SenseTime is developing a new image model: codenamed U1 Pro, internally claimed to be comparable to OpenAI.

SenseTime Technology is reportedly recently secretly developing a multimodal large model, mainly tailored for “design” scenarios. The project is led by Lin Dahua, SenseTime’s co-founder and chief scientist. It aims to benchmark against OpenAI’s GPT-Image 2 and build an image generation model that is “capable of thinking.” Currently, the model’s internal codename is “U1 Pro,” and it is being advanced by the SenseTime Research Institute, as a member of the SenseTime SenseNova model family. It is expected that in July this year the model will begin internal invitation testing and provide services to customers. (Sina Technology)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned