Tencent Hunyuan
A large language model developed by Tencent, supporting a range of AI application scenarios including code generation and conversational interaction.
Core Facts
WorkBuddy layers capabilities such as local file reading and writing, GUI manipulation, and domestic office software API integration on top of foundation models like Tencent Hunyuan.
Tencent Hunyuan 3D team released a technology called WorldClaw, which allows users to generate explorable, editable 3D open-world scenes from a single text description.
Timeline (last 90 days)
Teams from Fudan University, Tencent Hunyuan, and Zhejiang University open-sourced the audio-video joint generation framework Prism, which can natively generate videos with sound at resolutions from 720P and 1080P to 2K.
Tencent released Image 3.5 Preview, with generation capability improved by approximately 30% over the previous generation, supporting fusion retouching with up to 5 reference images, a maximum resolution of 2K, and generating one 2K image via Tencent Cloud API for only 0.15 yuan with no charge for rejected images.
WorkBuddy layers capabilities such as local file reading and writing, GUI manipulation, and domestic office software API integration on top of foundation models like Tencent Hunyuan.
Tencent Hunyuan 3D team released a technology called WorldClaw, which allows users to generate explorable, editable 3D open-world scenes from a single text description.
SAM3D is an extension of Meta's Segment Anything Model to the 3D domain, and Hunyuan3D is a text/image-to-3D generation system developed in-house by the Tencent Hunyuan team.
All Facts (4)
WorkBuddy layers capabilities such as local file reading and writing, GUI manipulation, and domestic office software API integration on top of foundation models like Tencent Hunyuan.
65%VerifiedTencent Hunyuan 3D team released a technology called WorldClaw, which allows users to generate explorable, editable 3D open-world scenes from a single text description.
65%UnverifiedSAM3D is an extension of Meta's Segment Anything Model to the 3D domain, and Hunyuan3D is a text/image-to-3D generation system developed in-house by the Tencent Hunyuan team.
50%UnverifiedTeams from Fudan University, Tencent Hunyuan, and Zhejiang University open-sourced the audio-video joint generation framework Prism, which can natively generate videos with sound at resolutions from 720P and 1080P to 2K.
50%