Tencent Opens an 80B Image Model and a Part-Level 3D Generator
- Source
- x.com
- Date
We just hit the top of the Hugging Face trend list with two models! 🏆 🔹HunyuanImage 3.0: The largest and most powerful open-source text-to-image model to date with over 80 billion parameters. The performance is comparable to industry flagship closed-source models. 🔹Hunyuan3D-Part: This open-source part-level 3D shape generation model packing key features like P3-SAM, the industry's first native 3D part segmentation, and X-Part, which delivers SOTA controllability and shape quality. Stop waiting and start building with these powerful models—both are FREE to deploy now! Try them now: HunyuanImage 3.0: https://t.co/s9Jt1RvvzK Hunyuan3D-Part:
Context
The part-level 3D system in Tencent's announcement addresses a production problem: turning a single object mesh into separate components. Hunyuan3D-Part first uses P3-SAM to detect and segment parts and produce their bounding boxes. X-Part then generates complete parts from that decomposition, making component-level work possible. Pipeline documentation.
The repository's notice says the released X-Part is a light version, with the full version offered through Hunyuan3D-Studio. That scope matters when judging the downloadable pipeline against the broader capabilities promoted in the announcement. Release notice.
articleExplorationBench: Feedback and Self-Designed Probes Drive Agent Discovery
postHy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win…
postTencent Hunyuan's EvolveScaler trips up frontier models on evolving facts
postTencent Hunyuan open-sources AuK, a unified speech generation and editing model
Checking sign-in…
Loading comments…