Google launches open source visual language model: PaliGemma
Supports multiple visual language tasks such as image and video…
AI projects
New SDXL Controlnet line model MistoLine
It can handle all types of line art, whether it…
DeepFacelive: A tool that allows you to change faces in real time during live broadcasts and video calls
DeepFaceLive is based on DeepFaceLab, the currently leading facial exchange…
The new project in this byte of StoryDiffusion performed well
Ability to generate images and videos with rich details and…
Can GPT-4 teach robot hands pen turning skills better than you?
Eureka bridges the gap between high-level reasoning (coding) and low-level…
LGM: Generating high-quality 3D models
Supports text generation models and image generation models with a…
Supertone Shift: Real-time speech converter
You can change your voice when you speak live and…
Apple announces new accessibility features
Including “eye tracking”,”musical touch” and “sound shortcuts” Apple today announced…
Automatically convert your web content to podcasts
Audio Native is an embedded audio player that can automatically…
Robot dog equipped with AI aiming rifle
Robot dog equipped with artificial intelligence aiming rifle is evaluated…
FAIR’s new research: predicting better and faster large language models through multiple tags
Meta AI reintroduced their new paper, accelerating LLM training by…