AI

Why nothing In AI is every dead.Zero shot and EBsynth come together for a revival for a new vid2vid tool.Will be testing this today to see if maybe, just maybe, we have something that can do lips.Code below. pic.twitter.com/fmc62dowha— AmliArt (@amli_art) March 20, 2024

DiffMorpher demo is outUnleashing the Capability of Diffusion Models for Image Morphingdemo: https://t.co/0WLDi0VYqBGiven two input images, approach can generate a smooth and natural transition video between them.This is achieved purely by leveraging the prior knowledge of… pic.twitter.com/E7d7UVs9MV— AK (@_akhaliq) December 24, 2023

Official implementation of DreaMoving. Contribute to dreamoving/dreamoving-project development by creating an account on GitHub.

FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injectionpaper page: https://t.co/HyM3AunFpYRecently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D… pic.twitter.com/dYUAmZRTmk— AK (@_akhaliq) December 15, 2023

Open AI released a great Prompt Engineering guide (link in comments). Here is a summary of their 6 strategies for getting better results when prompting GPT-4 pic.twitter.com/QiBASsbOHD— MindBranches (@MindBranches) December 15, 2023

Resemble AI just released a Speech Super Resolution AI Model 🗣️Enhance is an open-source speech enhancement model that transforms noisy audio into noteworthy speechvideo showcasing Enhance improving a classic Robert Feynman lecture pic.twitter.com/NcNmdNBRVy— AK (@_akhaliq) December 15, 2023

Segment Anything Model (SAM) now runs at 30 FPS on an iPhone! 🤯EdgeSAM is the first SAM variant that can run at over 30 FPS on an iPhone 14 with good quality. Low how accurately it segments tiny vegetables!Code and @HuggingFace demo below! ⬇️⬇️ pic.twitter.com/tEQqysbXHa— Alex Carlier (@alexcarliera) December 13, 2023

MotionDirector: Motion Customization of Text-to-Video Diffusion Models. - GitHub - showlab/MotionDirector: MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

Visual Electric — the first image generator designed for creatives.You can start trying this out for free on the link below pic.twitter.com/UQrwqVDfFR— Linus (●ᴗ●) (@LinusEkenstam) December 6, 2023

SDXL Turbo is out, and it's incredible. It's a real-time text-to-image generation model by Stability AI. And wow, it's FAST.Here are the most mind-blowing examples I've found:— Nathan Lands (@NathanLands) November 29, 2023

spaCy is a free open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more.

The Stable Diffusion search engine