shape distortion and completing unseen regions. The experimental results demonstrate that our method can achieve shape-aware consistent video editing and compare favorably with the state-of-the-art."

https://text-video-edit.github.io

Shape-aware Text-driven Layered Video Editing Demo

Show threaddmvrgJan 31, 2023
[Google] SingSong: Generating musical accompaniments from singing
https://storage.googleapis.com/sing-song/index.html
SingSong: Generating musical accompaniments from singing (Online Supplement)

dmvrgJan 28, 2023

[Google] MusicLM: Generating Music From Text

"We introduce MusicLM, a model generating high-fidelity music from text descriptions such as 'a calming violin melody backed by a distorted guitar riff'. MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. "

https://google-research.github.io/seanet/musiclm/examples

MusicLM

dmvrgJan 23, 2023
Stable Diffusion & OpenCV for Face Detection and Automatic Compositing
https://www.youtube.com/watch?v=ISr_gTkO42M
Tutorial: Stable Diffusion & OpenCV for Face Detection and Automatic Compositing

YouTube
dmvrgJan 23, 2023
Audio-visual Expression Using Image Generation AI — Case Study at MUTEK.JP
https://medium.com/qosmo-lab/audio-visual-expression-using-image-generation-ai-development-case-study-at-mutek-jp-8a6bdaf36e99
Audio-visual Expression Using Image Generation AI — Development Case Study at MUTEK.JP

I was in charge of visuals for Nao Tokui — Emergent Rhythm (AI Generative Live Set) at MUTEK.JP on Thursday, 12/8. Emergent Rhythm” is an improvisational performance built entirely from thre sounds…

Qosmo Lab
dmvrgJan 23, 2023
NVIDIA Broadcast AI-powered eye contact
https://www.nvidia.com/en-us/geforce/news/jan-2023-nvidia-broadcast-update/
NVIDIA Broadcast 1.4 Adds Eye Contact and Vignette Effects With Virtual Background Enhancements

Plus new options to mirror your camera and take a selfie.

NVIDIA
Show threaddmvrgJan 23, 2023
How AI learns “feels right”
https://medium.com/qosmo-lab/how-ai-learns-feels-right-e32a80bfa153
How AI learns “feels right” - Qosmo Lab - Medium

AI is used to solve problems that humans do to make decisions that would otherwise be made only by experts. In business, targets of AI predictions are problems that ultimately have a correct answer…

Qosmo Lab
dmvrgJan 10, 2023
Uncrop: Outpainting With AI
https://neural.love/uncrop
Uncrop Image – Online Outpainting – AI Aspect Ratio Changer – Try It for Free | neural.love

Do you want to synthesize the rest of your image or to uncrop a photo? Our online AI aspect ratio changer is here to help.

dmvrgJan 9, 2023
LALAL.AI — AI-powered service for high-quality extraction of vocals, accompaniment, and various instruments from any audio and video.
https://www.lalal.ai
Vocal Remover & Instrumental AI Splitter | LALAL.AI

Split vocal and instrumental tracks quickly and accurately with LALAL.AI. Upload any audio file and receive high-quality extracted tracks in a few seconds.