Expired50% confidenceFactExact time
SenseTime is reportedly developing a multimodal image large model called U1 Pro, internally benchmarked against GPT Image 2, targeting design scenarios, supporting long-range generative review loops, and capable of outputting at up to 8K resolution.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
Sources
GPT-5.6 Three-Tier Model Lineup Leaked, OpenAI May Delay IPO to Next Year
bilibili阿梨Aria早鸟报6/26/2026
Related Claims
UnverifiedImagen的核心架构基于大规模语言模型（如T5-XXL）作为文本编码器，配合级联式扩散模型进行图像生成73% similarUnverified该工具的技术基础是多模态大模型与视频理解技术的协同，包括计算机视觉分析画面构图色彩镜头切换、NLP理解字幕配音文案、时序建模捕捉帧间运动和剪辑节奏72% similarUnverifiedCodex's built-in image_gen skill can call the GPT image model to generate images, and the computer use plugin includes operations such as app control, screen recording, and keyboard input.72% similarUnverifiedImage 2.0 represents a qualitative leap over GPT-4o's image generation capabilities in areas such as text rendering accuracy, logical structure visualization, and style consistency.71% similarUnverifiedThe N2 model supports multimodal input and can understand screenshots and design drafts, allowing developers to directly provide the model with UI design draft screenshots or hand-drawn interface sketches.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/392927API
curl https://kongchang.com/api/v1/knowledge/claims/392927MCP
get_claim(id=392927)