Latest AI

Generate 3D images from text (prompt). Accelerates the creation of 360° interactive content

Generate 3D models from text (prompt). Benefit from 2D diffusion and 3D data consistency

Understand and edit your videos with precise spatio-temporal localization, object detection, and comprehensive editing instructions. The model analyzes long videos, answers your questions, and automates cropping, transitions, and narration

Interactive, real-time, scalable video simulations: smooth at 1080p/60 fps, multimodal generation from images or text, and granular editing via prompts

An AI capable of making an avatar speak while simulating very realistic facial expressions and emotions. A project still in development

A high-resolution image generator (up to 2K), with accurate rendering of Chinese and English text, even at small sizes. Enjoy remarkable speed and visual quality

An AI that automatically inserts an invisible Watermark on your images, allowing you to easily identify them later

An AI application for creating pro videos automatically. Write, produce and edit a video clip from your browser. Coming soon with Gemini

A generative AI assistant with capabilities similar to ChatGPT created by the famous Apple firm. Currently in the planning stage

A technology that transforms your images into 3D scenes that can be explored in your browser. Add camera effects, change the lighting and navigate worlds generated from famous photos or…

An image generator developed by Nvidia that uses the Key-Locking technique to create customized concepts without overfitting

Transforms 2D video into detailed 3D structures. Ideal for game development and virtual object creation