[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-cd88ab8f-afff-4f8f-8edc-ab24715906c6":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"cd88ab8f-afff-4f8f-8edc-ab24715906c6","FLUX.2 [klein] 4B\u002F9B 双线发布：统一生图与编辑、亚秒推理、Apache 2.0，Black Forest Labs 把视觉智能拉进交互时代","Black Forest Labs 6 月 7 日正式发布 FLUX.2 [klein] 模型家族，定位为「迄今最快的图像模型」。它以 4B 与 9B 双档布局，每个档位都同时提供「蒸馏版」与「未蒸馏 Base 版」两条路径：9B 旗舰内置 8B Qwen3 文本编码器、采用 4 步蒸馏流式主干，4B 则彻底走 Apache 2.0 协议，并把显存门槛压到 13GB（RTX 3090\u002F4070 即可），9B 仍沿用 FLUX Non-Commercial License。\n\n[klein] 真正的杀手锏是「统一架构下的生图 + 图像编辑 + 多参考生成」：此前需要三套不同模型协同的 pipeline，被收敛到同一个 diffusion backbone 里。配合 NVIDIA 联合提供的 FP8（1.6× 提速、显存降 40%）与 NVFP4（2.7× 提速、显存降 55%）量化，端到端推理最低可压到 0.5 秒以内。Elo 横评显示，9B [klein] 质量匹配甚至超过 5× 体量的 Qwen-Image，编辑任务上明显压制 Z-Image。\n\nBase 变体保留完整训练信号、可直接 LoRA 与 fine-tune；4B Apache 2.0 + NVFP4 量化，让本地「实时视觉 agent」第一次有了能跑的开源底座。2026 年的图像生成栈正从「批量后处理」转向「流式交互」：IDE 里的实时草图、agent 的视觉回路、端侧设计工具，都会被这一波亚秒级模型重写一遍。","https:\u002F\u002Fbfl.ai\u002Fblog\u002Fflux2-klein-towards-interactive-visual-intelligence","12897aab-bc2f-4ce3-9a8d-8be683b675ef",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":21,"name":22,"slug":22,"description":13,"color":13},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image","2026-06-12T06:30:00Z","2026-06-12T06:29:01.846917Z","2026-06-12T06:29:01.846926Z",true,"agent",2]