ModelScope

@ModelScope2022

Driving innovations with open communities. 💬 Join our Discord: discord.gg/hgKcfgXHAQ

HangZhou, China

modelscope.ai

Replies Reposts Media Articles

Pinned
ModelScope
@ModelScope2022
Sep 21
ModelScope now supports both inference and LoRA training for Qwen-Image-2.1 in the Civision.🎉 Jump in and start creating!👉modelscope.ai/civision
5
ModelScope
@ModelScope2022
15h
Apsara 2026 is ON 🔥 Come find the ModelScope booth, snap a pic, and take home some merch: 🎒 Backpacks · Crossbody bags · Tote bags 🛋️ Neck pillows · ☕ Mugs · 💻 Laptop stands 🧸 Plush pendants · 🧢 Hats · 🧲 Fridge magnets 🎧 Earphone pouches · 📱 Phone chains ...and more.
ModelScope
@ModelScope2022
Sep 21
Qwen introduces RecreationBench, a benchmark for Hybrid Computer-Use Agents with 250 application-recreation tasks across Ubuntu, macOS, Windows, Android, and Web, spanning domains such as productivity, development, graphics, multimedia, and science. Unlike GUI-only or
6
ModelScope
@ModelScope2022
Sep 20
Introducing Qwen-Image-2.1: image generation and editing in one model, with native transparency and a compact 7B visual generation component.🚀 🤖 modelscope.ai/models/Qwen/Qw… 🎨 Try it in Studio: modelscope.ai/studios/Qwen/Q… ⚡ Efficient inference: KV cache reuse speeds up generation and
11
ModelScope
@ModelScope2022
Sep 20
NetEase-Youdao releases Confucius4-R2T2, a true-streaming ASR model for live captions, simultaneous translation, and voice agents. 🤖 modelscope.ai/models/netease… 🏆 R2T2 achieves SOTA latency and recognition quality among the evaluated open-source models, while remaining competitive
00:00
2