#开源生态

Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier quality in a lightweight package. Highlights: 👀 - Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs. - Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images. - Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products. - Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography. Start to create your next masterpiece with Qwen-Image-2.1! 🖼️ - Blog: https://qwen.ai/blog?id=qwen-image-2.1 - GitHub: https://github.com/QwenLM/Qwen-Image-2.1 - Model Scope: https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1 - Hugging Face: https://huggingface.co/Qwen/Qwen-Image-2.1

At Apsara Conference 2026 in Hangzhou, Alibaba CEO Eddie Wu shared our strategic roadmap for the Machine Intelligence era: - Scaling to 1,000x human capacity leaves an enormous growth runway ahead. - Machines are becoming the primary force behind Thinking. - Machine Thinking is currently <3% of all Human Thinking.

Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier quality in a lightweight package. Highlights: 👀 - Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs. - Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images. - Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products. - Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography. Start to create your next masterpiece with Qwen-Image-2.1! 🖼️ - Blog: https://qwen.ai/blog?id=qwen-image-2.1 - GitHub: https://github.com/QwenLM/Qwen-Image-2.1 - Model Scope: https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1 - Hugging Face: https://huggingface.co/Qwen/Qwen-Image-2.1

MiMo-V2.6-Pro just landed @XiaomiMiMo back in the top 10 on Code Arena: WebDev, debuting at ~#10 overall, and ~#3 among open-weights models with an MIT license. It scores 1628 pts (AutoEval), tying Claude Fable 5 (High) and just ahead of Hy4-preview (1624 pts). That's a +153 pt jump from the previous MiMo-V2.5-Pro (1475 → 1628 pts). Among open-weights models, it lands at ~#3. Impressively only 7 pts behind Qwen3.8 Flash Next (#2) and 46 pts behind Kimi K3 Max (#1). Note: this is an early AutoEval score, in which a Reward Model trained on Arena’s human preference data casts automatic votes in place of live votes. We’ll continue to see how scores converge as more live human votes come in. Congrats to the @XiaomiMiMo team on this release!

隆重介绍小米 MiMo-V2.6 —— Pro 与 Flash。 前沿智能，全模态，公开构建。 🔹 两款全模态模型，通过规模化强化学习不断进阶 🔹 在大多数智能体基准测试中，Pro 的表现与 Claude Opus 5 和 GPT-5.6 Sol 不相上下 🔹 Pro 在 Artificial Analysis Intelligence Index 上得分 46 —— 为开源模型中的最高分 🔹 更强的编程、计算机操作、3D 推理与创作能力 🔹 开放模型权重、技术报告、RL 环境与训练代码 博客：https://mimo.xiaomi.com/mimo-v2-6

MiMo-V2.6-Pro 首次亮相，即成为 Artificial Analysis Intelligence Index 上排名第一的开放权重模型（46 分）。每项 Intelligence Index 任务成本为 $0.13，使其跻身智能水平与每任务成本帕累托前沿。 @Xiaomi 刚刚发布了 MiMo-V2.6-Pro，这是一款开放权重模型，相比其前代 MiMo-V2.5-Pro（Intelligence Index：26），在智能水平上取得了重大进步。尽管有所提升，它仍保持了同样具有吸引力的定价：每 1M 输入 token 为 $0.435（含 99% 缓存命中折扣），每 1M 输出 token 为 $0.87。这使 MiMo-V2.6-Pro 成为部署成本效益最高的模型之一。 MiMo-V2.6-Pro 是一款 MoE 模型，总参数量为 1.02T，激活参数量为 42B。敬请期待对该模型的更多分析。 在此查看 MiMo-V2.6-Pro 的完整基准测试详情：https://artificialanalysis.ai

Qwen Image 2.1 来了！🖼️ 一个 7B 参数的原生图像生成与编辑模型，最多支持 10 张图像参考 该模型自带提示词增强 LLM，已集成 diffusers 🧨 和 ComfyUI ▶️ 在 Spaces 上 https://huggingface.co/spaces/hugging-apps/qwen-image-2-1

Day-0 support for @Alibaba_Qwen’s Qwen-Image 2.1 is here in SGLang-Diffusion! 🖥️ Native precision on a single RTX 4090 24GB with CPU offload - 1024×1024 generation in 18.7s and image editing in 21.7s with 22.7 GiB peak GPU memory during requests. - On an RTX PRO 6000 96GB: 8.0s generation and 9.6s editing. 🎨 Text-to-image, multi-image editing, and transparent RGBA output—all with one checkpoint. ⚡ Native inference with TP/SP, LoRA, and OpenAI-compatible APIs. 40 denoising steps, one image per request, warmed HTTP latency including PNG output. No quantization. Cookbook and GPU-specific commands below 👇

Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉 Generate, edit, and create transparent images with one model: a 7.1B DiT paired with Qwen3-VL-8B. Setup and supported combinations 👇 https://recipes.vllm.ai/Qwen/Qwen-Image-2.1

Qwen-Image-2.1 现已在 ComfyUI 中支持！ 开放权重。一个 7B 检查点即可生成和编辑。 → 原生 2K 图像生成 → 单次处理中基于最多 10 张参考图像的指令编辑 → RGBA 输出，包含 alpha