Hunyuan
@TencentHunyuan
Tencent's large model, encompasses text generation, image generation, video generation, and 3D generation. @ me anytime!
🚀 Introducing Hunyuan-A13B, our latest open-source LLM. As an MoE model, it leverages 80B total parameters with just 13B active, delivering powerful performance that scores on par with o1 and DeepSeek across multiple mainstream benchmarks. Hunyuan-A13B features a hybrid…
This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model…
We're thrilled to release & open-source Hunyuan3D World Model 1.0! This model enables you to generate immersive, explorable, and interactive 3D worlds from just a sentence or an image. It's the industry's first open-source 3D world generation model, compatible with CG pipelines…
Congrats to Lovart as they go live today! We're proud that Hunyuan3D is powering Lovart's innovative vision for AI-powered design. Excited to partner and deliver ultra-high-precision modeling for a smooth and efficient 3D design experience.
No more invite codes. Lovart goes public today. Thanks to the 800,000 of you on our waitlist and our many beta friends who helped us prove Lovart's capabilities – but we wanted to make it better for you. Design agent capabilities are just the beginning. True creativity…
🔴Tencent Zodiac Penguin X Hunyuan 3D Design Contest livestream has begun! Get essential tips & details to create your winning design. Tune in! 👇
Join us for a special livestream on the Tencent Zodiac Penguin X Hunyuan 3D Design Contest! We'll cover everything you need to know to get started and create your winning design. Don't miss out! ⏰July 17, 12:00 UTC x.com/i/broadcasts/1…
🎨Ready to design the next iconic Tencent Zodiac Penguin? Your step-by-step guide to the Zodiac Penguin 3D Design Contest is here! We'll walk you through everything – from logging in to creating your masterpiece and submitting your entry. Get ready to design:…
Major milestone for Hunyuan-large-vision! 🚀 Our multimodal understanding model has secured the #1 spot among Chinese models on the LMSYS Vision Arena leaderboard this week. Globally, we've climbed to #12 overall and an impressive #5 globally when removing style control. See…
🐧Design the Tencent Penguin for the year of the horse with AIGC! For the first time, we're inviting you to co-create the official mascot for our iconic Tencent Zodiac series—a tradition since 2010 with 16 unique designs. Your design could be mass-produced and sold in the…
📢 Design the Next Tencent Collectible Mascot🐧🐴 The Tencent Zodiac Penguin is our beloved annual mascot series, a tradition since 2010 with 16 unique designs, each representing a Chinese zodiac animal. For the 2026 Year of the Horse, we're making history: for the first time…
🚀Thrilled to introduce #ArtifactsBench! We're bridging the visual-interactive gap in code generation evaluation. Our benchmark uses a novel automated, multimodal pipeline to assess LLMs on 1,825 diverse tasks. An MLLM-as-Judge evaluates visual artifacts, achieving 94.4% ranking…
🚀Introducing Hunyuan3D-PolyGen, our newly upgraded and industry-first art-grade 3D generative model. It brings effortless intelligent retopology, making AI-generated models ready for professional art pipelines. ✅ Superior Mesh Topology: Our self-developed mesh autoregressive…
Dive into Hunyuan-A13B, our latest open-source LLM built on an MoE architecture for optimal resource efficiency and high performance. Watch the video to discover its core strengths and how it provides a robust foundation for advancement across academic research, cost-effective…
Check out RLVER — the first RLVR framework to boost LLM empathy, using a simulated user that turns emotional reactions into reward signals. We’re open-sourcing code, checkpoints, and scripts to accelerate research into emotionally intelligent AI! Learn more:…
We've taught LLMs math and code with RLVR. But can we teach them empathy? 🤖❤️ Introducing Reinforcement Learning with Verifiable Emotion Rewards (RLVER), the first RLVR framework that enhances LLMs' empathy from a simulated user . ❤️ Feelings → Numbers: A…
Explore Hunyuan-A13B's innovation and technical details in our tech report👇github.com/Tencent-Hunyua…
The first look on @TencentHunyuan's new LLM looks quite interesting: - Great performance for a 13B activation model (total 80B) - Both pretrain & instruct model released - Native quantization support for Int4 & FP8 via AngleSlim - 256K long context window with possibilities to…
2025.6.27 new LLM open sourced by @TencentHunyuan
🔴 We’re live. Join the Tencent Hunyuan #ICML2025 Frontier Papers Workshop now!