Tencent just opened an official integration channel for OpenClaw on QQ, letting users create up to five AI bots per account with a single click. The bots handle text, voice, and file transfers, giving the viral open-source desktop agent a direct bridge to millions of daily chat windows.
Tencent researchers just introduced EffectMaker, a framework that clones visual effects from a reference video onto new subjects. It pairs a multimodal LLM with a diffusion transformer to adapt complex effects without per-effect training, backed by a massive 130k-video dataset.
Tencent Cloud engineers just set up offline pop-up booths at its headquarters to help people install the viral OpenClaw AI agent for free, drawing long lines of retirees and kids. The agent craze has already spawned cottage industries charging up to 1,000 yuan for in-home setups, though some early users reported unexpected cloud service fees.
Tencent just open-sourced HY-WU, a powerful image editing framework designed for high-fidelity virtual try-on and style transfer. It generates on-the-fly LoRA adapters per prompt to dress subjects in reference outfits without test-time fine-tuning, nearly matching Nano Banana. The only hurdle is compute: running its base model currently requires at least four 80GB GPUs.
Tencent just unveiled InteractAvatar, a framework that lets talking digital humans realistically interact with objects around them, like picking up a phone or putting on headphones. Unlike traditional avatars limited to stiff talking-head motions, it supports continuous action prompts with precise timestamps. Why it matters: It turns static talking avatars into truly interactive virtual characters.
Tencent just introduced ScriptAgent, a multi-agent framework that turns dialogue into cinematic videos. Three specialized agents handle scripting, orchestrate video models like Sora2-Pro and Veo3.1 across scenes, and critique visual quality. Why it matters: It universally boosts script faithfulness across top models, tackling one of generative video's biggest pain points—long-horizon narrative coherence.
Tencent just released HunyuanImage 3.0 Instruct, an open-weights image-to-image model that uses chain-of-thought reasoning to plan edit steps and preserve untouched regions before rendering. It handles lighting, perspective shifts, and multi-image merging, though self-hosting its 169 GB weights requires massive VRAM.
Researchers from Tencent just introduced VerseCrafter, a 4D video world model that turns a single image into fully controllable video. By piping 3D Gaussian paths and custom camera rigs straight from Blender into a frozen Wan2.1 diffusion model, creators can finally dictate exact scene choreography without visual degradation.
Tencent just open-sourced HY-Motion 1.0, a 1B+ parameter text-to-motion model built on the Diffusion Transformer architecture and flow matching. It covers over 200 motion categories across 6 major classes and uses a complete pre-training, SFT, and RL loop to generate physically plausible 3D animations ready for typical production pipelines.
Tencent just released Hunyuan3D 3.0, boosting geometric resolution to 1536³ alongside 3.6 billion voxel ultra-HD modeling. The update introduces lifelike facial contouring and a layered generation strategy that reconstructs complex, hidden structures with high texture fidelity. Users can try 20 free generations on the Hunyuan 3D AI Engine or access it via Tencent Cloud API.
Tencent just open-sourced HunyuanVideo-Foley, an end-to-end text-and-video-to-audio framework designed to generate realistic Foley sound effects for videos. Trained on 100,000 hours of multimodal data, it uses an MMDiT architecture to tightly align sound with visual motion, outperforming existing open-source baselines in audio quality and temporal alignment.
Tencent Hunyuan just open-sourced Hunyuan3D World Model 1.0, an industry-first model that turns a single prompt or image into an explorable, interactive 3D scene. It connects directly with standard CG pipelines for editing and simulation, built to speed up game dev and VR creation.
Tencent Hunyuan just launched Hunyuan 3D 2.1, labeling it the first fully open-source, production-ready PBR 3D generative model. It generates realistic materials like leather and bronze with full physics-based lighting, releases all weights and training code, and runs straight on consumer-grade GPUs.
Tencent Hunyuan and Tencent Music just open-sourced HunyuanVideo-Avatar, a new model that brings static photos to life from audio clips. It automatically reads scene context and emotion to generate lifelike speech or singing videos up to 14 seconds long. The single-character mode is out now, with multi-character interactions coming soon.
Tencent just upgraded its Hunyuan 3D AI Creation Engine to v2.5, bumping the geometric model from 1B to 10B parameters with 10x more mesh faces. It introduces multi-view PBR generation, automatic bone binding, and doubles daily free generation quota to 20.
Tencent just rolled out a major upgrade to its Hunyuan T1 deep reasoning model, boosting its project-level code generation and text writing capabilities. The update also sharpens multi-turn comprehension, instruction following, and the handling of mixed Chinese and English text. You can test it out right away on Tencent's platform or Hugging Face.
Krea just officially launched a 3D generation feature alongside a complete website redesign. Users can now turn text prompts and 2D images directly into 3D assets ready for export to Blender or Unity. Industry insiders speculate it may borrow from Tencent's Hunyuan tech, marking a big push from 2D images into full 3D creative workflows.
Tencent Hunyuan just unveiled Hunyuan-TurboS, an ultra-large MoE model blending Transformer and Mamba architectures to ease long-context training and KV-cache overhead. The team claims it tops GPT-4o and DeepSeek-V3 in math and reasoning, all while cutting inference costs to one-seventh of its predecessor.
Tencent Hunyuan just open-sourced HunyuanVideo-I2V, releasing weights, inference code, and LoRA training scripts. The 13B parameter model turns a single image into a 5-second 2K clip complete with background audio, and even handles motion driving and lip-syncing. It is available on GitHub and HuggingFace, with a web demo open to the public.
Tencent just open-sourced Hunyuan3D 2.0, a two-stage foundation system for generating detailed, textured 3D meshes from single images. By decoupling geometry creation via a DiT shape generator from texture baking with a dedicated diffusion model, it can also texture handcrafted meshes, beating previous open and closed-source baselines.
