github.com
Talking, drawing and editing with visual foundation models
Visual ChatGPT is a system that allows talking to ChatGPT with words and images, enabling complex visual questions and multi-step instructions. It combines various visual models with ChatGPT to study how pictures can help ChatGPT learn more.
AI regulatory intelligence platform 🌱 Sponsored
Advanced image generation and editing model
Browser-based video editing with GPU acceleration.
CSS modern data visualization framework
Foundation model for embodied robot manipulation.
Revolutionizing Language Models with DBRX
Fully Open Foundation Model for Sovereign AI
Exploring the quirks of cartography and data visualization.
Visualizations and techniques for maze generation algorithms.
Open-weight multimodal agentic model with vision.
Create video tutorials with AI that edits and fixes mistakes
Create rich visualizations with AI
What to watch next
Remove unwanted things from images in seconds
Infinitely generated text adventure powered by deep learning.
Explore more than 664 billion web pages saved over time
哥斯拉跳舞
By zacarias on January 11, 2024