
野西大人
63 posts

野西大人
@xiaobei1943
🎬 AI短片创作者 🚫 原创不跟风 | 拒绝一切热点 🎁 好故事值得等待 | 不定期掉落 👇 点击关注,一起入梦






Wan 2.2ベースでftのt2iなら素性良さそう!


We're excited to announce the the open-source release of Hunyuan-MT-7B, our latest translation model that just won big at WMT2025! 🚀🏆 Hunyuan-MT-7B is a lightweight 7B model that's a true powerhouse. It dominated the competition by winning 30 out of 31 language categories, outperforming much larger models under strict open-source and public-data constraints. On the widely-used Flores200 benchmark, its performance rivals closed-source models like GPT-4.1.🌍💬 Why is this a game-changer? 🔹Unmatched Efficiency: The 7B model delivers lightning-fast inference, processing more translation requests on the same hardware. 🔹Deployment Flexibility: It's cost-effective and can be deployed on a wide range of hardware, from high-end servers to edge devices. 🔹Broad Language Support: It supports 33 languages and 5 minority languages, providing comprehensive coverage. But that's not all. We're also open-sourcing Hunyuan-MT-Chimera-7B, the industry's first open-source integrated translation model. It intelligently refines translations from multiple models to deliver more accurate and professional results for specialized use cases. Download and deploy it for your next project! 👉Try it now: hunyuan.tencent.com/modelSquare/ho… 🔗Code: github.com/Tencent-Hunyua… 📄Technical Report: github.com/Tencent-Hunyua… 🤗Hugging Face: huggingface.co/tencent/Hunyua… 🔧AngelSlim: github.com/Tencent/AngelS…


千问开源了 Qwen-Image-Edit 图像编辑模型。 基本上 FLUX Kontext 能做的他都能做,而且还能编辑和生成中文。 等 lora 训练工具上了的话估计又会有很多新玩法了。

照片重要性,跟设备没啥关系😅

















