通义千问发布 Qwen-Image-2.1-Turbo，8 步去噪生成与编辑图像并开放权重
🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available! Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture. Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene. Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go. 🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow. 🤖 ModelScope: https://t.co/Cixiro51v8 🤗 Hugging Face: https://t.co/4GqXcYeAmB 🔗 Pro API: https://t.co/fw2am7VCP7 🔗 Turbo API: https://t.co/qmDvTqiVZK What will you create with 8 steps? Share your results with us!
通义千问发布 Qwen-Image-2.1-Turbo，可在 8 步去噪内完成图像生成与编辑，并已开放权重。该模型基于 Qwen-Image-2.1，是同一 7B 视觉生成架构上的加速 checkpoint，仍能由文本生成 2K 图像，并支持通过自然语言编辑继续创作，例如添加配饰或改变场景。
官方放出 Qwen-Image-2.1-Turbo 开源权重和 8 步采样配置，适合上手实测 8 步出图与自然语言改图的效果。
- 浏览
- 72万
- 点赞
- 5311
- 评论
- 210
- 分享
- 535
- 收藏
- 4063
约为这个来源平时的 15 倍，是爆款
数字来自平台，为最近一次抓取时的数据。
来源：X · 通义千问 Qwen · x.com