Press Space to continue
Press Space to continue
A free 7B model just outscored Google's flagship image generator. The entire thing fits on a USB stick. Qwen's benchmark run puts Qwen-Image-2.1 at 60.28. Nano Banana 2 scores 59.82. GPT Image 1.5 sits at 59.65. Google and OpenAI serve their models from data center clusters. This one runs on a single consumer GPU. The technical trick is a 20-layer single-stream DiT that handles generation and editing in one pipeline. Most labs ship those as two separate models. Collapsing both into 7B…
Alibaba_Qwen@Alibaba_Qwen1d ago
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://t.co/tVntKOi7jy - GitHub: https://t.co/cRj66wCrWr - Model Scope: https://t.co/64d7Ix6YFR - Hugging Face: https://t.co/njHSBXUbVS
