[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@TencentHunyuan Tencent HYTencent HY posts on X about tencent, ai, native, $0700hk the most. They currently have XXXXXX followers and XXX posts still getting attention that total XXXXX engagements in the last XX hours.
Social category influence technology brands
Social topic influence tencent #25, ai, native #530, $0700hk #25, context window, shoutout, generative
Top accounts mentioned or mentioned by @txhunyuan @eric_ai_tencent @huggingface @comfyui @lmarenaai @latentspacer @whispers322 @chinamianyang @nimvideo @fal @hungrydonke @kijaidesign @deepbeepmeep @jikkujose @stanford @lllyasviel @camenduru @arena @qian @derekwall90176
Top posts by engagements in the last XX hours
"Tencent HY XXX is officially released. We are rolling out a major performance upgrade to our foundation model now available via Tencent Cloud API. Built on a Mixture-of-Experts (MoE) architecture (406B total 32B active parameters) and featuring a 256K context window HY XXX delivers significant gains across key benchmarks. HY XXX Highlights: 🧠Reasoning: Achieved XXXX on the IMO-AnswerBench (up nearly 20%) establishing top-tier math and scientific logic capabilities. 🛠Coding & Agents: Explosive growth with SWE-bench Verified scoring XXXX (from 6.0) and Tau2Bench reaching XXXX (from 17.1)."
X Link 2025-12-05T14:21Z 30.7K followers, 44.3K engagements
"Moving forward Tencent Hunyuan is now officially Tencent HY. Same powerful AI a simpler name"
X Link 2025-12-09T07:47Z 30.7K followers, 132.2K engagements
"Today we are open-sourcing Hunyuan World XXX (WorldMirror) a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World XXX (open-sourced lite version deployable on consumer GPUs) focused on generating 3D worlds from text or single-view images Hunyuan World XXX significantly expands the input scope by unlocking video-to-3D and multi-view-to-3D world creation. Highlights: 🔹Any Input Maximized Flexibility and Fidelity: Flexibly integrates diverse geometric priors (camera poses intrinsics depth maps) to resolve structural ambiguities and ensure"
X Link 2025-10-22T09:33Z 30.7K followers, 168.4K engagements
"We are excited to unveil HunyuanVideo XXX the strongest open-source video generation model. Built upon DiT architecture it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo XXX delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡ Unmatched Accessibility: Ultra-light 8.3B parameters deployable on consumer GPUs with only 14GB VRAM. 🖥 HD Cinematic Quality: Natively generates XXX second 480p/720p HD videos with super-resolution support for 1080p cinematic quality. By merging"
X Link 2025-11-21T04:12Z 30.7K followers, 106K engagements
"We are officially taking Hunyuan 3D Engine global 🌎 Responding to community demand and building on open-source acclaim Hunyuan 3D capabilities are now launching globally to empower all creators and enterprises This next-gen AI platform cuts commercial-grade 3D asset production from days or weeks down to minutes. 🎨Multimodal Input: Instantly generates from Text-to-3D Image-to-3D (multi-view support) or Sketch-to-3D. 💡Pro-Ready Quality: Achieves industry SOTA with our new 3D-DiT hierarchical carving model delivering a 3x boost in modeling precision (up to 15363 ultra-HD resolution). Seamless"
X Link 2025-11-26T02:05Z 30.7K followers, 88.6K engagements
"🗣Hunyuan: A Global Pronunciation Challenge (Until Now.) ✅ Meet Tencent HY"
X Link 2025-12-11T05:14Z 30.7K followers, 4762 engagements
"Awesome🤩 Let's get started with Hunyuan 3D model to generate your own custom figurines"
X Link 2025-12-02T12:34Z 30.7K followers, 8259 engagements
"🤩HunyuanOCR is trending on Hugging Face within its first week of release The model achieves SOTA performance with only X billion parameters making high-efficiency OCR accessible to everyone. Huge thanks to the open-source community for the incredible support 🎉 Project Page: (web) (mobile) Model: Demo: Technical Report:"
X Link 2025-12-03T08:53Z 30.7K followers, 22.7K engagements
"Huge shoutout to @kohya_tech 🙌 Custom I2V training is fully supported Time to build your own models"
X Link 2025-12-04T04:04Z 30.7K followers, 9894 engagements
"Hunyuan3D Plugin is now FREE on Tencent Cloud ADP until Christmas.🎄Let's build something awesome"
X Link 2025-12-08T07:45Z 30.7K followers, 19.2K engagements
"We are thrilled to open-source HunyuanOCR an expert end-to-end OCR model built on Hunyuan's native multimodal architecture and training strategy. This model achieves SOTA performance with only X billion parameters significantly reducing deployment costs. ⚡Benchmark Leader: Achieves a SOTA score (860) on OCRBench for models under 3B parameters and a leading XXXX on OmniDocBench for complex document parsing. 🌐Comprehensive OCR Capabilities: Extends beyond simple text recognition to handle text spotting (street view handwriting art text) complex document processing (tables/formulas in"
X Link 2025-11-25T06:18Z 30.7K followers, 145.2K engagements
"🚀🚀🚀Hunyuan 3D Studio just leveled up to XXX We've integrated the art-grade 3D generative model Hunyuan 3D-PolyGen XXX to deliver the industry's most advanced mesh quality directly to your workflow. 🎨 🖌 Art-Grade Quad Mesh: We've pioneered an end-to-end native quad mesh generation method. Unlike older methods that generated only tri-meshes PolyGen XXX directly learns quad topology to produce cleaner continuous edge loops and superior wireframe quality. 🎮 Professional Viability: Achieving this topology standard makes models instantly production-ready for game artists 3D designers and"
X Link 2025-11-28T03:59Z 30.7K followers, 55.9K engagements
"💡HunyuanVideo1.5 Update: We are now releasing the 480p I2V step-distilled model which generates videos in X or XX steps (recommended) On RTX 4090 end-to-end generation time is reduced by XX% and a single RTX 4090 can generate videos within XX seconds. The step-distilled model maintains comparable quality to the original model while achieving significant speedup. For even faster generation you can also try X steps (faster speed with slightly reduced quality). 🔗Check out the GitHub Repo:"
X Link 2025-12-05T15:32Z 30.7K followers, 37.5K engagements
"Check out a comprehensive overview of the Tencent HY Model Family 🧠✨"
X Link 2025-12-11T12:53Z 30.7K followers, 10.8K engagements