AI 导读
商汤发布并开源多模态模型 SenseNova U1,官方称其把看图、思考与创作合并在一个模型里。官方演示中输入一张普通运动鞋图片,即可输出营销视觉素材。模型已上线 SenseNova Studio 供在线试用,并在 Hugging Face 与 GitHub 开放模型与代码。
正文
A plain sneaker image went in. Marketing visuals came out. #SenseNova U1 — see, think, create — all in one model.
#OpenSourced.
This is the architecture shift people keep talking about.
Shoutout @AiLockup for the demo 🔥
🎥Watch the video: piped.video/9IFgPqMWBGg
Try it today:
🎛️ SenseNova Studio: unify.light-ai.top/ (Try infographics; also join Discord for text-image interleaved gen)
🤗 huggingface.co/collections/s…
🛠️ github.com/OpenSenseNova/Sen…
👾 Discord: discord.com/invite/BuTXPHmQu…
@huggingface @github
来源:@SenseTime_AI · x.com