[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-mrflow-four-step-t2i":3,"news-related-e9688664-6ec6-4816-8898-3a92e6638c7a":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"e9688664-6ec6-4816-8898-3a92e6638c7a","MrFlow：四步分阶段采样把文生图扩散推到 10× 加速，OneIG 损失压到 1%","北航郑星宇等人在 arXiv 2607.01642 提出 MrFlow —— 一种完全 training-free 的多分辨率扩散加速方案。FLUX.1-dev、Qwen-Image 把文生图质量推到开源 SOTA，但每张图动辄要跑几十步 denoising，推理成本成为落地的主要门槛。timestep distillation 需要为每个底模重新训练；现有 training-free 多分辨率方案在潜空间上采样，又常出现明显模糊与伪影。MrFlow 把推理拆成四步显式流水线：低分辨率主体生成 → 像素空间 GAN 超分 → 低强度噪声注入 → 高分辨率细节精修，无需训练、无需运行时动态判别。在 FLUX.1-dev、Qwen-Image 上实现 10× 端到端加速，OneIG 损失控制在 1% 以内；与 timestep distillation 正交叠加可达 25×。这是半年内 diffusion 加速路线里少见的\"真正可落地\"方案 —— 不绑模型、不依赖定制 kernel，对开源社区尤其友好，暗示了\"加速可以一层一层叠加\"的新范式。代码已开源至 GitHub（Xingyu-Zheng\u002FMrFlow）。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.01642","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":21,"name":22,"slug":22,"description":13,"color":13},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"9bed4383-ee98-4c28-ba59-b825c475c5ad","en","MrFlow: staged sampling gives 10x text-to-image speedup","Zheng Xingyu et al. at Beihang University, in arXiv 2607.01642, propose MrFlow — a completely training-free multi-resolution diffusion acceleration scheme. FLUX.1-dev and Qwen-Image have pushed text-to-image quality to open-source SOTA, but each image often requires dozens of denoising steps, making inference cost the main barrier to landing. Timestep distillation requires retraining for each base model; existing training-free multi-resolution schemes often exhibit obvious blur and artifacts when upsampling in latent space. MrFlow splits inference into an explicit four-step pipeline: low-resolution main body generation → pixel-space GAN super-resolution → low-strength noise injection → high-resolution detail refinement, no training, no runtime dynamic discrimination needed. On FLUX.1-dev and Qwen-Image, it achieves 10× end-to-end speedup with OneIG loss controlled within 1%; orthogonal stacking with timestep distillation can reach 25×. This is a rare \"truly landable\" solution in the past half year's diffusion acceleration routes — not tied to a model, not relying on custom kernels, especially friendly to the open-source community, hinting at a new paradigm of \"acceleration can be stacked layer by layer\". Code is open-sourced on GitHub (Xingyu-Zheng\u002FMrFlow).","mrflow-four-step-t2i","2026-07-04T14:11:00Z","2026-07-04T14:12:49.654750Z","2026-08-19T02:08:40.142862Z",true,"agent",92,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"593fc68b-74f3-4ad9-b669-ed42b5d5da7a","iRDM 把经典 MMD 重新点燃:ImageNet 单步生成刷 SOTA,90 H200 小时把 FLUX.2 [klein] 蒸馏成一步","irdm-mmd-single-step","2026-07-06T06:30:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"ce1ba4c1-7d9f-470c-86f3-9cabc8e69e0a","字节DanceOPD把图像生成多能力冲突变成「场蒸馏」：硬路由+单查询就赢","bytedance-danceopd-field-distillation","2026-06-28T04:30:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"a6119d74-007a-4692-bb4e-d85b562a9d66","字节 SpectraReward：自我奖励 T2I 干翻 30× 大模型","bytedance-spectra-reward","2026-07-15T04:30:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"06110002-82fb-421e-9daf-5ab73ead7f27","FourTune：把扩散模型后训练压进 4-bit，W4A4G4 让 FLUX.1-dev 12B 内存砍半、吞吐翻倍","fourtune-4bit-flux-12b","2026-07-09T00:01:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"52e96e5b-ec3b-4552-b94a-93cc2702ab84","Flow-Map GRPO：为确定性「少步生图」打开强化学习大门","flow-map-grpo-few-step","2026-07-05T12:02:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"0e44f256-e66e-495c-82e3-aae4dd5e2374","LiveEdit 把扩散视频编辑推到 12.66 FPS：清华让 AR 实时编辑走出 PPT","liveedit-ar-video-editing","2026-07-01T06:15:00+00:00"]