GEAR: 10× faster autoregressive image generation Tencent Hunyuan's new method jointly trains VQ tokenizers and AR generators end-to-end, beating LlamaGen-REPA with a novel dual read-out. All tokenizers are on Hugging Face.

Minimax H3 is the first *open* video model I've seen that outperforms HunyuanVideo 1.5 - which is actually an impressive accomplishment for @TencentHunyuan to have held that throne for so long. For a while now I've been sad that the image/video frontier seemed to be getting much more closed than the text LLM frontier. H3 is a very strong step back in the open direction. This was generated in ~30 min on my AMD laptop:

Introducing Hyra-1.0, the first version of Hunyuan Research Agent. 💡💡💡 Built to recursively improve solutions for performance-driven research and engineering tasks. Explore our demos in AI4AI, AI4Science, and AI4Fun:

🙏 Thank you all for the incredible love and support! Our latest Tencent Hunyuan translation models are on fire on Hugging Face: 🥰Hy-MT2-1.8B ranks #1# 🥰Hy-MT2-30B-A3B ranks #4# on the open-source model trending leaderboard, with over 7K downloads already! To make it even easier for everyone, we’ve launched the Tencent Hy Translation WeChat mini-program, built on Hy-MT2. It supports voice input and offline translation, plus powerful customization of translation styles and instructions — delivering results that better match your expectations and feel far more practical. Try it out and share your feedback with us — we’d love to hear from you! Models on HF: GitHub: #HyMT2# #TencentHunyuan# #OpenSource#

We've just merged its first community contribution! 🚀 6 new models benchmarked and submitted via open PR: DeepSeek, Kimi K2, Hunyuan, Nova Pro, Command A, Jamba and two new countries on the map. 24 models total, from 6 countries. And because trust is the whole point: community runs are displayed flagged as "pending re-verification" until we reproduce them ourselves. Open methodology means anyone can contribute, and nobody, including us, gets taken on faith. Thank you bricepirard-spec. Who's next?

TENCENT $700: AI catalysts last couple days. "Workbuddy" AI agent combined with new HY3 model launch seeing usage growth & news of ex OpenAI researcher becoming new head of "Hunyuan" AI division. Also, obviously a cheap stock and certain parallels w/ MAG7 rotation.

I built a game with Claude Fable 5, and what really surprised me was that Fable automatically generated the rigging-related animations on its own. In the past, I hadn't seen any model capable of creating the animations themselves, not just the assets. As these models become more capable, I think companies like Tripo, Meshy, Hunyuan, and VARCO that specialize in asset creation could become even more valuable. It feels like we're entering an era where assets themselves become the most important form of capital.

I was paying for Meshy. Then I found this repo and cancelled my subscription the same day. Modly is a free, open source desktop app that turns any photo into a 3D model using local AI running entirely on your GPU. No cloud. No account. No credits. Drop in a photo. The app removes the background automatically. A local image-to-3D model reconstructs the mesh on your machine. Export as GLB, OBJ, STL or PLY. → Runs Hunyuan3D 2 Mini by Tencent locally, with Microsoft's Trellis and Tripo AI's TripoSG coming next → Unlimited generations, your images never touch a server → Built-in 3D viewer, collections workspace, multiple export formats → Works with Unity, Unreal, Godot, Blender, ZBrush, Cura, PrusaSlicer, Bambu Studio → Hackable extension system, swap the model or modify the pipeline yourself → Windows and Linux installers ready, macOS coming soon Cloud services charge $20 to $60 a month and upload every photo you give them. This does the same job for free on hardware you already own. 3.5k stars. MIT License. 100% Opensource.

🚀 vLLM-Omni v0.20.0 is out — aligned with upstream vLLM v0.20.0 (CUDA 13.0 · PyTorch 2.11 · Transformers 5.x). ⚡ Qwen3-Omni throughput +72% on H20, 32 conc (0.241 → 0.414 req/s) via talker / code2wav multi-replica scaling 🎙️ TTS faster & leaner: VoxCPM2 RTF 0.946 → 0.106 · Fish Speech Fast AR latency -53% · Qwen3-TTS / Voxtral-TTS Code2Wav saves ~3.2 GiB 🎨 Diffusion dynamic step-level batching: +7.8% throughput / -5.8% latency 🆕 New / improved: HunyuanImage-3.0, ERNIE T2I, AudioX, Wan2.2-S2V, LTX-2.3, FastGen Wan 2.1 📱 Wan2.2 on NPU production-ready: MindIE-SD, fused ops, VAE BF16, HSDP/USP — +50–60% perf 🧮 Quant expanded: Qwen Omni W4A16, OmniGen2 FP8, Z-Image FP8, HunyuanImage3 NPU, GLM-Image 🧩 Multi-backend updates across CUDA / ROCm / MUSA / NPU / XPU Check it out →