SenseTime Secretly Developing Multimodal Model U1Pro: Led by Lin Dahua, Expected to Launch Internal Testing in July, Targeting OpenAI

SenseTime is currently secretly developing a multimodal large model for the "design" scenario, internally named "U1Pro". As a new member of SenseTime's "Ri Ri Xin" model family, the model is led by Lin Dahua, co-founder and chief scientist of SenseTime, aiming to compete with OpenAI's GPT-Image2, creating an image generation model with long-term logical capabilities and the ability to think. It is reported that "U1Pro" is expected to start internal invitation testing in July this year and officially provide services to customers.

In the text-to-image field, OpenAI's GPT-Image2 has significantly outperformed Google's Nano Banana2 in the LMSYS Chatbot Arena rating, due to its performance in image quality, text rendering, and instruction following, drawing widespread attention from the design industry. SenseTime's launch of "U1Pro" directly targets this core market. According to insiders, the model can achieve a "design-generation-review" long-cycle for complex design needs and supports ultra-high resolution output up to 8K. In extensive internal evaluations, the generated results of "U1Pro" under the same prompt words have highly approached GPT-Image2, and even showed advantages in some dimensions.

SenseTime Enters the Intelligent Agent Arena: New All-Modal Base Model is Ready to Launch

The competition in large models is shifting towards agents. SenseTime is developing the industry's first natively multimodal agent base, integrating a unified core of "understanding, generation, and action", directly benchmarking against GPT-Image 2, and pushing AI from passive Q&A to active execution.....

SenseTime Open Sources SenseNova U1, Achieving a Multimodal Native Unified Architecture

SenseTime has released and open-sourced the SenseNova U1 series of models, based on its self-developed NEO-unify architecture, achieving deep unification of multimodal understanding, reasoning, and generation, marking a transition from an integrated approach to a native unified one. The architecture discards the modular design, eliminating visual encoders and variational autoencoders, thereby improving model efficiency and performance.

SenseTime Launches the Industry's First Multi-Series Generative AI Agent Seko2.0, Domestic AI Chip Successfully Integrates the Full Multimodal AIGC Pipeline

SenseTime launches Seko2.0, the world's first AI agent for multi-scene video generation, enabling continuous narratives from single clips. It ensures high consistency in characters, scenes, and style, advancing plot coherence and visual uniformity, scalable for short videos, ads, and education, powered by its proprietary multimodal model.....

New GoT-R1 Multimodal Model Released: Making AI Drawing Smarter, the New Era of Image Generation!

Recently, a research team from the University of Hong Kong, The Chinese University of Hong Kong, and SenseTime has released a groundbreaking framework - GoT-R1. This new multimodal large model significantly enhances the semantic and spatial reasoning capabilities of AI in visual generation tasks by introducing reinforcement learning (RL), successfully generating high-fidelity and semantically consistent images from complex text prompts. This advancement marks another leap in image generation technology. Currently, although existing multimodal large models have made significant progress in generating images based on text prompts

SenseTime's Vimi Camera Renamed to Performance Package APP Now Officially Launched in Various App Stores

Recently, SenseTime's Vimi Camera was officially renamed to Performance Package APP and has been launched in major app stores. According to reports, the Performance Package APP is an AI performance application designed for creative and expressive content creators, featuring powerful generation functions and an active creative community. Users can easily portray classic characters through the AI role-playing feature; utilize the AI voice changer to achieve a variety of voice transformations; and interact with other creators in the creative community to spark more creative ideas.